2112245

The broader impact of this SBIR Phase I project is to reduce weather and climate risk for organizations within the environmental and natural resource sectors through multi-year forecasts. The proposed forecast system uses a combination of Earth science and computer science to create a highly interpretable forecast system that is optimizable for the needs of specific industries. These multi-year ("sub-decadal") forecasts help renewable energy resource assessment, hydropower applications, and the mining industries. Better forecasting can lead to cheaper energy, more reliable long-term water supply management, and the improved environmental sustainability of mining operations. This SBIR Phase I project will advance development of a sub-decadal weather and climate forecast system integrating geoscience and machine learning. Project activities include: assessing the technical feasibility; evaluating the computational scalability; determining the relevant industry-specific inputs and outputs; and validating the output and interpretability. The algorithm must scale across multiple spatial and temporal timescales. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.