A number of geospatial companies played a key role in the government’s response to the Kilauea Volcano eruption. The volcano on the Big Island of Hawaii began erupting May 3, and while quiet for more than a week, it could resume erupting at any time.
Mapping the flow. As a resident of Hawaii, Brennan O’Neill, Hawaiian branch manager of Frontier Precision, was in a unique position to offer support. Frontier Precision provided free access to technology and expertise to assist in mapping the lava flow.
“I had to help out,” O’Neill said. “It was tearing at my soul. For a geologist, it’s even more powerful than that. The lava flow is like a living mass that has a mind of its own, creeping, glowing — an upside-down conveyor belt surging forward and burning everything in its path.”
Through Frontier Precision, O’Neill offered high-tech mapping equipment, his own expertise, and the help of Nathan Stephenson, an applied geospatial engineer working in the company’s Denver office.
“We used a combination of Trimble R10s and Trimble R8s to gather accurate data points on the ground,” Stephenson said.
This thermal map shows the fissure system and lava flows as of 6 a.m. on Saturday, Aug. 11. The thermal map was constructed by stitching many overlapping oblique thermal images collected by a handheld thermal camera during a helicopter overflight of the flow field. The base is a copyrighted color satellite image (used with permission) provided by Digital Globe. (Map: USGS)
The mapping team flew UAS drones over the flow to gather visual imagery data, matched it to the ground reference points, stitched the photos together and draped it over county maps. The process was repeated as often as needed — daily, and sometimes even hourly — to show the speed and direction of the flow.
Stephenson isn’t new to mapping lava flows. As a graduate student at the University of Hawaii – Hilo, he worked on collecting data on the Pahoa eruption in 2014, and he’s seen advances in technology in just a few years.
“One thing we have now that we didn’t have in 2014 was a thermal radiometric camera that helps us map more accurately at night and enables us to capture large heat signatures.”
The collected data helps Hawaii Civil Defense and other agencies keep the public informed and safe, and in the long term it also contributes to the store of scientific knowledge about eruptions and lava flow behavior.
Lidar image of the Hawaii dataset showing the Kilauea Calderand the Halena’uma’u Crater and within it. (Image: Quantum Spatial)
Airborne lidar insights. Another technology that aids in volcano response is lidar. High-resolution lidar surveys help first responders, scientists and government agencies monitor Kilauea conditions and predict future lava flows.
Independent geospatial data firm Quantum Spatial Inc. (QSI) has conducted high-resolution lidar surveys of areas surrounding the Kilauea volcano eruption in Hawaii.
The emergency response effort was part of the U.S. Geological Survey’s (USGS) Rapid Response Imagery Products (RRIP) in support of the Kilauea’s 2018 East Rift Zone – Remote Sensing Acquisition Requirement.
The USGS Hawaiian Volcano Observatory (HVO), along with emergency responders, government agencies and academics, will use the data to better understand the conditions and characteristics of the volcano, and help planners model potential lava flows, which may better predict and respond to future flows and enhance safety of residents.
The QSI team, which included GEO1 and Windward Aviation, deployed within days to acquire high-resolution lidar at point densities averaging from 40 to 80 ppsm, with up to 150 ppsm in select areas and 100-mp digital imagery using a Riegl dual VUX-1 LR sensor pod equipped with ABGPS/IMU mounted on a Hughes 500D helicopter.
The project required 11 missions over the course of six days, operating at times as low as 500 feet above the ground and above active flows and nearby erupting calderas. With a need for a quick turn around, QSI deployed an analyst with the flight crew to post process each mission within hours of collection.
The data was uploaded to the Geospatial Repository and Data Management System (GRiD) interface, developed by the U.S. Army Corps of Engineers (USACE), where additional data products have been developed and provided to the response team that includes FEMA, Hawaii’s Emergency Operations Center (EOC) and the Hawaii County Civil Defense.
After data collection, QSI measured topographic shifts during the processing by comparing new data with a 2011 lidar collection from the same area. Survey specialists and USGS experts confirmed within hours of processing QSI’s lidar data that areas within the site had shifted up to 1.5 meters east, 2 meters to the north and 1 meter in elevation.
USGS scientists will continue to examine the new topographic data to better understand the nature of these shifts, and integrate it into lava flow models for more accurate predictive modeling.
The eruption in action. Using small unmanned aerial systems (sUAS) together with air-quality sensors, advanced imaging tools and Esri’s spatial analytics and mapping, a team from the Center for Robot-Assisted Search and Rescue (CRASAR) provided real-time aerial views of the eruption.
The five volunteers armed with drones, advanced sensor systems and GIS technologies joined the response effort May 14-19 at Kilauea Volcano Lower East Rift Zone to assist in tracking and predicting the ongoing volcanic eruption. The team supplemented the University of Hawaii Hilo’s (UHH) sUAS capabilities, allowing UHH sUAS operators to focus on geographical and volcanology.
The CRASAR team identified a new fissure not visible from the ground, projected the lava flow rate during the night when manned helicopters were not allowed to fly, and provided ongoing data collection from new thermal sensors technology.
During the six-day Leilani deployment, the CRASAR team flew 44 sUAS flights, including 16 at night, using DJI 200, 210, Inspire, and Mavic Pro drones. Esri’s Drone2Map for ArcGIS together with Hangar’s Enterprise Platform for 360-degree imaging enabled rapid 360-imaging for situational awareness.
DJI’s new XT2 thermal sensor provided unprecedented drone-based air-quality monitoring. Video and data were shared with local first responders using FirstNet, the first high-speed, nationwide wireless broadband network dedicated to public safety.
The CRASAR response marks the first known use of sUAS for emergency response to a volcanic eruption and first known use of sUAS for sampling air quality.
The GIS mapping and imaging technologies responders used on the scene at Kilauea Volcano Lower East Rift Zone are available here.
A voter enters a polling place. (Image: iStock.com/YinYang)
With the mid-term elections coming ever nearer, states are turning to geographic information systems (GIS) to help manage them.
Digital geographic representation of precinct boundaries within a GIS allow for transparency and ease of use for voters, candidates and electoral management, according to the National States Geographic Information Council (NSGIC).
GIS also enables the optimal siting of polling places for both voter access and the cost efficiency of operating polls.
Finally, GIS provides a platform for automated quality-control processes that ensure accurate voter precinct assignments.
“An electoral system with integrity — enhanced by accurate, authoritative geographic data and presented clearly and transparently — has never been more important,” said NSGIC President Andy Rowan.
Why GIS is an improvement over address files
NSGIC’s Geo-Enabled Elections project brings together geographic information systems (GIS) leaders in state government, local elections officials and state elections offices, national GIS and elections organizations, and federal partners to identify opportunities to integrate GIS into elections systems across the country.
The overall goal is to strengthen elections management and citizen engagement. The project aims to provide the impetus for replacing non-spatial “address file” tables with the visual and analytical advantages of election precinct and voter data in a natively GIS format.
Geo-enabled elections overcome the four fundamental challenges with the existing address list approach to precinct management, according to Rowan.
In the address list approach, Rowan said,
No actual boundaries are stored explicitly in the systems,
Quality control is difficult without a method to visualize precinct assignment using aerial photography and boundary information that can change frequently,
There is no efficient method for applying large-scale precinct boundary updates, and
The process is usually not aligned efficiently with other state and local address or boundary-management processes.
To this end, the project conducted a nationwide survey on elections data in the first half of this year. More than two-thirds of states responded.
Here are key takeaways from the baseline survey.
Addresses
The survey found that 55 percent of responding states confirm voter registration addresses against a database of known addresses such as a driver’s license or state ID database, a statewide point address set, a master address database used for 911 call routing, or a commercially available address database.
“The results indicate a need to advocate for coordination between state agencies (such as the state elections department and the department of motor vehicles) and encourage integration of the voting system and other systems,” said Jamie Chesser, the Geo-Enabled Elections project manager.
Election Precincts
More than half of responding states indicated they maintain statewide mapping of precincts. Within this group, 40 percent also maintain a layer of sub-precincts in digital mapping systems.
“There remains a need to develop local precinct data content and procedural standards to examine the relationship between precincts, local and state boundaries, and residential structures,” Chesser said.
Other Data
In all, 82 percent of states keep up-to-date spatial data of city and county boundaries, which is essential for computer-based mapping of precincts.
“Statewide spatial data — especially city, county, school, and special district boundaries – are essential to mapping precinct boundaries across the state,” Chesser said. “The survey reflected, however, that accuracy of current city and county boundary mapping varies
considerably.”
A substantial majority, 79 percent of respondents, confirm their mapping of state-level district-based elected offices are accessible online in a digital mapping format.
Survey responses were coordinated by state government representatives who focus on the development and deployment of mapping data and systems across state agencies and local governments.
Later this year, NSGIC will release the results of a study probing the spatial approach to elections management from the perspective of state elections officials.
The two-year Geo-Enabled Elections project, underwritten by the bipartisan Democracy Fund Voice, convenes a wide variety of stakeholders to explore ways geographic information systems and related processes can enhance elections management and citizen engagement across the U.S.
A little more than a decade ago, the IT world began to buzz about the next big thing, a concept called service-oriented architecture (SOA). SOA promised a better way to build enterprise applications, delivering efficiency, business agility and fluid communication — a near revolution in business workflows. Such was its promise that business executives — not just CIOs — began to ask, How do I get an SOA?
In the fog of excitement, few executives asked the more appropriate question: What exactly is an SOA? Is it an off-the-shelf product, an IT methodology, a business philosophy? And where does it belong in my organization — do I need a strategy to drive business value from it?
Today, artificial intelligence (AI) triggers similar levels of excitement, with a chaser of fear. In a recent survey by New Vantage Partners, C-level executives crowned AI the most disruptive technology — far outranking cloud computing and blockchain. And nearly 80 percent of those executives fear competitors will harness AI to outflank their business.
An Executive Checklist for AI in the Enterprise
Create a strategy. AI is already making an impact in the enterprise — via chatbots, virtual assistants, and other point solutions. Experts advise executives to establish a framework for how AI will be incorporated into business strategy and processes, and to define measurable goals.
Apply executive support. Assign a C-level executive to oversee the company’s strategy. “When companies are looking to do fundamental digital transformations and reinvention of the business, there is incredible value in having top-down guidance drive much of that activity,” says Microsoft’s Joseph Sirosh.
Mind the data. “Predictions will be accurate only if the training data used to teach the AI prediction model is truly representative of the target cases being classified or predicted,” explains Esri’s Sud Menon. “AI is a data-driven game, hands down.”
