UC Merced researchers write AI drought-forecasting chapter for new Elsevier book
Six UC Merced scientists, from a postdoc to senior professors, explain how machine learning can combine satellite, sensor and climate data to forecast drought in California and elsewhere.
AI-assisted summary of reporting by UC Merced. How we report
UC Merced researchers write AI drought-forecasting chapter for new Elsevier book
Key Takeaways
- Six UC Merced researchers wrote a chapter on AI drought modeling for Elsevier's new book "Global Drought and Sustainability."
- The chapter explains how AI tools can combine climate records, current observations, satellite imagery and sensor data to forecast drought.
- The team says AI can add to existing drought monitoring, especially where ground data is thin, if it's paired with physics-based water science.
- The book has 14 chapters by more than 40 authors from over 15 institutions in at least 10 countries.
"Drought is becoming harder to manage because conditions can change quickly across farms, watersheds and regions," said Abid Sarwar, a project scientist at UC Merced.
Sarwar and five UC Merced colleagues wrote a chapter about that problem for "Global Drought and Sustainability," a new book from the academic publisher Elsevier. According to the university, their chapter, titled "Artificial Intelligence for Multiscale Drought Modeling and Decision Making," explains how AI and machine learning tools can combine historical climate records, current observations, satellite imagery and sensor data to assess and forecast drought. The timing matters in the Valley. After a couple of years with enough water, much of California showed "abnormally dry" conditions in spring 2026, the university said, citing the state drought monitor.
Who wrote it
The authors range from early-career researchers to senior faculty. Sarwar is a project scientist. Rui Gao is a postdoctoral scholar. The other four are professors: Safeeq Khan, John Abatzoglou, Josué Medellín-Azuara and Joshua Viers.
The university's announcement was written by Patty Guerra of UC Merced's communications staff, and it went out in May.
What the chapter argues
The team's claim is limited. AI can be a more scalable way to add to the drought monitoring that's already done, the researchers said, especially in regions with few ground observations. That only holds when the models are used together with a physics-based understanding of how water systems work.
The university says the need is growing because climate change is bringing more swings between wet and dry years. When a dry spell follows a wet one, forecasts have to account for changes on individual farms and across whole watersheds and regions, which is the problem Sarwar described.
The rest of the book
"Global Drought and Sustainability" has 14 chapters. More than 40 authors from over 15 institutions in at least 10 countries contributed. According to UC Merced, the book looks at how drought is connected to climate change and lays out science-based ways to improve water management, keep agriculture sustainable and make ecosystems more resilient. It also covers newer methods, including advanced drought forecasting and the use of AI to predict and respond to changing conditions.
UC Merced's earlier AI work
This isn't the campus's first AI project on water. ABC30 reported earlier that UC Merced received a $20 million federal grant to research artificial intelligence, which experts said could be vital for Central Valley agriculture. Abatzoglou, then an associate professor, was among the researchers the station interviewed.
More recently, UC Merced and University of California Agriculture and Natural Resources researchers installed an AI-powered irrigation system in an almond orchard in Parlier. It's designed to deliver the exact amount of water the trees need and to measure the results. Farms to Incubators reported that the project was led by Wan Du, an associate professor of electrical engineering and computer science. The orchard has one test bed watered by the AI system and one watered the traditional way.
Central Valley AI is produced by the CVAI Education Desk team and developed by Kaweah Tech, a regional firm that builds, deploys, and integrates AI solutions for businesses across California's Central Valley.