Reservoir inflow forecasting using Voting Ensemble model:  A case study at A Luoi hydropower, central Vietnam

Chi Chi Cong Nguyen; Viet Long Doan; Trung Quan Nguyen; Ly Trieu Pham; Tien Cuong Nguyen; Van Hiep Le; Huu Huy Nguyen

doi:10.15625/2615-9783/23973

Author affiliations

Authors

Chi Cong Nguyen The University of Danang, University of Science and Technology, Da Nang, Vietnam
Viet Long Doan The University of Danang, University of Science and Technology, Da Nang, Vietnam
Trung Quan Nguyen The University of Danang, University of Science and Technology, Da Nang, Vietnam
Ly Trieu Pham The University of Danang, University of Science and Technology, Da Nang, Vietnam
Tien Cuong Nguyen Faculty of Vehicle and Energy Engineering, School of Engineering, Phenikaa University, Hanoi, Vietnam
Van Hiep Le Geotechnical and Artificial Intelligence research group, University of Transport Technology, Hanoi 100000, Vietnam
Huu Huy Nguyen Central Hydropower Joint Stock Company, Da Nang, Vietnam

DOI:

https://doi.org/10.15625/2615-9783/23973

Keywords:

Machine learning, Data-driven model, Voting Ensemble model, Rainfall-runoff modeling, A Luoi hydropower reservoir

Abstract

Accurate reservoir inflow forecasting is critical for real-time water management in monsoon-dominated basins. This study develops a weighted Voting Ensemble model to predict daily inflow to the A Luoi hydropower reservoir in central Vietnam using multi-station rainfall and lagged inflow data. Five machine learning models MLP, RF, KNN, XGB, and Ridge Regression, were trained on a unified feature set containing current and lagged rainfall inputs and three runoff memory terms, and subsequently combined using performance-based weights derived from time-series cross-validation errors. Evaluation using MSE, RMSE, and NSE shows that the ensemble outperforms all standalone learners, reducing RMSE by 12–25% and improving NSE from 0.70–0.91 (best individual models) to 0.92 on the test set. SHAP analysis is also used to explain model predictions and highlight the most influential features. During an independent verification period, the ensemble maintained strong performance (NSE ≈ 0.98), accurately capturing rising and recession limbs and minimizing peak-flow underestimation. These results demonstrate the robustness and operational feasibility of weighted ensemble learning for short-term inflow forecasting, offering valuable support for reservoir operation, flood mitigation, and water allocation in data-rich reservoir systems.

Downloads

Download data is not yet available.

References

Adnan D., Arunachalam V., Raju K.S., 2024. Daily reservoir inflow prediction using stacking ensemble of machine learning algorithms. Journal of Hydroinformatics, 26(5), 972–997. https://doi.org/10.2166/hydro.2024.210.

Chen M., Liu S., Lu D., 2023. Advancing subseasonal reservoir inflow forecasts using an explainable machine learning method. Journal of Hydro-environment Research, 51, 101584. https://doi.org/10.1016/j.jher.2023.101584.

Food and Agriculture Organization of the United Nations (FAO), 2023. The State of Food and Agriculture 2023: Revealing the True Cost of Food to Transform Agrifood Systems. Rome: FAO. https://doi.org/10.4060/cc7724en.

Güneş Şen S., 2025. Machine Learning-Based Water Level Forecast in a Dam Reservoir: A Case Study of Karaçomak Dam in the Kızılırmak Basin, Türkiye. Sustainability, 17(18), 8378. https://doi.org/10.3390/su17188378.

Khorram S., Jehbez N., 2023. A Hybrid CNN-LSTM Approach for Monthly Reservoir Inflow Forecasting. Water Resources Management, 37(10), 4097–4121. https://doi.org/10.1007/s11269-023-03541-w.

Li Z., Zhang Y., Wang L., 2024. Improving cascade reservoir inflow forecasting and extracting insights by decomposing the physical process using a hybrid model. Journal of Hydrology, 630, 130717. https://doi.org/10.1016/j.jhydrol.2024.130717.

Liu Z., Cai Y., Meng S., Zhu Z., Meng X., Wang X., 2025. Hybrid LSTM-ARIMA Model for Improving Multi-Step Inflow Forecasting of Reservoirs. Water, 17(21), 3051. https://doi.org/10.3390/w17213051.

Lundberg S.M., Lee S.-I., 2017. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.

McKinney, Wes, 2010. Data Structures for Statistical Computing in Python. Proceedings of the 9th Python in Science Conference 1697900(Scipy), 51–56.

