Machine Learning for Postprocessing Ensemble Streamflow Forecasts
This work addresses water policy and management decisions by improving streamflow forecasts, but it is incremental as it applies existing machine learning methods to a specific domain.
The authors tackled the problem of improving medium-range streamflow forecasts by integrating numerical weather prediction ensembles, hydrological modeling, and machine learning postprocessing, showing that their approach enhances forecast skill relative to simpler benchmarks and standalone models, with higher gains at medium-range timescales, high flows, and warm seasons.
Skillful streamflow forecasts can inform decisions in various areas of water policy and management. We integrate numerical weather prediction ensembles, distributed hydrological model and machine learning to generate ensemble streamflow forecasts at medium-range lead times (1 - 7 days). We demonstrate a case study for machine learning applications in postprocessing ensemble streamflow forecasts in the Upper Susquehanna River basin in the eastern United States. Our results show that the machine learning postprocessor can improve streamflow forecasts relative to low complexity forecasts (e.g., climatological and temporal persistence) as well as standalone hydrometeorological modeling and neural network. The relative gain in forecast skill from postprocessor is generally higher at medium-range timescales compared to shorter lead times; high flows compared to low-moderate flows, and warm-season compared to cool ones. Overall, our results highlight the benefits of machine learning in many aspects for improving both the skill and reliability of streamflow forecasts.