Scalable Country-Level Crop Yield Modeling for Food Security and Risk Mitigation

We propose a scalable framework for generating regional crop yield predictions at the country level using coarse-resolution data, designed to support food security monitoring, policy planning, and climate adaptation. While much recent work focuses on fine-grained, field-level yield prediction, such models often require high-resolution data unavailable for many low-income countries. Our approach leverages coarser signals from satellites and household surveys, demonstrating through a Uganda proof-of-concept that machine learning models trained on regional averages can approach theoretical accuracy limits for smallholder yield prediction. We propose to extend this method by building country-specific models across all LSMS-ISA partner countries (Burkina Faso, Ethiopia, Malawi, Mali, Niger, Nigeria, Tanzania, and Uganda), and then constructing a pooled multi-country model. Comparing country-specific and multi-country models will allow us to assess generalizability in data-scarce settings. These models could provide actionable early warning signals of food shortages, enabling governments, NGOs, and international agencies to better target interventions and allocate resources under climate stress.