Data Driven Streamflow Forecasting

The Bureau of Reclamation, along with partners from the Center for Energy Advancement through Technological Innovation hydropower industry group including the Department of Energy - Pacific Northwest National Laboratory, Tennessee Valley Authority and others, ran a year-long evaluation of existing 10-day streamflow forecasting technologies. A companion prize competition open to the public, also focused on 10-day streamflow forecasts.  

Streamflow forecasting is integral to water management, and with higher skill forecasts water managers are better equipped to operate facilities for high flows, mitigate impacts of drought, and achieve other improved outcomes like hydropower generation. 

The growing capability of Artificial Intelligence (AI) / Machine Learning (ML) and High-Performance Computing has begun to be applied toward generating streamflow forecasts. This has the potential to complement traditional physically based streamflow forecast methods via hybrid or purely data-driven approaches. The purpose of this challenge aims to spur innovation in the field of streamflow forecasting, with emphasis on assessing the potential application of AI/ML for streamflow forecasting. 

During the challenge, forecasts were issued every day for a year and verified against observed flows. Numerous AI/ML methods outperformed benchmark state of practice forecasts. The top performer was Upstream Tech, a private forecast service provider. Reclamation continues to evaluate these methods at locations across the west to assess their benefits to western water management. 

Image