July 21, 2016 | Written by: Jeff Bertolucci
Categorized: AI for the Enterprise
Share this post:
Leading scientists predict that severe global water shortages could impact more than half of the world’s population by 2050. It’s a complex problem that defies easy solutions, but that hasn’t stopped one Arlington, Virginia-based startup from tackling it, leveraging the IBM Watson platform to develop water-conservation strategies for drought-stricken areas.
California’s Drought Dilemma
The OmniEarth story provides a fascinating glimpse into how the application of machine learning to huge chunks of data—in this case, aerial imagery—can help solve complicated, multi-layered and information-heavy problems too daunting for conventional approaches.
The story begins with the ongoing drought in the western United States, which reached a crisis point in April 2015, at which point California Governor Jerry Brown issued the state’s first mandatory water restrictions. Cities and towns had to cut water usage by 25 percent over the next 10 months—an extremely aggressive target.
A Data-driven Solution
OmniEarth’s team knew how to help. Founded in 2014 by a small team of scientists and entrepreneurs, this environmental technology company uses advanced geoanalytics, powered by the IBM Watson Visual Recognition cognitive service, to process, clarify and fuse vast amounts of satellite and aerial imagery with other data sets. By providing granular data on water consumption, the firm could help local agencies quickly identify land parcels that needed to reduce water usage, and by how much.
“If we can determine how much water a property needs on every given day,” says Chelsea Minton, senior sales engineer at OmniEarth, “and then compare that to how much that property is actually using, we can calculate exactly how much potential that property or that homeowner has to save water.”
OmniEarth Leverages Watson
The OmniEarth solution required computation-heavy analysis of large swaths of data. So they reached out to IBM Watson. The goal: to leverage Watson’s advanced processing, learning and visual recognition capabilities to quickly make sense of all that information.
The Watson Visual Recognition cognitive service analyzed OmniEarth’s extensive collection of aerial images of drought-stricken lots for specific areas where water usage could be scaled back. In one instance, Watson’s cognitive capabilities made it possible for the OmniEarth team to identify swimming pools in 150,000 parcels in just 12 minutes—something that would’ve taken hours or days if done manually.
Armed with this information, water districts were able to make very specific, water- saving recommendations to property owners and governments in drought areas.
The California case study is just one example of how OmniEarth’s scientists plan to develop smart, decision-making applications that revolutionize agriculture and land use. The team has indicated that IBM Watson will play a major role in enabling this “green data revolution.”
To learn more about OmniEarth’s utilization of IBM Watson, download the case study. To see a demonstration of the IBM Watson Visual Recognition service, and learn how this cognitive technology can deliver value for your business, click here.