Incorporate robust datasets, including location information. In nearly all its forms, business data can become more valuable when coupled with information about its location. This form of geoenrichment is especially useful for AI models, which can discover insight that humans might overlook. (See “A Business Case” in the article.)
From an executive’s perspective, now is the time to answer critical questions: What is AI, what can it do for my business, and who should be responsible for its development and strategic alignment?
AI in the Enterprise
Although 93 percent of businesses are investing in artificial intelligence, not all are using it in the same way or toward the same end, says Sud Menon, director of software product development at Esri. “AI is a very broad term, and businesses are adopting different aspects of it at different rates,” Menon notes.
Sud Menon, Esri
When envisioning how AI can deliver value to their enterprises, business executives should think of three primary processes, according to Menon and Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft: internal business operations, customer interactions, and business planning. Interestingly, a survey by Tata Consultancy Services found that high-performing companies are more likely to focus their AI efforts on internal operations, while AI followers tend to concentrate on customer interactions.
Regardless, each process is being transformed with help from cloud computing, data, and intelligent algorithms that power AI. Here are a few examples of how:
Internal Operations. AI is improving companies’ internal operations in several ways. In some workplaces, AI-based facial recognition systems regulate employee access to secure areas. Predictive maintenance systems run by AI help determine the optimal service schedule for fleets of delivery vans. And AI-infused bots are performing HR tasks that once required human intervention, such as guiding employees through the steps of changing their last name, or adjusting the allocation of their 401k plan. The bots connect to systems of record like ERP and HR software, analyze pertinent data, and lead employees through an intuitive workflow.
Customer Interactions. AI is adding intelligence to some customer-facing tasks. For example, AI powers many of the recommendation systems that suggest a relevant product or a message to a website visitor who lives in a particular location. It anchors security systems that recognize a fraudster’s voice signature or suspicious online activity in real time and deny the person access to an online account. And it supports the chatbots that interact with millions of consumers online each day.
Business Planning. For executives and decision-makers looking for strategic guidance, AI can predict shifts in supply and demand and how businesses might react. To plan next quarter’s operations, the technology can sift through customer purchasing habits and factors such as planned competitor stores to predict sales, product mix, and staffing levels. Business decisions that were once governed primarily by an executive’s intuition — like where to invest and when — are now being strengthened by data-driven AI. (See the section titled “A Business Case” for an example.)
AI Accuracy: Machine Learning Keeps on Learning
Much has been made of AI’s abilities — to see, to understand human speech, to predict outcomes. But some wonder whether the technology has evolved enough to form the foundation of business decisions. For instance, a recent WIRED story reported that an AI-based image detection program was 91 percent sure that a photo of two skiers was a dog. It turns out that like any computer program, AI will need debugging before it is put into production.
AI systems today are statistical learning systems that drink in data. If the data used to teach AI systems is flawed, either because it’s wrong, statistically unsound, or does not cover the use cases the AI system was designed for, the outcomes can be erroneous.
As companies increasingly turn to AI and machine learning to inform business decisions, experts advise a meticulous approach to data. “While AI models have increased greatly in sophistication, including the ability to learn from ever larger datasets of known cases, businesses need to understand that the approach is still empirical,” Menon says. “Predictions will be accurate only if the data used to train the prediction model truly represent the target cases being classified or predicted.”
For example, an AI model schooled to predict the health outcomes of a certain diet might overstate results if the data used in training the model is tied to a specific subgroup of the population. In such a case, the model would have no way of taking into account the genetic and lifestyle variations in other groups that could modulate the effect of diet on health, and its results could be flawed if applied broadly.
Joseph Sirosh, Microsoft
The good news, Sirosh says, is that AI systems can be tested in scientific ways — with new data — and validated. Especially in the case of AI designed for mission-critical operations, it may be important to have controlled statistical testing, similar in spirit to clinical trials in medicine.
“It is up to a business to gather the right data for the problem at hand and apply prediction results appropriately depending on the type of problem being solved and the decisions being made,” Menon says. Executive-level support can set these ground rules for AI, helping ensure accurate decision support throughout the enterprise.
With the right data, the business case for applying AI widely is growing stronger by the week — across many forms of AI. A Danish company, for example, claims that the AI behind its pricing technology can improve gas stations’ margins by as much as 5 percent. Meanwhile, the insurance company Lemonade recently claimed a world record, saying the company’s AI bot settled a client’s claim in three seconds (including sending wiring instructions for the payout and notifying the client of the settlement).
In all these instances, businesses are either offloading decisions to AI or strengthening them with AI’s help — and creating new experiences for customers, new business models, and new ways of working.
Trend Spotting: Adding Location Data to AI
(Image: Esri)
“All this decision-making feeds on data,” Menon says. “The more data you have that is relevant to the problem, the better the decision-making process is.”
One type of data driving AI in new directions is location, Sirosh says. “Geographic information systems [GIS], which can correlate and analyze location in time and space and integrate it with many other types of information — and then serve it up for higher-order AI to be applied on it — are particularly interesting,” he told WhereNext.
“GIS and geography provide organizations with additional contextual information that enriches observations, leading to better predictions,” Menon explains. That might be the quarterly sales at stores in a particular market. Or the rate of home ownership in the area where a bank is considering building a new branch. It could even be data on physical phenomena such as weather, vegetation, or urban density. The more data elements that GIS catalogs, the more oxygen AI has, and the better its predictions will be.
“Most things are located in the world and related to or influenced by nearby things,” Menon says. That simple statement underscores the value of using location data to strengthen AI-based decision making.
The Pillars of Artificial Intelligence
Unlike technologies that are well known but struggling for widespread business adoption — among them, virtual reality and blockchain — artificial intelligence is already being put to work in organizations worldwide.
The coming-out party for AI is due to three factors, according to Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft. The first is the massive compute power now available in the cloud or on premises, which allows data to be processed into insight. The second is the data unleashed by digital transformation, including sensors that relay information via the Internet of Things (IoT), GPS and mobile devices that report accurate locations, and innumerable other sources. Sirosh calls data the oxygen of artificial intelligence.
The third pillar of AI is the algorithms that fuel its intelligence. Recent innovations have provided AI with “the ability for computers to learn from every type of data, make predictions, and act without being programmed explicitly,” Sirosh says.
Together, those forces help AI mimic — and in some cases, outperform — humans’ abilities to see, analyze, communicate with, and make predictions about the world around them.
A Business Case: AI Powered by Location Intelligence
Just as search engines revolutionized the speed of information discovery and knowledge sharing, AI and location data are accelerating business activities by performing some tasks faster than humans can, with more data. The benefit isn’t simply faster decisions, Sirosh and Menon say. It’s smarter decisions.
A new breed of AI-based sales analysis is a case in point. A sales executive at a national retailer has identified young parents as a core customer segment and wants to learn more about them. But manually gleaning insight from thousands of customers and hundreds of thousands of transactions is an impossible task. The company turns to a machine learning model in the hope of discovering more insight.
The goal is to find patterns in the data that will help the company understand this core customer segment — insight that will improve the company’s marketing messages, store assortments, and the events it sponsors in its communities. The project team tutors an AI model using data from multiple stores, including customer addresses and a record of purchases attributed to each address.
The AI model sifts through these records looking for insight. It homes in on diaper purchases as a signal for young parents and discovers a curious correlation: many diaper purchases are accompanied by purchases of pill organizers, denture cream, and senior vitamins.
To refine the analysis, the team enriches the AI model with location-based demographic data pulled from GIS. To each customer address, the AI model adds hundreds of data points about the demographic characteristics of the surrounding neighborhood — average household income, family composition, marital status, hobbies, languages spoken, and recreational preferences.
Combing through that location-enriched big data, the AI algorithm reveals something executives hadn’t expected. At many of the company’s stores, young parents from the surrounding area live in multigenerational homes. And, as it turns out, the grandparents are doing most of the shopping.
The AI model helped executives adjust plans for marketing, merchandizing, and community outreach before they spent millions targeting the wrong demographic. And it did so by using the three traits that make AI a valuable tool for augmenting the human workforce, according to the consultants at PwC:
Automating complex business processes
Spotting patterns in historical data that lead to business value
Providing insight that strengthens human decisions
Business Strategy: Who Oversees AI — CXOs or LOB Managers?
Considering AI’s expected business impacts and the fact that 93 percent of organizations are already investing in the technology, it’s worth asking where artificial intelligence should live in the organization, and who should be responsible for it. There may be no simple answer, but those with a ringside seat for AI’s emergence have some suggestions.
“When it involves the data that a company uses and the way that decisions are made, AI requires top-down vision and investment,” Menon says.
Sirosh agrees. “Where we have found dramatic wins related to AI, the CEO had a vision of how to transform the organization toward creative work and away from old-economy and labor-intensive processes, or to create new customer experiences and business models. That vision was much more cohesive and integrative than what would have bubbled up” from the lines of business, he says.
AI Need Not Apply — Business Processes Untouched by AI
Despite the sense that AI is sweeping through every function of business, some remain AI free, according to Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft. “For example, engineering and physics are incredibly well-developed mathematical sciences, and we are going to make tremendous progress in those areas. That will include breakthroughs in quantum computing and other disciplines. Those are all areas that are just core scientific and engineering work. AI doesn’t encompass all of that, although it may help amplify some of this work.”
Using AI to move companies away from labor-intensive processes will likely have profound effects on the workforce. McKinsey researchers assert that 45 percent of activities in today’s workforce could be automated — whether through AI or other means. And when natural-language processing — a form of AI — reaches the median level of human capability, another 13 percent of jobs could be on the block.
C-level executives will need to find an effective balance. Writing about the C-level challenges of AI, McKinsey senior partners Jacques Bughin and Eric Hazan note that measurable ROI typically comes only when AI is laced into a business’s culture and workflows. That in itself is a sizable feat, the partners say, possible only with the guidance of company leaders.
“When companies are looking to do fundamental digital transformations and reinvention of the business,” Sirosh says, “there is incredible value in having top-down guidance drive much of that activity.”
Workforce shifts and workflow transformation aside, Sirosh and Menon advise concerned executives to focus on the foundation of AI. The goal of such a sophisticated technology, they say, is rather simplistic.
AI, informed by location data, helps organizations reason and interact with the increasingly sophisticated world around us,” Sirosh says.
“If I had to put it in one term,” Menon adds, “AI is basically about decision-making — smarter decision making.”
(Listen to a podcast featuring Joseph Sirosh to explore this concept in more depth, including a look at how AI is changing business models.)
