Ensembling differentiable process-based and data-driven  models with diverse meteorological forcing datasets to  advance streamflow simulation

Li, Peijun; Song, Yalan; Pan, Ming; Lawson, Kathryn; Shen, Chaopeng

doi:10.5194/hess-29-6829-2025

Articles | Volume 29, issue 23

https://doi.org/10.5194/hess-29-6829-2025

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

https://doi.org/10.5194/hess-29-6829-2025

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

Articles | Volume 29, issue 23

Research article

|

01 Dec 2025

Research article |

| 01 Dec 2025

Ensembling differentiable process-based and data-driven models with diverse meteorological forcing datasets to advance streamflow simulation

Peijun Li, Yalan Song, Ming Pan, Kathryn Lawson, and Chaopeng Shen

Data sets

Streamflow Simulation Data from Differentiable HBV and LSTM Models Using CAMELS Datasets P. Li et al. https://doi.org/10.5281/zenodo.16895228

A large-sample watershed-scale hydrometeorological dataset for the contiguous USA A. J. Newman and M. Clark https://doi.org/10.5065/D6MW2F4D

NeuralHydrology - A Python library for Deep Learning research in hydrology F. Kratzert et al. https://doi.org/10.5281/zenodo.6326394

differentiable parameter learning (dPL) + HBV hydrologic model D. Feng et al. https://doi.org/10.5281/zenodo.7943626

Short summary

This study explores how combining different model types improves streamflow predictions, especially in data-sparse scenarios. By integrating two highly accurate models with distinct mechanisms and leveraging multiple meteorological datasets, we highlight their unique strengths and set new accuracy benchmarks across spatiotemporal conditions. Our findings enhance the understanding of how diverse models and multi-source data can be effectively used to improve hydrological predictions.