Weather and climate extremes, despite their relatively rare occurrences, have disproportionately large impacts on agriculture. However, skillful operational subseasonal to seasonal (S2S) forecasts of extremes are not available to inform stakeholders and empower them to take mitigative actions. It is partly due to the sharp decrease in the prediction skills of global prediction models beyond a two-week forecast lead time, and partly due to the lack of significant collaboration between meteorologists and agricultural stakeholders in producing, formatting, and disseminating extreme weather prediction information. The overarching goal of the project is to develop skillful and actionable subseasonal to seasonal predictions of weather extremes and crop yields to help mitigate negative impacts on Midwest agriculture by effectively utilizing predictability sources and leveraging machine learning methods. By addressing the impacts of extreme events, the project will improve agricultural production and enhance food security. It will also aid the adoption of best practices by helping farmers overcome information gaps and uncertainty barriers, thereby improving agricultural sustainability and resilience.
Assessing the subseasonal to seasonal predictability of various weather/climate extremes affecting Midwest agriculture and developing prototype machine learning-based models for skillful predictions
Developing a scalable phenology-integrated crop yield forecasting model that can handle extreme conditions
Developing and strengthening partnership with stakeholders to co-produce actionable prediction products to mitigate agricultural impacts
The project team has participated in multiple stakeholder engagement meetings, including the Orr Agicultural Research and Demonstration Center Field Day in western Illinois, the Will County Illinois Farm Bureau's Nutrient Stewardship Field Day in northeast Illinois, the University of Illinois' Crop Physiology Field Day in Champaign, and Illinois Extension's Sauk Valley Field Day in northwest Illinois. For each of these events, the project team hosted focus groups with agricultural producers to discuss existing sources of weather forecast information, weather hazards and impacts, and weather communication. The feedback and data collected from these focus groups is being used to inform the development of the team's subseasonal-to-seasonal forecast tools.
University of Illinois-Urbana Champaign
Lead Principal Investigator
University of Illinois-Urbana Champaign
Co-Principal Investigator
University of Illinois-Urbana Champaign
Co-Principal Investigator
University of Illinois-Urbana Champaign
Collaborating Researcher
University of Illinois-Urbana Champaign
Graduate Student
University of Illinois-Urbana Champaign
Graduate Student
University of Illinois-Urbana Champaign
Graduate Student
University of Illinois-Urbana Champaign
Graduate Student
University of Illinois-Urbana Champaign
Graduate Student
Food Works
Illinois Farm Bureau
Illinois Specialty Growers Association
Nutrien Ag
University of Illinois Extension
USDA Midwest Climate Hub
Liu, Y., Diao, C., Yang, Z., Mei, W., & Guo, T. (2025). A novel Normalized Harvest Phenology Index (NHPI) for corn and soybean harvesting date detection using Landsat and Sentinel-2 imagery on Google Earth Engine. Remote Sensing of Environment, 331, 115016.
Graber, M., Wang, Z., and Trapp, R. J. (2026) Seasonal prediction of springtime tornado activity in the United States using a hybrid model, Weather and Climate Dynamics, 7, 1349–1361.