Marianna Kantor joined Esri as chief marketing officer in 2015. Prior to Esri, Marianna was the VP of Marketing at PTC, where she built the worldwide services marketing and field-enablement organization, helping drive sustained revenue growth in dynamic and changing markets. Marianna has held technology and marketing leadership positions throughout her career in leading organizations such as AT&T, Akamai, and Los Alamos National Labs. At Esri, Marianna is exposing and amplifying the transformational capabilities of geospatial technology as an indispensable tool for problem solving and decision making in business and government. Marianna holds two engineering degrees from Columbia University and University of Pennsylvania, and an Executive MBA from MIT.  As Esri’s chief technology officer, Jay Theodore guides the long-term vision for the ArcGIS platform. Jay is passionate about harnessing innovative ideas to increase the value companies gain from location intelligence, geoscience, computer science, and technology. He takes great pride in working with outstanding software developers, architects, and product engineers. Jay earned a master’s degree in computer science from Florida Institute of Technology, where his research focused on finite element analysis and modeling (FEA/FEM), computer graphics, and composite structure design for Space Station Freedom. He also holds a bachelor’s degree in computer engineering.
A little more than a decade ago, the IT world began to buzz about the next big thing, a concept called service-oriented architecture (SOA). SOA promised a better way to build enterprise applications, delivering efficiency, business agility and fluid communication — a near revolution in business workflows. Such was its promise that business executives — not just CIOs — began to ask, How do I get an SOA?
In the fog of excitement, few executives asked the more appropriate question: What exactly is an SOA? Is it an off-the-shelf product, an IT methodology, a business philosophy? And where does it belong in my organization — do I need a strategy to drive business value from it?
Today, artificial intelligence (AI) triggers similar levels of excitement, with a chaser of fear. In a recent survey by New Vantage Partners, C-level executives crowned AI the most disruptive technology — far outranking cloud computing and blockchain. And nearly 80 percent of those executives fear competitors will harness AI to outflank their business.
An Executive Checklist for AI in the Enterprise
Create a strategy. AI is already making an impact in the enterprise — via chatbots, virtual assistants, and other point solutions. Experts advise executives to establish a framework for how AI will be incorporated into business strategy and processes, and to define measurable goals.
Apply executive support. Assign a C-level executive to oversee the company’s strategy. “When companies are looking to do fundamental digital transformations and reinvention of the business, there is incredible value in having top-down guidance drive much of that activity,” says Microsoft’s Joseph Sirosh.
Mind the data. “Predictions will be accurate only if the training data used to teach the AI prediction model is truly representative of the target cases being classified or predicted,” explains Esri’s Sud Menon. “AI is a data-driven game, hands down.”
Incorporate robust datasets, including location information. In nearly all its forms, business data can become more valuable when coupled with information about its location. This form of geoenrichment is especially useful for AI models, which can discover insight that humans might overlook. (See “A Business Case” in the article.)
From an executive’s perspective, now is the time to answer critical questions: What is AI, what can it do for my business, and who should be responsible for its development and strategic alignment?
AI in the Enterprise
Although 93 percent of businesses are investing in artificial intelligence, not all are using it in the same way or toward the same end, says Sud Menon, director of software product development at Esri. “AI is a very broad term, and businesses are adopting different aspects of it at different rates,” Menon notes.
Sud Menon, Esri
When envisioning how AI can deliver value to their enterprises, business executives should think of three primary processes, according to Menon and Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft: internal business operations, customer interactions, and business planning. Interestingly, a survey by Tata Consultancy Services found that high-performing companies are more likely to focus their AI efforts on internal operations, while AI followers tend to concentrate on customer interactions.
Regardless, each process is being transformed with help from cloud computing, data, and intelligent algorithms that power AI. Here are a few examples of how:
Internal Operations. AI is improving companies’ internal operations in several ways. In some workplaces, AI-based facial recognition systems regulate employee access to secure areas. Predictive maintenance systems run by AI help determine the optimal service schedule for fleets of delivery vans. And AI-infused bots are performing HR tasks that once required human intervention, such as guiding employees through the steps of changing their last name, or adjusting the allocation of their 401k plan. The bots connect to systems of record like ERP and HR software, analyze pertinent data, and lead employees through an intuitive workflow.
Customer Interactions. AI is adding intelligence to some customer-facing tasks. For example, AI powers many of the recommendation systems that suggest a relevant product or a message to a website visitor who lives in a particular location. It anchors security systems that recognize a fraudster’s voice signature or suspicious online activity in real time and deny the person access to an online account. And it supports the chatbots that interact with millions of consumers online each day.
Business Planning. For executives and decision-makers looking for strategic guidance, AI can predict shifts in supply and demand and how businesses might react. To plan next quarter’s operations, the technology can sift through customer purchasing habits and factors such as planned competitor stores to predict sales, product mix, and staffing levels. Business decisions that were once governed primarily by an executive’s intuition — like where to invest and when — are now being strengthened by data-driven AI. (See the section titled “A Business Case” for an example.)
AI Accuracy: Machine Learning Keeps on Learning
Much has been made of AI’s abilities — to see, to understand human speech, to predict outcomes. But some wonder whether the technology has evolved enough to form the foundation of business decisions. For instance, a recent WIRED story reported that an AI-based image detection program was 91 percent sure that a photo of two skiers was a dog. It turns out that like any computer program, AI will need debugging before it is put into production.
AI systems today are statistical learning systems that drink in data. If the data used to teach AI systems is flawed, either because it’s wrong, statistically unsound, or does not cover the use cases the AI system was designed for, the outcomes can be erroneous.
As companies increasingly turn to AI and machine learning to inform business decisions, experts advise a meticulous approach to data. “While AI models have increased greatly in sophistication, including the ability to learn from ever larger datasets of known cases, businesses need to understand that the approach is still empirical,” Menon says. “Predictions will be accurate only if the data used to train the prediction model truly represent the target cases being classified or predicted.”
For example, an AI model schooled to predict the health outcomes of a certain diet might overstate results if the data used in training the model is tied to a specific subgroup of the population. In such a case, the model would have no way of taking into account the genetic and lifestyle variations in other groups that could modulate the effect of diet on health, and its results could be flawed if applied broadly.
Joseph Sirosh, Microsoft
The good news, Sirosh says, is that AI systems can be tested in scientific ways — with new data — and validated. Especially in the case of AI designed for mission-critical operations, it may be important to have controlled statistical testing, similar in spirit to clinical trials in medicine.
“It is up to a business to gather the right data for the problem at hand and apply prediction results appropriately depending on the type of problem being solved and the decisions being made,” Menon says. Executive-level support can set these ground rules for AI, helping ensure accurate decision support throughout the enterprise.
With the right data, the business case for applying AI widely is growing stronger by the week — across many forms of AI. A Danish company, for example, claims that the AI behind its pricing technology can improve gas stations’ margins by as much as 5 percent. Meanwhile, the insurance company Lemonade recently claimed a world record, saying the company’s AI bot settled a client’s claim in three seconds (including sending wiring instructions for the payout and notifying the client of the settlement).
In all these instances, businesses are either offloading decisions to AI or strengthening them with AI’s help — and creating new experiences for customers, new business models, and new ways of working.
Trend Spotting: Adding Location Data to AI
(Image: Esri)
“All this decision-making feeds on data,” Menon says. “The more data you have that is relevant to the problem, the better the decision-making process is.”
One type of data driving AI in new directions is location, Sirosh says. “Geographic information systems [GIS], which can correlate and analyze location in time and space and integrate it with many other types of information — and then serve it up for higher-order AI to be applied on it — are particularly interesting,” he told WhereNext.
“GIS and geography provide organizations with additional contextual information that enriches observations, leading to better predictions,” Menon explains. That might be the quarterly sales at stores in a particular market. Or the rate of home ownership in the area where a bank is considering building a new branch. It could even be data on physical phenomena such as weather, vegetation, or urban density. The more data elements that GIS catalogs, the more oxygen AI has, and the better its predictions will be.
“Most things are located in the world and related to or influenced by nearby things,” Menon says. That simple statement underscores the value of using location data to strengthen AI-based decision making.
The Pillars of Artificial Intelligence
Unlike technologies that are well known but struggling for widespread business adoption — among them, virtual reality and blockchain — artificial intelligence is already being put to work in organizations worldwide.
The coming-out party for AI is due to three factors, according to Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft. The first is the massive compute power now available in the cloud or on premises, which allows data to be processed into insight. The second is the data unleashed by digital transformation, including sensors that relay information via the Internet of Things (IoT), GPS and mobile devices that report accurate locations, and innumerable other sources. Sirosh calls data the oxygen of artificial intelligence.
The third pillar of AI is the algorithms that fuel its intelligence. Recent innovations have provided AI with “the ability for computers to learn from every type of data, make predictions, and act without being programmed explicitly,” Sirosh says.
Together, those forces help AI mimic — and in some cases, outperform — humans’ abilities to see, analyze, communicate with, and make predictions about the world around them.
A Business Case: AI Powered by Location Intelligence
Just as search engines revolutionized the speed of information discovery and knowledge sharing, AI and location data are accelerating business activities by performing some tasks faster than humans can, with more data. The benefit isn’t simply faster decisions, Sirosh and Menon say. It’s smarter decisions.
A new breed of AI-based sales analysis is a case in point. A sales executive at a national retailer has identified young parents as a core customer segment and wants to learn more about them. But manually gleaning insight from thousands of customers and hundreds of thousands of transactions is an impossible task. The company turns to a machine learning model in the hope of discovering more insight.
The goal is to find patterns in the data that will help the company understand this core customer segment — insight that will improve the company’s marketing messages, store assortments, and the events it sponsors in its communities. The project team tutors an AI model using data from multiple stores, including customer addresses and a record of purchases attributed to each address.
The AI model sifts through these records looking for insight. It homes in on diaper purchases as a signal for young parents and discovers a curious correlation: many diaper purchases are accompanied by purchases of pill organizers, denture cream, and senior vitamins.
To refine the analysis, the team enriches the AI model with location-based demographic data pulled from GIS. To each customer address, the AI model adds hundreds of data points about the demographic characteristics of the surrounding neighborhood — average household income, family composition, marital status, hobbies, languages spoken, and recreational preferences.
Combing through that location-enriched big data, the AI algorithm reveals something executives hadn’t expected. At many of the company’s stores, young parents from the surrounding area live in multigenerational homes. And, as it turns out, the grandparents are doing most of the shopping.
The AI model helped executives adjust plans for marketing, merchandizing, and community outreach before they spent millions targeting the wrong demographic. And it did so by using the three traits that make AI a valuable tool for augmenting the human workforce, according to the consultants at PwC:
Automating complex business processes
Spotting patterns in historical data that lead to business value
Providing insight that strengthens human decisions
Business Strategy: Who Oversees AI — CXOs or LOB Managers?
