❌

Reading view

There are new articles available, click to refresh the page.

Microsoft and NASA create AI agents that can help scientists anticipate floods and other water woes

A screenshot shows how Hydrology Copilot can turn a simple query into an interactive, color-coded map. (Microsoft Infographic)

Microsoft and NASA say they’re applying artificial intelligence to a challenge that has become increasingly urgent: how to cope with flooding and other disasters driven by extreme weather.

The result of their efforts is Hydrology Copilot, a set of AI agents aimed at making hydrological data easier to access and analyze. The platform is built on the foundation that was established for NASA Earth Copilot, a cloud-based AI tool that can sift through petabytes of Earth science data.

Hydrology is the scientific study of Earth’s water cycle, which encompasses precipitation, runoff, evaporation and the movement of water through rivers, lakes and soil. It’s not just an academic exercise: Hydrologic insights are put to use in fields ranging from agriculture to forestry to urban development.

β€œNASA has long produced advanced hydrology and land-surface datasets, powering breakthroughs in drought early-warning systems, environmental planning and environmentalΒ research,” Juan Carlos LΓ³pez, a senior solution specialist at Microsoft who focuses on space and AI, wrote in a blog post. β€œYet despite their value, these datasetsΒ and the specialized toolsΒ requiredΒ to navigate and interpret themΒ remain difficult to access for many who could benefit most.”

That’s where Hydrology Copilot comes in: Powered by Microsoft Azure OpenAI Service and Microsoft Foundry, the platform lets researchers and others query NASA’s data using straightforward questions β€” for example, β€œWhich regions may be facing elevated flood risk?”

Hydrology Copilot simplifies access to one of NASA’s most advanced hydrology datasets, theΒ North American Land Data Assimilation System Version 3. The dataset integrates satellite measurements with computer models to present a continuously updated, high-resolution, continental-scale view of the water cycle.

Insights gleaned from the database can help planners figure out how to improve drought monitoring, agricultural planning, water resource management, flood risk assessment and emergency preparedness. Recent flooding in Western Washington, fueled by a succession of atmospheric rivers, shows how important it can be to gain such insights β€” and how useful Hydrology Copilot can be.

β€œThe goal of this project is to provide the tools that can enable local officials, city planners and emergency responders to more easily understand weather patterns and better prepare for the types of hydrological events we are seeing now in the Pacific Northwest and around the world, and will likely continue to see in the future,” a Microsoft spokesperson told GeekWire in an emailed statement.

Hydrology Copilot is still under development, and is being used primarily by researchers for now. Microsoft’s Azure AI team can provide further information about the platform. To take a test spin through more publicly accessible hydrology datasets, check out King County’s Hydrologic Information Center and the interactive map provided by the National Water Prediction Service.

❌