Spatio-Temporal Graph Neural Networks for Streamflow Prediction in the Upper Colorado Basin

Authors

Akhila Akkala, Utah State UniversityFollow
Soukaina Filali Boubrahimi, Utah State UniversityFollow
Shah Muhammad Hamdi, Utah State UniversityFollow
Pouya Hosseinzadeh, Utah State UniversityFollow
Ayman Nassar, Utah State UniversityFollow

Document Type

Article

Author ORCID Identifier

Akhila Akkala https://orcid.org/0009-0005-8016-7533

Soukaina Filali Boubrahimi https://orcid.org/0000-0001-5693-6383

Shah Muhammad Hamdi https://orcid.org/0000-0002-9303-7835

Pouya Hosseinzadeh https://orcid.org/0000-0001-8045-2709

Ayman Nassar https://orcid.org/0000-0003-0878-5861

Journal/Book Title/Conference

Hydrology

Volume

12

Issue

3

Publisher

MDPI AG

Publication Date

3-17-2025

Journal Article Version

Version of Record

First Page

1

Last Page

27

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Abstract

Streamflow prediction is vital for effective water resource management, enabling a better understanding of hydrological variability and its response to environmental factors. This study presents a spatio-temporal graph neural network (STGNN) model for streamflow prediction in the Upper Colorado River Basin (UCRB), integrating graph convolutional networks (GCNs) to model spatial connectivity and long short-term memory (LSTM) networks to capture temporal dynamics. Using 30 years of monthly streamflow data from 20 monitoring stations, the STGNN predicted streamflow over a 36-month horizon and was evaluated against traditional models, including random forest regression (RFR), LSTM, gated recurrent units (GRU), and seasonal auto-regressive integrated moving average (SARIMA). The STGNN outperformed these models across multiple metrics, achieving an R² of 0.78, an RMSE of 0.81 mm/month, and a KGE of 0.79 at critical locations like Lees Ferry. A sequential analysis of input–output configurations identified the (36, 36) setup as optimal for balancing historical context and forecasting accuracy. Additionally, the STGNN showed strong generalizability when applied to other locations within the UCRB. These results underscore the importance of integrating spatial dependencies and temporal dynamics in hydrological forecasting, offering a scalable and adaptable framework to improve predictive accuracy and support adaptive water resource management in river basins.

Recommended Citation

Akkala, A.; Boubrahimi, S.F.; Hamdi, S.M.; Hosseinzadeh, P.; Nassar, A. Spatio-Temporal Graph Neural Networks for Streamflow Prediction in the Upper Colorado Basin. Hydrology 2025, 12, 60. https://doi.org/10.3390/ hydrology12030060