Considering AI’s expected business impacts and the fact that 93 percent of organizations are already investing in the technology, it’s worth asking where artificial intelligence should live in the organization, and who should be responsible for it. There may be no simple answer, but those with a ringside seat for AI’s emergence have some suggestions.
“When it involves the data that a company uses and the way that decisions are made, AI requires top-down vision and investment,” Menon says.
Sirosh agrees. “Where we have found dramatic wins related to AI, the CEO had a vision of how to transform the organization toward creative work and away from old-economy and labor-intensive processes, or to create new customer experiences and business models. That vision was much more cohesive and integrative than what would have bubbled up” from the lines of business, he says.
AI Need Not Apply — Business Processes Untouched by AI
Despite the sense that AI is sweeping through every function of business, some remain AI free, according to Joseph Sirosh, corporate vice president of artificial intelligence and research at Microsoft. “For example, engineering and physics are incredibly well-developed mathematical sciences, and we are going to make tremendous progress in those areas. That will include breakthroughs in quantum computing and other disciplines. Those are all areas that are just core scientific and engineering work. AI doesn’t encompass all of that, although it may help amplify some of this work.”
Using AI to move companies away from labor-intensive processes will likely have profound effects on the workforce. McKinsey researchers assert that 45 percent of activities in today’s workforce could be automated — whether through AI or other means. And when natural-language processing — a form of AI — reaches the median level of human capability, another 13 percent of jobs could be on the block.
C-level executives will need to find an effective balance. Writing about the C-level challenges of AI, McKinsey senior partners Jacques Bughin and Eric Hazan note that measurable ROI typically comes only when AI is laced into a business’s culture and workflows. That in itself is a sizable feat, the partners say, possible only with the guidance of company leaders.
“When companies are looking to do fundamental digital transformations and reinvention of the business,” Sirosh says, “there is incredible value in having top-down guidance drive much of that activity.”
Workforce shifts and workflow transformation aside, Sirosh and Menon advise concerned executives to focus on the foundation of AI. The goal of such a sophisticated technology, they say, is rather simplistic.
AI, informed by location data, helps organizations reason and interact with the increasingly sophisticated world around us,” Sirosh says.
“If I had to put it in one term,” Menon adds, “AI is basically about decision-making — smarter decision making.”
(Listen to a podcast featuring Joseph Sirosh to explore this concept in more depth, including a look at how AI is changing business models.)
Marianna Kantor joined Esri as chief marketing officer in 2015. Prior to Esri, Marianna was the VP of Marketing at PTC, where she built the worldwide services marketing and field-enablement organization, helping drive sustained revenue growth in dynamic and changing markets. Marianna has held technology and marketing leadership positions throughout her career in leading organizations such as AT&T, Akamai, and Los Alamos National Labs. At Esri, Marianna is exposing and amplifying the transformational capabilities of geospatial technology as an indispensable tool for problem solving and decision making in business and government. Marianna holds two engineering degrees from Columbia University and University of Pennsylvania, and an Executive MBA from MIT.  As Esri’s chief technology officer, Jay Theodore guides the long-term vision for the ArcGIS platform. Jay is passionate about harnessing innovative ideas to increase the value companies gain from location intelligence, geoscience, computer science, and technology. He takes great pride in working with outstanding software developers, architects, and product engineers. Jay earned a master’s degree in computer science from Florida Institute of Technology, where his research focused on finite element analysis and modeling (FEA/FEM), computer graphics, and composite structure design for Space Station Freedom. He also holds a bachelor’s degree in computer engineering.
Drones and robots complement traditional platforms, delivering insights in unique use cases.
Guest column by Mike Fuller
Geographic surveys have changed in the last 150 years. What started with early film cameras strapped to hot air balloons, kites and homing pigeons has advanced — both in terms of sensors and the platforms on which they’re deployed. These innovations — which include drones and robots — are changing the way we can collect data, enabling us to gather greater detail and providing richer insights about the world around us.
These nascent platforms are set to explode in popularity. The global market for remote sensing platforms will more than double in the next four years. It’s projected to reach more than $21 billion by 2022, driven in large part by use of drones, according to an October 2017 report from MarketsandMarkets.
Despite the anticipated growth in drone and robot usage, they will not replace traditional remote sensing platforms such as airplanes, satellites and vehicles. The new technologies bring with them some limitations with regard to the number, size and weight of sensors they can carry, capture rates, area covered and and line-of-site restrictions.
As a result, drones and robots will offer new capabilities that complement the traditional platforms and provide greater geographic detail, as well as the ability to be quickly deployed and constantly monitor areas where humans cannot routinely go.
How far we’ve come
To understand how far geographic information system (GIS) mapping and remote sensing technology has come, it’s important to consider how it started. Inventors in the 1800s relied on early film cameras and somewhat unreliable, imprecise airborne platforms — such as hot air balloons, pigeons and kites — to conduct land surveys and do surveillance.
The introduction of a new kind of “bird” — the airplane — opened up new opportunities in the 1900s, supporting the use of more accurate aerial photography for reconnaissance and mapping.
Satellite technology launched remote sensing into space in the 1970s, supporting the collection of detailed multispectral data that led to improved understanding of minerals, soils, urban growth, agriculture and other geographic features.
Even though the technology has become more sophisticated, GIS professionals still leverage data from many of these historical platforms:
Manned aircraft – planes and helicopters
Satellites – high-resolution satellites and cubesats
Terrestrial – survey vehicles and handheld devices
But — much like the impact of airplanes and satellites — we’re on the precipice of another significant milestone for remote sensing. Marked by use of burgeoning drone and robotic technology, this new technology will complement traditional platforms and deliver more insights than ever before possible.
Rise of drones and robots
Drones and robots are the newest remote sensing platforms catching the eye of the GIS community. Not only are they cool and cutting-edge, they open up a new class of use cases that were previously not possible with traditional aerial survey methods. They offer new opportunities to monitor remote areas, and their form factors and cost enables a higher frequency of data collection compared to aerial survey.
Because of their unique features, users are envisioning how these platforms can be implemented for remote sensing in many fields, such as energy, oil and gas, aviation, forestry, transportation, emergency management, and natural resource preservation and restoration.
When the frequency of data from these platforms is coupled with analytics and cloud infrastructure, it is possible to acquire, analyze and act in ways that were not possible before.
Keep in mind, though, that each technology comes with trade-offs. Users should assess their goals, and weigh these factors, to determine if drones or robots will deliver the results they wish to achieve. Let’s take a closer look:
Drones
Drones are capable of delivering ultra-high-resolution data, with ground sample distances (GSD) of 1 cm and accuracy of under 5 cm. However, accuracy is highly variable; it can vary based on the drone model, terrain and software used to process the collected data.
The form factor of many drones also limits the ability to do multi-sensor flights. A drone typically can cover no more than a few square miles per day with a visible or multispectral camera, compared to manned aircraft that span hundred of thousands of acres a day carrying hyperspectral, lidar and orthophotography devices simultaneously.
Because they can be deployed quickly, and on a daily basis, drones offer a cost-effective, practical approach for covering small areas compared to other aerial survey methods. But drone usage currently faces a significant impediment.
Current regulations require operators to maintain sight of the devices during all flights. These line-of-site restrictions limit the distance a drone can go on each flight, and require operators to change locations multiple times for a single survey. As a result, frequent revisits can be labor intensive.
Battery life also plays a role in the usability of drones. Most commercial drones can fly for only about 45 minutes, despite continued improvements in battery technology. Combined with the line-of-site restrictions, battery life impacts the amount of territory drones can cover. Most can handle only a few square or linear miles during each flight, making helicopters or airplanes better suited for projects that span hundred of miles or more.
Despite some of the drawbacks, drones are proving ideal in many use cases — from damage assessment and power restoration after hurricanes to data collection for hydraulic modeling, stream restoration design and aquatic habitat assessment.
For example, drones equipped with bathymetric and terrestrial laser scanning sensors are ideal for supporting riverine mapping applications. In these cases, drones offer an effective alternative when the waterway cannot be accessed, or it is too dangerous to use ground- or water-based survey methods for collecting channel geometry.
Robots
Robotic platforms are flexible, enabling users to attach a variety of sensors, including thermal cameras, lidar and sniffers for natural gas or other hazardous material. They are rarely hampered by payload restrictions, like drones.
And, with programming, robots can return to their chargers when their batteries dip below a certain threshold.
Like drones, there are many potential applications for terrestrial remote sensing robots. One use is for precision agriculture to test soil, water and plant health.
Many utilities are expressing serious interest, too, for robots. These robots can include onboard spectral, thermal and lidar sensors, precision navigation and hazard cameras to perform fine-scale spatial mapping and can acquire a wide array of data from electrical substations.
In this scenario, the robotic platform could detect physical and spectral changes, identify objects, monitor corrosion, detect liquid and gas leaks, and conduct thermal monitoring. Using this model, utilities could track substation environments remotely, saving time associated with physical inspections and enabling earlier detection of potential problems.
Systemwide approach required
Traditional remote sensing platforms — airplanes, satellites and vehicles — will continue to play an important role in GIS mapping. Drones and robots give us new tools that will have a dramatic impact on the amount of detailed geographic information collected.
For these new platforms to be used effectively as complements to traditional platforms, the industry must adopt a systems approach that takes into consideration a number of factors:
The end application
The sensors and acquisition protocol that will collect data at the precision required by the end application
The actionable analytics that need to be extracted from the data
How the data and insights integrate with the business processes used for decision making.
By taking this approach, those who work in a variety of fields can gather the insights they need to do their jobs more effectively and efficiently, while leveraging the unique strengths offered by these emerging platforms.
An oblique image of downtown Chicago, captured in June 2017, with measurements. (Image: Nearmap)
Guest column by Sanchit Agarwal Vice President, Field Operations, Nearmap
With high-resolution imagery comes the ability to model reality, creating real-life visualizations for engineers, planners, construction teams and many others.
A quantum leap in computing capacity has allowed us to model and analyze the real world — all from our desktop and mobile devices. In days past, maps were purely for visualization and direction.
Today, they have graduated to full-blown analytics platforms empowering users to make decisions faster than ever before.
Why?
They closely represent truth on the ground — truth created from high-resolution aerial imagery captured at heights of up to 18,000 feet. Camera systems mounted in the bellies of planes can efficiently map the real world in incredible high detail. These aerial photographs are updated continuously.
In years past, access to aerial mapping content and services was reserved for more significant players.
Today, with easy access to scalable high-definition mapping content, anyone can utilize the power of maps in applications that extend far beyond directions and navigation.
