DAWN: Coproducing Predictive Decision Support Systems Using Enhanced NOAA Operational Climate Forecasts to Improve Agricultural Operations

Agricultural producers face complex decisions involving climate anomalies, economic pressures, and environmental concerns. Sustainable planning must consider local crop yields, socioeconomic drivers, competing user needs, and multi-scale climate feedbacks, impacting regional water availability and quality. Effective decision support requires predictive science at scales capturing climate and earth system feedbacks across regions and sectors. Under USDA funding, a transdisciplinary team is developing the DAWN (Dashboard for Agricultural Water use and Nutrient management) to provide Corn Belt farmers with enhanced predictive information. DAWN leverages NOAA operational climate forecasts, enhanced by coupled climate-crop dynamic downscaling and machine learning, to deliver credible, usable information by making subseasonal-to-seasonal forecasts accessible. The integrated approach includes engaging stakeholders to coproduce a decision support system, building a coupled modeling system to transfer holistic systems knowledge into practical tools, producing reliable forecasts to optimize crop productivity and environmental quality, and integrating research and extension into experiential education. This presentation will overview DAWN’s framework for integrating climate-agriculture research, extension, and education to bridge science and service, highlighting key challenges and lessons learned in infrastructure development, stakeholder engagement, product design, communication, and tool implementation. By effectively communicating scientific advancements to decision-makers, DAWN facilitates the transition of research into operational applications, thereby extending the benefits of research to societal services and incorporating feedback to continually improve the tools and processes, ultimately enhancing community engagement through science and services.