A University of Chicago research team has received a $10 million grant from the Laude Institute to develop artificial intelligence weather forecasting models and a software platform aimed at improving decision-making for people in low- and middle-income economies, according to a UChicago news release.
The grant builds on earlier work by the team, which has already provided AI-generated forecasts to more than 50 million smallholder farmers in South Asia and Africa over the past two seasons. Those forecasts, sent via text message, helped farmers decide when to plant their crops—a critical choice in tropical climates where the timing of monsoon rains can determine whether a harvest succeeds or fails.
For a small farmer in a tropical region, the difference between planting too early and losing a crop versus planting at the right time can be a matter of economic survival, the university noted. The new funding aims to make the forecasting process faster, simpler, and more accurate, and to extend it to new regions and types of weather hazards.
The team is led by Rebecca Willett, the Worah Family Professor of Statistics and Computer Science; Pedram Hassanzadeh, an associate professor in Geophysical Sciences; Ian Foster, the Arthur Holly Compton Distinguished Service Professor of Computer Science; and Michael Kremer, a Nobel laureate and University Professor in Economics who also serves as Chief Economist and Senior Vice President for Development Economics at the World Bank Group.
According to UChicago, the researchers are working to close a persistent gap between weather forecasting capabilities in mid-latitude and tropical regions. Wealthy nations have developed modern forecasting models primarily for mid-latitude climates, relying on dense networks of observation stations and powerful supercomputers—resources that most meteorological agencies in tropical countries lack. Even when those models are applied globally, they are typically designed to predict general conditions rather than the specific events, such as monsoon onset, that drive farmers' most important decisions.
The UChicago team's approach uses AI-powered systems that can work with sparse observational data and modest computing resources. The group has developed methods that blend the best existing AI and physics-based forecasts and then tune them to the specific, human-centered decisions that farmers, health officials, and emergency managers face.
Over the last six months, the team and its collaborators have reduced the time needed to benchmark and adapt forecasting models from four to five months of expert labor to a single day of expert review, the university reported.
"The leading AI weather models are evaluated on whether they accurately predict global temperature and precipitation," Willett said in the release. "That's useful if you're a meteorologist. But it tells you almost nothing about whether a model will correctly predict monsoon onset for a farmer in West Java or a dangerous heat wave for a public health official in Addis Ababa."
Instead, Willett said, the team built its platform around a different question: "not 'how accurate is the model' but 'does this forecast help a specific person make a better decision in a specific place.'"
With the Laude Institute support, the team will build new AI weather forecasting frameworks embedded in the UChicago–Laude AI Almanac, described as a free, open-source platform that will allow any meteorological agency, government, or nonprofit to generate, evaluate, and deploy AI weather forecasts tailored to their own geography, observations, decision needs, and local weather dynamics. The system is designed to run without requiring specialized technical expertise, supercomputing infrastructure, or dense observational networks.
"This platform will significantly accelerate the translation of the AI-driven weather forecasting revolution into enhanced capabilities of the meteorological agencies that need it most, so they can give high-quality, actionable information to the people they serve," Hassanzadeh said.
Early deployments have already demonstrated the potential of AI weather forecasts. From 2024 to 2026, the UChicago Human-Centered Weather Forecasts initiative supported government agricultural ministries in producing AI forecasts that were sent via text message to tens of millions of farmers in Africa and South Asia. Those forecasts correctly predicted an unusual stall in the seasonal rains, providing an early warning. Farmers who received the AI-powered forecast could make informed planting decisions rather than planting too early and losing their crop, according to the university.
Funding from the Laude grant will enable the expansion of this project into a worldwide system that addresses various weather and climate threats. Major development banks and charitable organizations, including the OpenAI Foundation and the Gates Foundation, are making significant investments to provide precise weather predictions and decision-making aids to agricultural workers, public health professionals, and government leaders in low- and middle-income nations, aiming to impact hundreds of millions of individuals in the coming years, UChicago reported.
For forecast delivery, the UChicago team collaborates closely with those groups, plus the Agricultural Innovation Mechanism for Scale (AIM for Scale) initiative, the nonprofit Precision Development, and UC Berkeley. Funding from the Laude Institute will enhance the computational foundation of these activities through novel AI techniques, community-centered trusted assessment, and an open, scalable platform that broadens access and boosts forecast accuracy without requiring heavy spending on computing hardware or software coding. The platform will serve agriculture, public health, and alerts for compound climate extremes..
"Reaching hundreds of millions of people requires infrastructure that can scale across countries, datasets, and weather hazards," Foster said. "With Globus, a non-profit research data management platform, we have learned how to make large-scale research computing reliable and accessible. We will draw on that experience to help meteorological agencies adapt and deliver forecasts for their communities without having to build and maintain their own computing infrastructure."
Government meteorologists from 14 nations are already being trained through a joint AIM for Scale initiative, run by UChicago and the UAE's Mohamed bin Zayed University of Artificial Intelligence, which aims to expand to 30 countries by 2027..
"If this works for weather, it is a model for AI for public health, for education, and for many other areas where the people who need these tools most cannot pay for them," Kremer said. "Philanthropy can step up where the market cannot. That is what makes this moment extraordinary."
For university students, the project highlights how AI research can be applied to real-world challenges in development economics and climate resilience, and it offers potential pathways for those interested in data science, atmospheric physics, or international development to work on problems with direct human impact.