There are two essential attributes of aerial maps driving this transformation — image resolution and model density. Today, most users are applying low-resolution satellite images that lack the detail needed for accurate decisions. But, as resolution increases, the imagery becomes more detailed; the visualizations, more vivid.
Ground features have gone from fuzzy satellite photos to clearly identifiable homes, buildings, roads, lakes and more — all captured using powerful cameras that have found the perfect pixel. With high-resolution comes added benefit.
Aerial image of the Aria Resort in Las Vegas captured in May 2017. (Image: Nearmap)
Users can manipulate the imagery — zoom closer and closer without losing the details. Computers can classify the features, distinguishing skylights from solar panels, walking paths from sidewalks, and pools from ponds.
Rich imagery is yielding richer data used to instantly query massive databases and return results that answer complex questions for businesses and government.
With high-resolution imagery comes the ability to model reality, creating real-life visualizations for engineers, planners, construction teams and others.
These models of landscapes, cities and neighborhoods are portrayed inside design tools and mapping systems, saving the analyst countless days of traveling to the site only to be surprised that the outdated low-resolution imagery does not depict what’s actually on the ground.
Imagery can vary greatly in resolution. Pixel resolution refers to the actual distance on the ground that each pixel represents in the orthophotography — the vertical image. For example, one-foot pixel resolution means that each pixel in the image covers one foot on the ground.
Common resolutions include three-inch, six-inch, one-foot and one-meter. The higher the imagery resolution (for instance, three inches per pixel), the greater the visible detail within the photograph. Clearly, a three-inch resolution is much better than a one-foot resolution.
Most mapping content currently consumed is two-dimensional and generated from low to mid-resolution nadir imagery. In other words, you see the land as if you were staring straight down at it, not height-of-ground features and certainly not change over time.
While that was adequate for some users, others reached for higher resolution and, while they were at it, decided they needed a third and fourth dimension — namely, height and time. These new perspectives provide more analytical options, more insights and a variety of new use cases that show change over time, height and multi-perspectives of the same property or landscape.
With the democratization of mapping products and services and the general trend toward consumption of multi-dimensional experiences, there is an implicit need to increase resolution, detail, dimensions and perspectives in mapping content and services as well.
The Rancho Mirage community of California, captured in February 2017. (Image: Nearmap)
Traditionally, satellite imagery has been used to monitor large areas of the earth at scale remotely. The resolution of the satellite imagery has graduated from multiple meters to feet with the advent of advanced mapping satellites.
The challenge here is the resolution. Low-resolution satellite imagery, although scalable, is good for macro-analysis of cities and neighborhoods but is not detailed enough for accurate measurements and micro-analysis at the level of each individual property.
On the other end of the spectrum come drone mapping solutions that offer the promise of delivering incredibly high-resolution datasets (sub-centimeter resolution) but fails to provide the scalability and repeatability.
Let’s get specific. Why does resolution matter?
You cannot measure what you cannot see. The resolution of imagery provides a more detailed, zoomed in and richer view of the real world, thereby enabling desktop based reconnaissance, inspection, analysis and measurement of features that are not traditionally visible in satellite imagery.
Higher resolution means high fidelity and dependable measurements. With the added details and definition of features that high-resolution offers comes the much-needed advantage of clearly and legibly identifying feature boundaries and hence measuring the feature with high precision and accuracy.
Higher resolution map content means fewer site visits. Rather than travel onsite to inspect and measure, many organizations are now relying on high-resolution imagery and, in the process, not having to waste resources sending team members on site.
High resolution means more detailed documentation of reality. Gamers have experienced reality-like landscapes for quite some time. Now, 3D and 4D mapping content allows users to immerse themselves in the landscape, navigate through street views, and fly like a bird to inspect rooftops with ease.
High resolution and refreshed content means more accurate change analysis. Identifying how locations have changed over time through multiple captures that embody leaf-off and leaf-on imagery allow users to not only visualize detail but also notice progress, changes in construction, degradation of property features, growth in vegetation and more.
High-resolution content means more automated workflows. High-resolution content allows for better feature definition models resulting in higher success rates in interpreting and analyzing the reality algorithmically. Higher success rates of automated algorithms results in efficient exploitation of datasets to solve real world problems.
Machine learning thrives on high-resolution content. There’s no shortage of news on the use of machine learning and artificial intelligence in data science. With the advent of high-resolution maps, machine learning is now able to differentiate skylights from solar panels, decks from patios and pavement from pavers. In turn, the ground features identified are being stored in databases for lightning fast queries to complex problems.
The higher the resolution, the higher your confidence will be.
Story maps combine geographic data withmultimediato tell a story and present information in a useful, interesting way.
While many story maps are designed for general, non-technical audiences, some story maps can also serve highly specialized audiences. They use the tools of GIS, and often present the results of spatial analysis, but don’t require their users to have any special knowledge or skills in GIS.
“Story maps use geography as a means of organizing and presenting information. They tell the story of a place, event, issue, trend or pattern in a geographic context,” explains Esri’s press staff in a blog. “They combine interactive maps with other rich content — text, photos, illustrations, video and audio — within intuitive user experiences.”
Haven’t yet dipped your toe into Story Maps? This Esri blog takes users through story map creation step by step.
Below are six visual narratives that provide timely information using Esri’s Story Map creation tools.
Faces Show Personal Impact of Opioid Epidemic
The National Safety Council is adopting the Celebrating Lost Loved Ones map, which allows family and friends of those lost to the opioid epidemic to place an image and description of their late loved one on an interactive map. The project helps raise awareness of the broad impact of the opioid crisis and advances the council’s mission of ending opioid deaths. Unintentional opioid overdose deaths totaled 37,814 in 2016.
Jeremiah Lindemann, a solution engineer for Esri, created the map in 2016 following the death of his younger brother. Since its launch, the map has gathered more than 1,300 memorials from people across the U.S.
The map has been a crowdsourced effort, allowing grieving friends and family members to honor their loved ones, share their stories with others and find a supportive community in return.
Communities Potentially Affected by DACA Policy Changes
When elected officials talk about changing our immigration system, just who and where are people affected? That’s the question Esri is trying to help answer with a new interactive story map that explores communities with the highest shares of non-citizen residents and DACA (Deferred Action for Childhood Arrivals) recipients.
The map shows estimates on DACA eligible, recipients, and annual GDP loss from removing DACA workers by congressional district. Data comes from USC’s Dornsife Center for Immigrant Integration.
The size of the symbol shows the estimate of DACA recipients, and the color of the symbol shows the estimated GDP loss from removing DACA workers. This map shows that the economies of many states in the Southwest and several major urban cities could be substantially disrupted if DACA recipients are no longer permitted to work.
The Ever-Changing Minimum Wage
National, state and local government policies toward the minimum wage vary widely and are continually changing. On Jan. 1, new or adjusted minimum wage policies took effect in 18 states and territories. Varying rates, policies, and impacts across the nation make it challenging to understand the minimum wage landscape.
This Esri story map provides an overview of the the nation’s changing minimum wage policies. A few notable findings:
At the highest level, the variability of minimum wage policies from state to state is striking — this ranges from some states in the South that don’t even require a minimum wage, to places like D.C. that have a $12.50 minimum wage (currently the highest for a state or territory).
Similarly, the number of cities and counties that have taken it upon themselves to raise wages locally is impressive; these cities and counties have robust plans for raising minimum wages over the next few years.
Regardless of an area’s minimum wage, all states fail to guarantee minimum wages that actually match up to the cost of living for their respective areas. As such, there is a growing divide between states that have raised minimum wages and are at least bringing minimum wages closer to the cost of living, versus those states that are slower to raise minimum wages (or don’t raise wages at all) and fall much further below the local cost of living.
Even while minimum wages have nominally increased, inflation has devalued the dollar in such a way that even in 2018 some wages today have less purchasing ability than nominally lesser wages in the 1970s.
Ireland Encourages Emmigrees to Come Home
Like much of Ireland, the history of County Donegal is inextricably wedded to the geography of migration. Now county officials are using a story map to try and woo émigrés back to the Emerald Isle.
The Irish government views the loss of its citizens so seriously that a minister for diaspora affairs was appointed to the Irish cabinet in 2014.
“Ireland’s Call — To Return Its Global Diaspora Home” displays key factors to assist those in contemplating returning. The story map launches the Global Skills Locator to link its global diaspora with job opportunities back home.
Smart City 3.0 Book Explained
Esri China (Hong Kong) Limited uses the story map tools in a unique way — to highlight its new book Smart City 3.0. The book and map discuss artificial intelligence, the internet of things, robotics and the sharing economy, and how all of them are shaping a new phase of development for the smart city.
Hurricane Harvey’s Lasting Effects
Within cities, poor communities often live in segregated neighborhoods with higher flood risks. This is especially true in Houston, where Hurricane Harvey hit this past August.
As in previous disasters like Katrina and Sandy, the heaviest cost of Harvey’s destruction is likely going to be borne by the most vulnerable communities in its path.
Humanitarian aid organization Direct Relief’s interactive Esri maps used the Centers for Disease Control and Prevention’s social vulnerability index to show the geographic distribution of households with elderly or disabled members (in orange), immigrant and limited English-speaking populations (in purple), and pockets of poverty (in green). The darker the color, the higher the concentration of these factors in each region.
Learn more about story maps and how to create them here.
Making cities cleaner, providing better services and housing, and decreasing pollution are all achievements of nine cities recognized for using data to improve citizens’ lives.
In January, Bloomberg Philanthropies announced that nine cities have achieved What Works Cities certification, a first-of-its-kind national standard of excellence in city governance.
What Works Cities certification rates how well cities are managed by measuring the extent to which city leaders incorporate data and evidence in their decision-making.
Having shown leadership in data-driven government, the nine cities will receive additional expert assistance from What Works Cities to accelerate progress and deepen their leadership in using data.
Bloomberg Philanthropies launched What Works Cities in April 2015 to drive the use of data in U.S. municipal governance and to facilitate the exchange of best practices. It has reached its initial goal of bringing 100 mid-sized American city partners into the program. The nine certified cities were selected from more than 115 applications.
Los Angeles was awarded Gold Level, and eight other cities received Silver Level certification. No city has yet achieved Platinum, the highest level.
Accomplishments of each of the certified cities can be found here; below is a snapshot.
Gold Level: Los Angeles
Los Angeles has demonstrated a strong commitment and impressive track record with data-driven initiatives, according to Bloomberg Philanthropies.
