Artificial intelligence is bringing reliable weather forecasting to smallholder farmers across Africa, helping them adapt to increasingly unpredictable climate patterns. A collaboration between the University of Chicago and Ethiopia's meteorological institute is deploying AI-driven forecasts designed specifically for farmers' needs, supported by the Gates Foundation. This approach represents a fundamental shift in how developing nations can access climate information without requiring expensive supercomputers or dense networks of weather stations .

Why Do African Farmers Need Better Weather Forecasts?

For millions of smallholder farmers across Africa, weather is everything. A delayed rainy season, unexpected drought, or sudden flooding can wipe out an entire year's harvest. Yet most African countries lack the infrastructure that wealthy nations take for granted: satellite networks, weather stations, and the computing power to process climate data into actionable forecasts. Traditional forecasting methods require resources that simply aren't available in low- and middle-income countries .

Climate variability is intensifying the problem. According to Dr. Fetene Teshome, Director General of Ethiopia's Meteorological Institute, irregular rainy seasons, longer dry spells, and periods of excessive rainfall are becoming more common. "The role of climate information in minimizing risks and optimizing opportunities is therefore non-debatable," he stated .

Dr. Fetene Teshome

"Reliable weather information is the backbone of agricultural resilience, but traditional forecasts have historically required supercomputers and dense weather-observing station networks that many nations lack. By providing governments with the training, hardware and institutional capacity to adapt and use AI models, we are driving a paradigm shift in weather forecasting that brings high-quality and actionable information to people living in low- and middle-income countries," explained Katie Kowal, director for AI for Weather at the University of Chicago's Human-Centered Weather Forecasts Initiative.

Katie Kowal, Director for AI for Weather, Human-Centered Weather Forecasts Initiative, University of Chicago

How Is the University of Chicago Scaling AI Weather Forecasts in Ethiopia?

The initiative, called the Human-Centered Weather Forecasts Initiative (HCWF), is taking a collaborative approach that goes beyond simply deploying technology. Rather than imposing a one-size-fits-all AI model, researchers are working directly with Ethiopian meteorologists and farmers to build forecasts tailored to local conditions and agricultural practices .

The project involves multiple organizations working in concert. The Agricultural Innovation Mechanism for Scale (AIM for Scale) brings expertise in scaling agricultural innovations across the Global South. The University of Chicago's Development Innovation Lab and Precision Development, a nonprofit supporting smallholder farmers, are designing the actual forecast messages that will reach farmers. This ensures the AI predictions are translated into language and formats that farmers can actually use to make planting and harvesting decisions .

In February 2026, researchers convened more than 30 government and technical partners in Ethiopia to align on implementation. Technical sessions focused on identifying what signals the start of the rainy season, then building that knowledge directly into the AI model. This human-in-the-loop approach ensures the technology reflects local meteorological expertise .

Steps to Deploy AI Weather Forecasts for Agricultural Communities

• Build Local Capacity: Train government meteorologists and technical staff to understand, adapt, and maintain AI models rather than relying on external experts. This creates sustainable, long-term forecasting capability within the country.
• Design Farmer-Centered Messages: Work with agricultural extension services and farmers themselves to translate AI predictions into actionable guidance, such as optimal planting dates or irrigation schedules specific to local crops.
• Integrate Seasonal Knowledge: Combine AI model outputs with traditional meteorological understanding of regional patterns, such as rainy season onset indicators, to improve forecast accuracy and trust.
• Establish Cross-Sector Coordination: Convene government agencies, meteorological institutes, agricultural ministries, and development organizations to align on implementation and ensure forecasts reach farmers through existing agricultural advisory networks.

What Results Has This Approach Already Achieved?

The model has already proven successful at scale. The same team previously worked with India's Ministry of Agriculture and Farmers Welfare to distribute AI-based forecasts to 38 million Indian farmers during the 2025 monsoon season. That project is now being used as a global template for how national governments can deploy AI-driven forecasts to help farmers adapt to climate change .

Ethiopia's initiative builds on this momentum. The country is now positioned to become another proof point that AI weather forecasting can work in resource-constrained settings, potentially opening the door for similar projects across Africa and other developing regions.

The broader context matters here. While some AI applications for climate focus on large-scale energy systems or carbon tracking, this project targets a more immediate, human-centered need: helping the world's most vulnerable farmers survive increasingly erratic weather. It demonstrates that AI's climate value isn't limited to high-tech solutions for wealthy nations. When designed thoughtfully and deployed with local expertise, AI can democratize access to information that has historically been available only to wealthy agricultural operations .

Why Does This Matter Beyond Ethiopia?

The Ethiopia project is part of a larger initiative to integrate AI-driven forecasting techniques throughout several African countries. As climate variability increases, the gap between countries with advanced weather infrastructure and those without will only widen. By proving that AI can deliver reliable, actionable forecasts without requiring massive infrastructure investments, this work could reshape how developing nations prepare for climate impacts .

The approach also offers a counterpoint to concerns about AI's environmental footprint. Rather than consuming enormous amounts of energy to power data centers, these AI models are designed to be efficient and deployable on modest hardware. The goal is to maximize climate resilience while minimizing the technology's own environmental burden, a balance that the broader AI industry is still struggling to achieve .