Draper develops a game that informs decision makers about the value of satellite data
CAMBRIDGE, MA—Get ready for a sharp increase in satellite data. The current crop of 1,700 satellites orbiting Earth is poised to top 10,000 in 20 years. That should be good news for everyone from farmers and shipping firms to law enforcement and insurance companies—anyone keen to use satellite data to make better decisions, reduce risks, fight poverty or catch criminals.
But that rich trove of data can be a mixed blessing, because many customers can’t tell what is noise and what is truly valuable, according to John Irvine, a chief data scientist at Draper. Irvine develops tools to analyze satellite data to gain insights beyond the standard assessments of a given location, such as determining urban decay, affluence, crime and other social factors.
“The problem isn’t that the data aren’t there,” Irvine said. “The problem is there is too much data and it’s too hard for a human to know what is going to be useful.” NASA agrees, going so far as to say mission managers aren’t allocating nearly enough money in their budgets for satellite data analysis. Irvine and his colleagues found a promising path forward in figuring out which data will yield useful information through gamification.
Irvine and his team named their game UPBEAT, which stands for Understanding Persistence for Better Exploitation, Analysis and Tasking. “The game works by simulating how particular behaviors would present in satellite data,” he said. “The goal of the game is to use satellite data to solve specific problems. Players can select data from different satellites, and are scored by how well they solve the problem. While players compete for high scores, their results reveal which data are useful and which aren’t.”
An example of an UPBEAT challenge would be to catch drug traffickers in ocean waters. Fishing boats that go about legitimate business leave from and return to the same ports. Drug runners masquerading as fishing boats, on the other hand, travel from port to port as they pick up and deliver drugs. With UPBEAT, law enforcement customers could experience how satellite data might help identify and track such suspicious movements and potentially stem the tide of drug trafficking. “We found that players are more likely to use data if they have to compete for high scores in a game rather than rely on a lengthy data analysis,” Irvine said.
UPBEAT can be modified for a variety of scenarios, such as identifying ocean patterns related to pollution and sea temperature or detecting illegal logging operations from a comparison of vehicle traffic and the forest canopy.
Draper isn’t alone in pursuing gamification and visualization tools to leverage satellite data and imagery. The U.S. National Geospatial-Intelligence Agency (NGA)—the largest buyer of satellite imagery in the world—has stated a shift in its strategy from data acquisition toward data analytics to produce informative products. “We must pursue and discover meaning. We will discover the vital patterns and uncover relationships hidden in the massive collections of content continuously updated in and through the Map of the World. And we will deliver highly visual, easy-to-understand insights on mobile devices in every security domain,” NGA Director Robert Cardillo said.
The UPBEAT project complements other work Draper has done in the growing field of small imaging satellites for government and commercial customers. Draper’s experience ranges from small satellite guidance and navigation to enabling better data transmission to ground stations to making satellite imagery understandable with big data analytics.
Irvine will present UPBEAT at the 32nd Annual Small Satellite Conference at Utah State University.
Draper has continued to advance the understanding and application of human-centered engineering to optimize the interaction and capabilities of the human’s ability to better understand, assimilate and convey information for critical decisions and tasks. Through its Human-Centered Solutions capability, Draper enables accomplishment of users’ most critical missions by seamlessly integrating technology into a user’s workflow. This work leverages human-computer interaction through emerging findings in applied psychophysiology and cognitive neuroscience. Draper has deep skills in the design, development, and deployment of systems to support cognition – for users seated at desks, on the move with mobile devices or maneuvering in the cockpit of vehicles – and collaboration across human-human and human-autonomous teams.
Draper combines specific domain expertise and knowledge of how to apply the latest analytics techniques to extract meaningful information from raw data to better understand complex, dynamic processes. Our system design approach encompasses effective organization and processing of large data sets, automated analysis using algorithms and exploitation of results. To facilitate user interaction with these processed data sets, Draper applies advanced techniques to automate understanding and correlation of patterns in the data. Draper’s expertise encompasses machine learning (including deep learning), information fusion from diverse and heterogeneous data sources, optimized coupling of data acquisition and analysis and novel methods for analysis of imagery and video data.