Nagesh Kumar D., Maity R., 2024. Reservoir operation based machine learning models. Knowledge-Based Engineering and Sciences, 5(2), 145–158. https://doi.org/10.51526/kbes.2024.5.02.145-158.

Ngoc Anh Le, Nguyen Thanh Phong, Nhat Truong Pham, Le Quoc Huy, Son T. Mai, Do Duc Dung, Huy Anh Nguyen, Duong Tran Anh, 2025. Enhancing daily runoff forecasting in hydropower basins with a voting ensemble model using historical data. Hydrological Sciences Journal, 70(5), 833–845.

Nguyen Duc H., Nguyen Tien G., Le Xuan H., Tran Ngoc V., Nguyen Huu D., 2024. Multi-step-ahead prediction of water levels using machine learning: A comparative analysis in the Vietnamese Mekong Delta. Vietnam Journal of Earth Sciences, 46(4), 468–488. https://doi.org/10.15625/2615-9783/21067.

Nguyen Huu Duy, 2023. Daily streamflow forecasting by machine learning in Tra Khuc river in Vietnam. Vietnam Journal of Earth Sciences, 45(1), 82–97. https://doi.org/10.15625/2615-9783/17914.

Huu Duy Nguyen, Dinh Kha Dang, Y Nhu Nguyen, Chien Pham Van, Quang-Hai Truong, Quang-Thanh Bui, Alexandru-Ionut Petrisor, 2023. A framework for flood depth using hydrodynamic modeling and machine learning in the coastal province of Vietnam. Vietnam Journal of Earth Sciences, 45(4), 456–478. https://doi.org/10.15625/2615-9783/21368.

Nourani V., Gokcekus H., Gelete G.A., 2022. Utilizing deep learning machine for inflow forecasting in two different environment regions: a case study of a tropical and semi-arid region. Applied Water Science, 12(12), 266. https://doi.org/10.1007/s13201-022-01798-x.

Louise J. Slater, Louise Arnal, Marie-Amélie Boucher, Annie Y.-Y. Chang, Simon Moulds, Conor Murphy, Grey Nearing, Guy Shalev, Chaopeng Shen, Linda Speight, Gabriele Villarini, Robert L. Wilby, Andrew Wood, and Massimiliano Zappa., 2023. Hybrid forecasting: blending climate predictions with AI models. Hydrology and Earth System Sciences, 27(9), 1865–1889. https:// doi.org/10.5194/hess-27-1865-2023.

Fabian Pedregosa, Gael Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Edouard Duchesnay, 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

Phan V.-H., Ly H.-B., 2024. RIME-RF-RIME: A novel machine learning algorithm, denoted RIME-RF-RIME, to predict permeability based on six key features' importance and interaction effects. Journal of Science and Transport Technology, 4(1), 58–71. Doi: 10.58845/jstt.2024.en.4.1.58-71.

Robert Szczepanek, 2022. Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost. Hydrology, 9(12), 226.

Sit M., Demir I., Irmak S., 2025. Event-Based vs. Continuous Hydrological Modeling with HEC-HMS: A Review of Use Cases, Methodologies, and Performance Metrics. Hydrology, 12(2), 39. https://doi.org/10.3390/hydrology12020039.

Tebong N.K., Simo T., Takougang A.N., Ntanguen P.H., 2023. STL-decomposition ensemble deep learning models for daily reservoir inflow forecast for hydroelectricity production. Heliyon, 9(6), e16456. https://doi.org/10.1016/j.heliyon.2023.e16456.

Van Der Walt, Stéfan S., Chris Colbert, Gaël Varoquaux, 2011. The NumPy Array: A Structure for Efficient Numerical Computation. Computing in Science and Engineering, 13(2), 22–30.

Wang M., Lu D., Gangrade S., 2025. Enhancing Multi-Step Reservoir Inflow Forecasting: A Time-Variant Encoder-Decoder Approach. Geosciences, 15(8), 279. https://doi.org/10.3390/geosciences15080279.

Weekaew J., Ditthakit P., Kittiphattanabawon N., Pham Q.B., 2024. Quartile Regression and Ensemble Models for Extreme Events of Multi-Time Step-Ahead Monthly Reservoir Inflow Forecasting. Water, 16(23), 3388. https://doi.org/10.3390/w16233388.

Zhang Y., Li J., Wang X., Chen Y., 2024. Data-driven forecasting framework for daily reservoir inflow time series considering the flood peaks based on multi-head attention mechanism. Journal of Hydrology, 639, 131593. https://doi.org/10.1016/j.jhydrol.2024.131593.