Abstract
Accurate short-to-subseasonal streamflow forecasts are becoming crucial for effective water management in an increasingly variable climate. However, streamflow forecast remains challenging over extended lead times, uncertainty in meteorological inputs, and increased frequency and variability in extreme weather and climate events. We implemented a Future Time Series Transformer (FutureTST) model for streamflow forecasting that separately integrates past meteorological and streamflow data while incorporating future weather conditions. FutureTST achieves a mean Nash-Sutcliffe Efficiency (NSE) of 0.82 to 0.67 for 1- to 30-day streamflow forecasts. Incorporating upstream streamflow information improved forecast accuracy by up to 10%. During real-time forecast, FutureTST maintains higher forecast skills of 9.03 for 1-day and 5.74 for 14-day forecasts. In contrast, calibrated process-based hydrological model forecasts become unreliable beyond a 4-day lead time. Our findings demonstrate the potential of FutureTST as a reliable streamflow forecasting tool that offers a valuable addition to operational flood monitoring systems and climate-resilient decision-making.
| Original language | English |
|---|---|
| Article number | e2025GL116707 |
| Journal | Geophysical Research Letters |
| Volume | 52 |
| Issue number | 14 |
| DOIs | |
| State | Published - Jul 28 2025 |
Funding
The authors acknowledge the Oak Ridge National Laboratory Distributed Active Archive Center [ORNL DAAC] for providing access to the Daymet data set, and the United States Geological Survey (USGS) for making the streamflow data set available. This research is supported by D. Lu's Early Career Project, sponsored by the Office of Biological and Environmental Research in the U.S. Department of Energy (DOE). Oak Ridge National Laboratory is operated by UT-Battelle, LLC, for the DOE under Contract DE-AC05-00OR22725. The authors acknowledge the Oak Ridge National Laboratory Distributed Active Archive Center [ORNL DAAC] for providing access to the Daymet data set, and the United States Geological Survey (USGS) for making the streamflow data set available. This research is supported by D. Lu's Early Career Project, sponsored by the Office of Biological and Environmental Research in the U.S. Department of Energy (DOE). Oak Ridge National Laboratory is operated by UT‐Battelle, LLC, for the DOE under Contract DE‐AC05‐00OR22725.