Immediately upon assuming office, Mayor Eric Garcetti embraced an aggressive approach to data and analysis to better understand and map the most pressing issues in Los Angeles. Now in his second term, the mayor is using the foundation created by these efforts to develop a system-wide, evidenced-based approach to address the problems of affordable housing, crime, traffic and pollution.
Through its Data Science Federation, the city is also partnering with local universities to accelerate its use of data-driven tools at the same time that it is creating a pipeline to bring new talent into local government.
Among the major accomplishments cited:
CleanStat. In 2016, the Los Angeles Bureau of Sanitation began regularly collecting data to measure street cleanliness levels, allowing the City to more proactively and equitably clean L.A.’s streets, and place thousands of new public trash bins in areas with the greatest need. In just one year, these efforts led to an 82 percent reduction in streets previously rated as “Not Clean.”
With CleanStat, staff from the Bureau of Sanitation drive all of the more than 20,000 miles of the city’s public streets and alleys, assigning a cleanliness score from 1 to 3 — or from clean to not clean — to every block, once a quarter. Those scores are added to the Clean Streets Index, where department officials can keep track of performance and residents can hold the City accountable for its goal to eradicate red grids (ones with a score of 3) by 2018.
Home for Renters Campaign: In 2016, the City of Los Angeles identified areas where housing displacement was likely to occur, and launched a multi-faceted campaign to raise awareness of tenants’ rights under the city’s rent stabilization ordinance, with a particular focus on assisting our most vulnerable residents.
Save the Drop: In 2015, the City of Los Angeles analyzed water consumption data by ZIP code to focus conservation campaigns on regions with excessive water usage, which has helped Los Angeles reach its 20 percent water conservation goal.
Silver Level Cities
Eight cities earned the Silver Level of Certification. Here is a sample of their accomplishments.
Boston, Massachusetts (Mayor Marty Walsh): Achieving What Works Cities Certification builds on Imagine Boston 2030, Boston’s first citywide plan in 50 years. The goal of Imagine Boston 2030 is to guide growth to support the city economy and expand opportunities for residents.
The plan prioritizes inclusionary growth and puts forth a comprehensive vision to boost quality of life, equity and resilience in every neighborhood across the city. Shaped by the input of 15,000 residents who contributed their thoughts to the plan, Imagine Boston 2030 identifies five action areas to guide Boston’s growth, enhancement, and preservation, and is paired with a set of metrics that will evaluate progress and successes.
Louisville, Kentucky (Mayor Greg Fischer): Mayor Fischer signed an open data executive order that considers public information to be open by default. The new LouieStat performance management program evaluates city departments’ work and shares progress with residents.
The city’s Innovation Team is finding creative ways to involve residents in tackling tough problems, sometimes by bringing them into the data-collection process itself. In one project, placing GPS-enabled sensors on asthma inhalers is helping to pinpoint areas throughout the city where low air quality is likelier to induce asthma attacks.
In another project, built at a CDA hackathon, crowdsourcing data on internet speed is helping the City assess the extent of its digital divide and develop a digital inclusion strategy to remove the barriers that are keeping residents from better jobs and other opportunities.
San Diego, California (Mayor Kevin Faulconer), applied data insights and evidence to advance city-improvement projects. After learning that 80% of San Diegans didn’t want to make phone calls to report problems, the city bypassed the traditional 311 model and launched its Get It Done app.
Using Get It Done, residents can report and track progress on a variety of complaints directly from their mobile phones, and response crews are closing the loop by sending “after” photos to residents, who can rate their experience with a thumbs up, thumbs down, or a comment. The app is helping the city become more efficient, too.
Kansas City, Missouri (Mayor Sly James), and San Francisco, California (Interim Mayor Mark Farrell), both found new ways to give citizens a voice in public service projects and increase government transparency.
New Orleans, Louisiana (Mayor Mitch Landrieu), tackled blight and natural disaster response through data, critical in the aftermath of 2005’s Hurricane Katrina. Through the BlightStat program, the city set priorities for inspectors and researchers who identify rundown properties and determine whether to levy fines, order a demolition, force a sale, or take some other action.
New Orleans has 15,000 fewer blighted properties thanks to BlightStat, a data-driven performance management program that’s helped the City strategically address the issue. (Photo: Bloomberg)
Seattle, Washington (Mayor Jenny Durkin) made strides to improve homeless individuals’ access to housing.
Washington, D.C. (Mayor Muriel Bowser) is beginning to see its rigorous approach to data spread throughout the city’s public agencies.
What makes these cities special
What Works Cities Certification evaluates whether cities have the right people, processes and policies in place to put data and evidence at the center of decision-making.
Cities are evaluated on factors such as whether they have dedicated staff responsible for helping departments use data to track their progress; contracts are awarded based on past performance; meetings are focused on numbers; key datasets are open to the public; and whether there is transparency in both the goals set and the progress towards achieving them.
“We are proud to recognize these leading cities as the best managed nationwide, using data and evidence to drive results. All over the country local governments are jumping into this movement and dramatically improving how their cities operate,” said Simone Brody, executive director of What Works Cities at Results for America. “Our hope is that What Works Cities Certification will continue to accelerate and celebrate the progress of cities as they improve opportunities for millions of residents.”
What Works Cities Certification has been endorsed by the National League of Cities as well as many of the country’s leading urban thinkers and practitioners. It is part of Bloomberg Philanthropies’ American Cities Initiative, a suite of investments that empower cities to generate innovation and advance policy that move the nation forward.
“Congratulations to each of the nine cities that earned certification for their use of data, which is improving services for people and setting a great example for other cities,” said Michael Bloomberg, founder of Bloomberg Philanthropies and three-term mayor of New York City.
“Data allows local governments to know what’s working and citizens to hold leaders accountable for results — but the fact is, many cities aren’t capturing it and putting it to use in making decisions,” Bloomberg said. “The more cities that integrate data into their planning and operations, the more progress our country will be able to make on the common challenges we face.”
Play ball! GeoVisual Search finds baseball stadiums. (Image: Descartes Labs)
Where are all the windmills on Earth? Or oil derricks? How about baseball stadiums?
You could scan through the millions of satellite images snapped by hundreds of satellites now circling the planet. Or you could try Descartes Labs’ demo search engine.
Satellites are snapping images of the Earth every day. Alongside Planet Inc. and DigitalGlobe satellites, constellations are planned from companies such as Urthecast and Astro Digital (the latter launched its first pair of satellites in July). But how do we make use of all of that data in an organized, searchable way?
New Mexico startup Descartes Labs has created a cloud-based supercomputing platform to apply machine intelligence to massive data sets, using satellite imagery to model complex systems on the planet.
While Descartes started by focusing on forestry and agriculture, its new tool Geovisual Search allows users to find similar-looking objects of any kind all over the globe. Just click anywhere on the map and a red tile appears, enabling users to search for similar objects. “To do this, we use deep learning, a form of artificial intelligence that is loosely inspired by the structure of the brain,” Descartes Labs explains.
“Last year, a team at Carnegie Mellon University applied the principles of visual search to seven cities around the world in a demo called Terrapattern. We were impressed with their work and wondered: could we do this not just for a few cities, but for the entire globe?”
Terrapattern was designed as a prototype for scanning geographical areas for specific visual features. Its focus is on helping people identify, characterize and track indicators that have not been detected or measured previously, and which have sociological, humanitarian, scientific or cultural significance. So far, it focuses only on specific cities: Pittsburgh, San Francisco, New York City, Detroit, Berlin, Miami and Austin.
Terrapattern locates cul-de-sacs in Pittsburgh. (Image: Terrapattern)
Inspired by Terrapattern, Descartes goes farther. The company has built three demo maps on three different scales.
The continental United States — This map uses aerial imagery at 1-meter per pixel from the U.S. National Agriculture Imagery Program (NAIP). The high-resolution imagery enables detection of smaller items such as orchards.
China — This map uses satellite imagery at 4-meter resolution from Planet. Though the resolution isn’t as high as the NAIP map over the U.S., Planet’s satellites will soon be providing daily pictures of the globe. In this map, you’ll be able to find solar farms and stadiums.
The entire world — This map uses Landsat 8 and is at 15-meter resolution. Though much coarser than the other maps, you’ll be able to find larger scale objects such pivot irrigation and suburbs.
Every time you click on a tile, GeoVisual Search looks over the entire map for visually similar tiles. At this point, GeoVisual Search isn’t trying to get an accurate count of objects such as windmills. Instead, a search will return the top results, up to 1,000.
However, Descartes Labs’ research on teaching the computer visual patterns is an important step on the road to counting objects accurately, the company said in a blog announcing the search engine.
“We use a type of artificial intelligence called deep learning, which is loosely inspired by neurons and the structure of the brain. For every tile on the map we run it through a deep learning algorithm that creates a fingerprint for that tile. Basically, you can think of it as abstracting some of the qualities of that tile in a way that allows the computer to begin representing the image like a human does: with colors, edges, and other features of the image. When you click on something, we compare every other image to that fingerprint and try to return the ones that look like each other.
“Our research will start to focus on object detection at scale: how do we look for wind turbines, derricks, oil tanks, buildings and other important objects all over the planet. For these objects, we’ll use the underlying principles of visual similarity to teach the computer what a wind turbine looks like in all of its forms and then try to do an accurate count of all the turbines globally. Obviously this is a very difficult task, but we think we’ve got the science to tackle this problem.
“Once we’ve counted objects, we can start looking at maps through time and see what changes — how many new wind turbines are there and where are they, for example.”
Descartes is inviting geospatial developers to take part in the search engine’s development. “If you have ideas about what you’d like to do with GeoVisual Search today and have a team of developers who are experts at machine learning and/or geospatial data, drop us a line for early access to our underlying platform.”
Descartes is evolving the demo, so a release date hasn’t yet been set. Read about the tech behind the demo.
The media is buzzing about the Great American Solar Eclipse that takes place Monday, Aug. 21.
It’s a historic event that last occurred 99 years ago. To be clear, 99 years ago is when the last total solar eclipse traversed the entire continental United States (lower 48 states).
To put that timeline in perspective, only one of the following inventions existed 99 years ago: FM radio, electric hair dryer, electric washing machine, frozen food, folding wheelchair and “talky” movies. Read further for the answer.
The last total eclipse that traversed part of the United States was 38 years ago, but in 1979 the total eclipse was only visible in five U.S. states (Washington, Oregon, Idaho, Montana, North Dakota). Have a look at the following map of the 1979 total eclipse path through the United States.
Figure 1- 1979 total eclipse path through the US. Source: NASA
It’s painful to think that in February 1979, when this eclipse occurred, I was a junior in high school in Oregon, living right in the path of the umbra (the moon’s shadow). I don’t recall the 1979 solar eclipse, but that doesn’t surprise me given the mind of a 16-year-old, at least mine.
