From RNNs to Transformers: benchmarking deep learning architectures for hydrologic prediction

Liu, Jiangtao; Shen, Chaopeng; O'Donncha, Fearghal; Song, Yalan; Zhi, Wei; Beck, Hylke E.; Bindas, Tadd; Kraabel, Nicholas; Lawson, Kathryn

doi:10.5194/hess-29-6811-2025

Articles | Volume 29, issue 23

https://doi.org/10.5194/hess-29-6811-2025

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

https://doi.org/10.5194/hess-29-6811-2025

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

Articles | Volume 29, issue 23

Research article

| Highlight paper

|

01 Dec 2025

Research article | Highlight paper |

| 01 Dec 2025

From RNNs to Transformers: benchmarking deep learning architectures for hydrologic prediction

Jiangtao Liu, Chaopeng Shen, Fearghal O'Donncha, Yalan Song, Wei Zhi, Hylke E. Beck, Tadd Bindas, Nicholas Kraabel, and Kathryn Lawson

Supplement

https://doi.org/10.5194/hess-29-6811-2025-supplement

Model code and software

From RNNs to Transformers: benchmarking deep learning architectures for hydrologic prediction J. Liu and C. Shen https://doi.org/10.5281/zenodo.15852145

Short summary

Using global and regional datasets, we compared attention-based models and Long Short-Term Memory (LSTM) models to predict hydrologic variables. Our results show LSTM models perform better in simpler tasks, whereas attention-based models perform better in complex scenarios, offering insights for improved water resource management.