Improving streamflow simulation through machine learning-powered data integration and its potential for forecasting in the Western U.S.

Yang, Yuan; Pan, Ming; Feng, Dapeng; Xiao, Mu; Dixon, Taylor; Hartman, Robert; Shen, Chaopeng; Song, Yalan; Sengupta, Agniv; Delle Monache, Luca; Ralph, F. Martin

doi:https://doi.org/10.5194/hess-29-5453-2025

Articles | Volume 29, issue 20

https://doi.org/10.5194/hess-29-5453-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/hess-29-5453-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 29, issue 20

Research article

|

21 Oct 2025

Research article |

| 21 Oct 2025

Improving streamflow simulation through machine learning-powered data integration and its potential for forecasting in the Western U.S.

Yuan Yang, Ming Pan, Dapeng Feng, Mu Xiao, Taylor Dixon, Robert Hartman, Chaopeng Shen, Yalan Song, Agniv Sengupta, Luca Delle Monache, and F. Martin Ralph

Data sets

mhpi/hydroDL: MHPI-hydroDL (v2.0) Kuai Fang et al. https://doi.org/10.5281/zenodo.5015120

A suite of global, cross-scale topographic variables for environmental and biodiversity modeling Giuseppe Amatulli et al. https://doi.org/10.1594/PANGAEA.867115

Compiling and mapping global permeability of the unconsolidated and consolidated Earth: GLobal HYdrogeology MaPS 2.0 (GLHYMPS 2.0) J. Huscroft et al. https://doi.org/10.5683/SP2/TTJNIU

CW3E 1-km 1-hourly meteorological forcing on NWM grid. Center for Western Weather and Water Extremes (CW3E) M. Pan https://doi.org/10.5281/zenodo.14714512

Short summary

We explore a machine learning-based data integration method that integrates streamflow (Q) and snow water equivalent (SWE) to improve streamflow estimates at various lag times (1–10 d, 1–6 months) and timescales (daily and monthly) over Western US basins. Benefits rank as: integrating Q at the daily scale > Q at the monthly scale > SWE at the monthly scale > SWE at the daily scale. Results highlight the method’s potential for short- and long-term streamflow forecasting in the Western US.