Or, it could be the fact that was about 8:15 a.m. in February. Februaries in Oregon can be depressing due to the lack of sunlight. Anyway, it’s painful because today there are 37-year-old adults who were born after I graduated from high school. Time has flown by.
One of the points I was going to make in this article is how much GIS technology has improved since the last total solar eclipse in 1979, but that was 38 years ago. Given Moore’s Law, it should have improved exponentially in the past 38 years, and it has.
One way the evolution of GIS is displayed are the maps of the Great American Solar Eclipse of 2017. Let’s start with this basic one illustrating the path of the moon’s shadow as it traverses the United States:
My office is in Lake Oswego, and my house is just east of Lake Oswego, as illustrated here:
Figure 3- Solar Eclipse 2017 Oregon path. Source: eclipse2017.org
As you can see in the above map, my house and office are really close to the 100 percent eclipse path. In fact, using the following interactive map, I determined that from my house the sun will be 99.77 percent eclipsed.
Figure 4- Interactive 2017 Eclipse Map. Source: NASA
Now, for some cool animations. Back in 1979 (even 2000), animations were tough to produce. With today’s computing power and software, it’s quite straight-forward and quick to produce high-quality animations. The following is a screenshot from a 48-second animation from NASA’s YouTube channel showing the path of the total eclipse.
Figure 5- 2017 Solar Eclipse animation. Source: NASA
As GISers, you know that software is the engine. Engines need fuel to run. With GIS, fuel is data. For this next animation, two key pieces of data enable a new level of accuracy in plotting the umbra.
The first is the topography (surface map) of the moon. It’s not as round as it appears from Earth. Its surface has jagged edges from varied terrain just like the Earth.
The second is the vantage point on the Earth. In producing the following animation, NASA used SRTM elevation data collected from the Space Shuttle Endeavor mission in 2000. In 2014, the U.S. government released high-resolution SRTM data (30-meter) to the public. As a result, the following animation incorporates high-resolution data with unprecedented accuracy.
Figure 6 – 2017 Solar Eclipse animation using high-accuracy topo and SRTM data. Source: NASA
Where are you going to be on August 21st?
The fascinating part of this event is that no matter where you are located in the continental United States, you’re going to experience the effect of the solar eclipse.
As I mentioned above, at my house and office, I’ll experience about 99.77 percent eclipse. If I drive 15 miles south, I can experience 100 percent eclipse. The challenge is going to be traffic. It is expected that a few hundred thousand tourists will visit Oregon for this experience.
Traffic is already heating up. Gas stations may run out of fuel. Grocery stores may run low on food. I have no idea what to expect for traffic if I decide to make the 15-mile drive. I assume country roads as well as I-5, Oregon’s major interstate road, will be jammed and everyone will be driving at a snail’s pace and when the actual event is in progress, stop on the side of the road.
If I was a betting man, I’d say I’ll make the trek with a tank full of fuel and a sack lunch (~10:15am is go-time in Western Oregon). I’ll take one piece of equipment to document the event, my drone. If I plan it right, I should be able to grab some incredible images, not necessarily of the solar eclipse itself, but of the crowds of people mesmerized by the event. Follow my Twitter for updates.
Lastly, it was the electric washing machine. That’s the only invention listed in the opening paragraph that existed in 1918, when the last event like this occurred. The next one won’t be until 2045. I think I’ll make the 15-mile drive on Monday.
I just returned from the 38th Annual Esri International User Conference (Esri UC), which is the largest gathering of GIS (geographic information systems) professionals in the U.S. No GIS event in the U.S. is close to its scale.
Every year for the past 38 years (I presume, as I’ve only attended the last 11), Esri President Jack Dangermond begins by spending time during the kick-off plenary session painting his GIS vision. I appreciate that he doesn’t just dive into Esri-product-specific information. Granted, I know he’s setting the stage for that, but why wouldn’t he? He has a vision, and the products Esri develops will naturally follow that vision. Every year during his plenary presentation, I look for striking statements he makes. This year, a statement that struck me was:
“GIS users come from nearly every field of human endeavor.”
Remember this slide from the Esri UC Plenary in 2015?
The concept was that historically, geospatial technology has been a technology for scientists, but as geospatial awareness builds with business consumers and then mainstream consumers, the users of geospatial technology will count in the millions and, eventually, billions of users. One could argue that location-based services (LBS) have already reached more than one billion as consumers use geospatial technology in their mobile phones for navigating.
Without geospatial technology, the mobile phone would just display latitude/longitude, offering no situational awareness. That’s not what the above slide is referring to. Geospatial awareness for the business consumer (and mainstream consumer) is becoming more about analytics. A communication tool, a decision-making tool. … not only for the scientist, but for a much wider audience.
Of course, some will say I’m just “drinking the Esri Kool-Aid.” I would agree, except for one point: It’s actually happening. Think about it.
Clearly, geospatial technology has reached thousands of users. (Reference the above slide.) Also, it’s clear that geospatial technology has already reached hundreds of thousands of users. We know this from market research, and even Esri has stated in the past it has about 350,000 customers of its enterprise, desktop and mobile products.
How about millions of users? Check out the following slide Mr. Dangermond presented at this year’s plenary session…
…4.4 million!
That’s more people that live in the State of Oregon (where I live). That’s more than one percent of the entire U.S. population. That’s the number of ArcGIS Online users.
If you’re still not convinced about the direction of the trend, then consider the number to the right of 4.4 million on the slide above: “+30%.” That means a 30 percent increase in ArcGIS Online users (presumably from this time last year). If you look closely at the slide, you’ll see that 30 percent is the lowest number. Map tiles served increased 95 percent to 3 billion. Open data downloads were more than 40 million, an increase of 200 percent.
Esri is a fascinating business case. With any other business model, it would be very difficult to accomplish what Esri has. Three points stand out to me:
Esri has remained a privately held company. In other words, they didn’t “go public” and risk polluting its culture. Also, being a privately held company held means Esri can make major strategic decisions (such as shifting to web GIS) very quickly without having to worry about Wall Street or the next quarter’s financial report. This is very rare, and makes it very difficult for other companies to compete with Esri. Esri says it spends 28 percent of its revenue on R&D (research and development). In comparison, Microsoft spends 13 percent.
The key management team has stayed intact. Senior management turnover is a killer in the technology world. Every time a key strategic manager changes, a company, or portion of it, is paralyzed until the next senior manager gears up. Six to 12 months can be lost during this transition. That’s an eternity in tech.
Focus. This is a function of leadership and a stable management team. Esri isn’t perfect, but they’ve done a solid job for being a billion-dollar organization.
Ok, enough of my armchair quarterbacking. Following are some quick observations.
Mobile GIS is king
The Collector and Survey123 user base is expanding, fueled by the rapid adoption of iOS and Android devices as field data-collection tools. Add to that the growth of high-accuracy GNSS receivers for the GIS professional.
This is a perfect storm of technology convergence that’s resulting in a paradigm shift in high-accuracy GIS data collection. In other words, there’s a ton of demand for iOS/Android mobile devices running hardware-agnostic data collection software (such as Collector or Survey123) connected to a high-accuracy Bluetooth GNSS receiver.
UAVs
The UAV technical sessions were jammed with people. If you’ve kept up with my GSS Monthly newsletter the past couple of years, you can see why. You can use an inexpensive UAV (~$1,500) to generate centimeter-level orthophotos, 3D models, volume calculations and elevation contours.
UAVs are another tool in the box, and one that I think most GIS users will eventually have access to. UAVs will continue to get cheaper and better. The challenge will continue to be how to consume UAV data efficiently into your GIS workflow.
Structure from motion
I see this technique being implemented with many technologies like UAVs and other devices. If you haven’t looked at the GeoSLAM device, the Zeb Revo, it looks incredible. With it, the GeoSLAM team scanned the San Diego Convention Center in 2 hours at 1.5-centimeter resolution.
The handheld Zeb Revo by GeoSLAM.Using the Zeb Revo, the GeoSLAM team scanned the San Diego Convention Center to 1.5-centimeter resolution in two hours.
The user simply walks around with it as it scans an area. No tripods, no setups. Just walk. It’s expensive, but so were GPS, UAVs and 3D scanners when they first entered the market. The beauty of the GeoSLAM product is its simplicity. Check out this three-minute YouTube video:
BYOD GNSS receivers
The transformation is here. Trimble is finally on board with the Catalyst, in a big way. No more proprietary GNSS handhelds. You pick the device you want to use (an Android smartphone or tablet) and the software you want to use, then select the BYOD GNSS receiver (submeter, decimeter, centimeter) you want to use. This is the way it is supposed to be. If you think about it, it was backwards for so many years!
Oh, and I forgot to mention. At nearly 18,000 attendees (that’s the high number I heard), this was the largest Esri UC in history. As someone who has attended the past 11 Esri UCs, this was the best one yet because I could feel the technology (hardware and software) really starting to come together to form practical solutions that can be deployed in a large scale.
Thanks, and see you next time. Follow me on Twitter.
It’s been a few months since I’ve published a GSS Monthly newsletter column. What a busy few months it has been. It’s been all about UAVs, high-precision GNSS projects and GIS, with some conferences and workshops sprinkled in between. High-accuracy GNSS technology and UAV technology are hot trends— red hot.
UAVs: Prosumer and mapping on a slope
Obviously, consumer UAVs have exploded in the mainstream consumer electronics market during the past five years. Since the FAA began requiring UAVs to be registered in late 2015, far more UAVs have been registered (~700,000 to date) with the FAA than manned aircraft (~320,000).
In fact, the number of registered UAVs aircraft eclipsed registered manned aircraft more than a year ago! The FAA reported that at any one point during the day, there are ~7,000 manned aircraft flying in the U.S. airspace. That begs the question, how many UAVs are flying above our heads at any one point in time? No one can answer that question.
On the coattails of consumer UAVs in mainstream America is the use of UAVs in the USA’s commercial world. Since the FAA opened the floodgates in August 2016 to allow almost anyone to fly UAVs for business ($150 and answer 42 out of 60 questions correctly), lots and lots of companies are buying inexpensive “prosumer” UAVs and extracting tremendous value from them.
Prosumer electronics is equipment and software targeted at the consumer market but also good enough to be used for business. The UAV market is a perfect example of this. DJI, by far the biggest UAV manufacturer in the world at $1B+ in annual revenue, targets the mainstream consumer market and sells a huge number of low-, medium- and high-end UAVs to businesses. Think about it: You can buy a DJI Phantom 4 Pro at your local Apple Store and the next day be generating one-foot elevation contours on a project site!
