Improving the prediction of daily reservoir releases over the CONUS using conditioned LSTM

Journal Article · Mon Jun 23 00:00:00 EDT 2025 · Journal of Hydrology

DOI:https://doi.org/10.1016/j.jhydrol.2025.133750· OSTI ID:2586451

Tran, Hoang ^[1]; Zhou, Tian ^[1]; Tan, Zeli ^[1]; Fang, Yilin ^[1]; Leung, L. Ruby ^[1]

---

1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Reservoirs play a vital role in regulating streamflow timing and variability for hydroelectricity, flood control, water supply, irrigation, and recreation. Despite their importance, many reservoirs lack comprehensive operational guidelines, making their management complex due to conflicting operational objectives. Hence traditional policy-based reservoir models often fail to capture real-world conditions accurately and they depend on perfect streamflow predictions, which are not always available. In contrast, data-driven models like Long Short-Term Memory (LSTM) networks offer a robust alternative. This study introduces an approach that integrates reservoir characteristics—such as main use, climate, and maximum capacity—into the LSTM model to enhance reservoir release predictions. Using data from nearly 200 reservoirs in the contiguous United States (CONUS), our conditioned LSTM model (LSTM_cond) was compared with both the vanila LSTM and a traditional policy-based approach. Furthermore, our results show that while both LSTM_cond and LSTM perfoms better than the policy-based approach, LSTM_cond consistently outperforms LSTM for hydroelectric, water supply, irrigation, and recreation reservoirs. The KGE median values for LSTM_cond for out-sample reservoirs are 0.764, 0.565, 0.821, and 0.779, respectively, for the aforementioned reservoir types, which are consistently higher that the corresponding KGE values of 0.737, 0.413, 0.775, and 0.713 of LSTM, demonstrating its advantages in improving generalizability.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: AC05-76RL01830
• OSTI ID: 2586451
• Report Number(s): PNNL-SA--203350
• Journal Information: Journal of Hydrology, Journal Name: Journal of Hydrology Vol. 661; ISSN 0022-1694
• Publisher: Elsevier BV
• Country of Publication: United States
• Language: English

Related Subjects

CONUS
LSTM
Machine learning
Operational control
Reservoirs