Machine learning generated streamflow drought forecasts for the conterminous United States (CONUS): developing and evaluating an operational tool to enhance sub-seasonal to seasonal streamflow drought early warning for gaged locations

Frontiers in Water
By: , and 

Links

Abstract

Forecasts of streamflow drought, when streamflow declines below typical levels, are notably less available than for floods or meteorological drought, despite widespread impacts. We apply machine learning (ML) models to forecast streamflow drought 1–13 weeks ahead at 3,219 streamgages across the conterminous United States. We applied two ML methods (Long short-term memory neural networks; Light Gradient-Boosting Machine) and two benchmark models (persistence; Autoregressive Integrated Moving Average) to predict weekly streamflow percentiles with independent models for each forecast horizon. ML models outperformed benchmarks in predicting continuous streamflow percentiles below 30%. ML models generally performed worse than persistence models for discrete classification (moderate, severe, extreme) but exceeded the benchmark models for drought onset/termination. Performance was better for less intense droughts and shorter horizons, with predictive power for 1–4 weeks for severe droughts (10% threshold). This work highlights challenges and opportunities to advance hydrological drought forecasting and supports a new experimental forecasting tool.

Suggested Citation

Hammond, J., Goodling, P.J., Diaz, J.A., Corson-Dosch, H.R., Heldmyer, A.J., Hamshaw, S.D., McShane, R., Ross, J.C., Sando, R., Simeone, C., Smith, E.A., Staub, L.E., Watkins, D., Wieczorek, M., Wnuk, K., Zwart, J.A., 2026, Machine learning generated streamflow drought forecasts for the conterminous United States (CONUS): developing and evaluating an operational tool to enhance sub-seasonal to seasonal streamflow drought early warning for gaged locations: Frontiers in Water, v. 7, 1709138, 32 p., https://doi.org/10.3389/frwa.2025.1709138.

Study Area

Publication type Article
Publication Subtype Journal Article
Title Machine learning generated streamflow drought forecasts for the conterminous United States (CONUS): developing and evaluating an operational tool to enhance sub-seasonal to seasonal streamflow drought early warning for gaged locations
Series title Frontiers in Water
DOI 10.3389/frwa.2025.1709138
Volume 7
Publication Date January 07, 2026
Year Published 2026
Language English
Publisher Frontiers Media
Contributing office(s) Maryland-Delaware-District of Columbia Water Science Center
Description 1709138, 32 p.
Country United States
Other Geospatial conterminous United States
Additional publication details