Following is an example of a papermill I flew a few weeks ago. I flew it in less than one hour (50 acres), generated an orthophoto with 2.4-cm/pixel resolution and a digital elevation model (DEM) with 4.79-cm/pixel resolution.
Figure 1. 2.4-cm/pixel resolution orthophoto, 50 acres.Figure 2. DEM with 4.79-cm/pixel resolution of the same flight.Figure 3. Zoomed-in image of the same DEM.
The detailed data above, generated from a $1,500 UAV, is clearly outstanding. By the way, the purpose of the project was to determine the volume of the various stockpiles, which I’ve not computed yet. But if the volume calcs are close enough to the traditional terrestrial-based measuring methods, the UAV return on investment (ROI) argument will be hard to beat.
It takes ~14 hours each month to measure all the stockpiles on this site using traditional terrestrial measurement tools. Also, the measurements must be taken on the weekend when the site activity is minimal. It took less than one hour to fly the entire site, and I flew it twice (one time west-east direction at 80/80 overlap and one time north-south at 70/70 overlap) to make sure I had enough data. I mean, seriously, I drove 1.5 hours to the site. Why not spend another 20 minutes to fly it in a perpendicular direction?
To date, I’ve only flown relatively flat sites such as construction sites, agricultural fields, and industrial sites. That was until a couple of weeks ago. While I’ve become pretty comfortable at flying open and relatively flat sites over the past 18 months, I’ve not ventured into flying a site with a lot of elevation changes and tree canopy. I finally did that earlier this month, and it was both challenging and rewarding. There are a few problems on sites with major elevation changes and tall tree canopy:
A. Maintaining visual line of sight (VLOS) as required by the FAA.
B. Flying in such a manner that the image-processing software has good quality data to work with so you can generate the products you need.
The mission planning/control software plays a very important roll in this process. Well, it always does, but it really does in this case. Typically, the mission planning/control folks want you to fly at a consistent height above the ground so your overlap is consistent. This is very difficult to accomplish if you’re flying a site with a lot of elevation change. In that case, they typically tell you to launch from the highest (or nearly the highest) elevation point and fly at that elevation.
The problem this causes is that you could end up flying 500, 600 or 700 feet above ground level (AGL). For example, if you are flying a site with 500 feet of elevation change and you instruct the mission planning/control software to fly at 350 feet AGL, at some point in the project the UAV will be at 850 feet AGL. That can be a problem from both a regulatory standpoint (FAA allows UAV flights up to 400 feet AGL) and an image-processing standpoint.
Fortunately, the mission planning/control software I use just introduced a Terrain Awareness feature. It uses SRTM (Shuttle Radar Topography Mission) elevation data. Granted, it’s 30-meter pixel elevation data, so each elevation block is 30 meters x 30 meters, so I really wondered if the resolution was high enough. The site I was going to fly was only 60 acres in size and had 550 feet of elevation change. Note that the trees on the site had already been harvested, so the land was relatively clear. There’s about a 550-foot difference from the projected launch point (purple dot) to the northern and western end of the site. Following is the mission plan for the site I was planning to fly.
Figure 4. 60-acre site with ~550 feet of elevation change.
To give you an idea of the slope, the solid red lines in the following image are 100-foot elevation contour lines. The green triangle is the projected UAV launch point. This was a great launch point because I could see the entire site and maintain VLOS.
Figure 5. Site topo with projected UAV launch point.
I chose to fly the mission at 300 feet AGL. I figured it would be high enough if there was some “slop” in the SRTM elevation model. Still, I was concerned about the resolution of the SRTM data because at 300 feet AGL, my UAV would be flying below the launch elevation due to the extreme elevation slope on the site. Remember, the Terrain Awareness feature of the mission planning/control software is based on the SRTM elevation data, and not based on any sensors in the UAV itself — if the SRTM elevation data was incorrect, my UAV might crash into the ground.
Following is the SRTM elevation data along with the flight path data displayed in the mission planning/control software.
Figure 6. The projected UAV flight path based on the SRTM elevation data.
The moment of truth came when I launched the UAV from the start point (purple dot) and watched it rise to 300 feet AGL to start its mission. The first few swaths were uneventful. After that, it started to fly into the canyon, following the terrain as programmed, then rise up from the canyon during each pass. It was a thing of beauty to watch.
Unfortunately, about 70% of the way through the mission, it started raining, so we called it quits. However, we proved that at least on the four sites I flew that day, the SRTM data and Terrain Awareness feature were effective in collecting data in steep-slope environments. Following is the 2.69-cm/pixel orthophoto generated from the flight. Note the tracks where the logging rigs pulled the logs up the steep slope.
Figure 7. 2.69-cm/pixel resolution orthophoto.
Following is a zoomed-in view of the UAV launch site.
Figure 8. Zoomed-in view of the orthophoto.
Following is an image of the 5.37-cm/pixel DEM generated from the flight data. Notice the logging tracks.
Figure 9. 5.7-cm/pixel image of the DEM generated from the flight data.
Following is a zoomed in view of the 5.37-cm/pixel DEM image.
Figure 10. Zoomed-in 5.37-cm DEM image of UAV launch point.
The mission was successful in proving that SRTM elevation data was sufficient enough to fly a mission with a dynamic AGL. It handled the steep slopes by maintaining a sufficient AGL elevation as I hoped it would despite only having 30-meter x 30-meter block elevation resolution. The image processing software seemed to like the UAV data, as you can see from the results above. I didn’t have to spend any additional processing time over and above what I usually spend in order to generate these products.
I did experience a hiccup with the mission planning/control software running on my iPad Mini 2. It turns out that the Terrain Awareness feature in my mission planning/control software requires some extra CPU horsepower — the software overpowered my iPad Mini and crashed once during a mission. The UAV kept flying its intended course as instructed, but it stopped taking photos when the software crashed, so I brought it back to the launch point.
After visiting the software vendor’s website, it became clear to me that it’s probably time to upgrade my iPad Mini to the latest model to keep up with the new features being implemented in the software.
A Quick Note on High-Accuracy GNSS
In March, I attended the Hawaii GIS conference and decided to perform some benchmark testing on a survey mark using WAAS and a high-accuracy GNSS receiver.
My goal was two-fold.
See how WAAS is behaving in Hawaii. WAAS in Hawaii is an anomaly because it’s far away from the Continental U.S. (CONUS) where all the WAAS reference stations are located (there’s one in Honolulu, but that’s it). In other words, Hawaii is the most challenging place for WAAS accuracy in North America.
See how many GNSS satellites I could track and use in Hawaii.
Holy moly, was I surprised at how good it was. I’ve tested WAAS in Hawaii several times in the past many years. The last time I tested it was in 2013 and the GNSS receiver I used (GPS + GLONASS) achieved a steady 80-cm accuracy. That was pretty darned good for WAAS in Hawaii at that time.
I packed up some receivers and hiked about 4 miles to a survey mark I could find in Honolulu. I was a great survey mark for testing because it was on the sidewalk of a quiet residential street. Following is a photo of the survey mark.
Figure 11. PID DK4162 survey mark in Honolulu.
I set up on the survey mark and then looked at the satellites the receiver was tracking. I wanted to know how many GPS, GLONASS, Galileo and BeiDou satellites were being used. Following is a screen shot.
Figure 12. Total number of GNSS satellites being used – 23.
Twenty-three GNSS satellites being used! Are you kidding me? This is more than double the number of GPS satellites being used. This illustrates the power of four-constellation GNSS that is only going to continue to get better over the next several years.
What surprised me the most was the number of Galileo satellites being used, and this was before two Galileo satellites were declared healthy in late May.
My next test was to evaluate WAAS accuracy. Who cares how many satellites the receiver is using if the accuracy isn’t improved? I plumbed the receiver antenna on the survey mark and plotted ~7 minutes of data.
Figure 13. Accuracy plot compared to the DK4162 survey mark coordinates.
Yep, that’s about 30-cm accuracy over a 7-minute period. That’s better by a factor of two compared to the accuracy I saw in 2013. Sure, WAAS has improved somewhat, and maybe the ionosphere was particularly happy that day, but I have to believe that the additional GNSS satellites contributed the most to the improvement in accuracy. In the next few months, I’m going to be performing more tests with WAAS and RTK on my GNSS test course near my office. I’ll keep you posted on the results of those tests.
The Esri International User Conference – July 10-14
As usual, I’ll be attending the largest gathering of GIS professionals in the U.S. next month, the Esri International User Conference. 16,000 of our colleagues will descend upon San Diego to share, network and enjoy the spatialness that we have for one another.
If you’re interested, I’m giving a couple of presentations at the Esri UC:
Tuesday (July 11), 08:30 a.m., Room 28B (subject to change)
Paper Title: An Efficient, Accuracy Mobile GIS Workflow using RTK GNSS
Session Title: Mobile Data Collection
This is cool project I worked on with WaterOne, a large water utility, to design a real-time, high-accuracy GNSS workflow in the Esri environment. They are collecting data at the centimeter level for mapping their above-ground assets as well as new construction using tablet computers and RTK GNSS receivers.
Thursday (July 13), 8:30 a.m., Room 29C (subject to change)
Paper Title: UAV (drone) applications for water utilities
Session Title: Applied GIS: Three Unique Examples
This is some groundbreaking work I’ve done with American Water on using UAV technology for mapping and inspection. We did a lot of experimenting during the proof-of-concept phase to figure out what applications are practical and which aren’t.
Marianna Kantor joined Esri as chief marketing officer in 2015. Prior to Esri, Marianna was the VP of Marketing at PTC, where she built the worldwide services marketing and field-enablement organization, helping drive sustained revenue growth in dynamic and changing markets. Marianna has held technology and marketing leadership positions throughout her career in leading organizations such as AT&T, Akamai, and Los Alamos National Labs. At Esri, Marianna is exposing and amplifying the transformational capabilities of geospatial technology as an indispensable tool for problem solving and decision making in business and government. Marianna holds two engineering degrees from Columbia University and University of Pennsylvania, and an Executive MBA from MIT.
As Esri’s chief technology officer, Jay Theodore guides the long-term vision for the ArcGIS platform. Jay is passionate about harnessing innovative ideas to increase the value companies gain from location intelligence, geoscience, computer science, and technology. He takes great pride in working with outstanding software developers, architects, and product engineers. Jay earned a master’s degree in computer science from Florida Institute of Technology, where his research focused on finite element analysis and modeling (FEA/FEM), computer graphics, and composite structure design for Space Station Freedom. He also holds a bachelor’s degree in computer engineering.
