Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM

Wandee Thaisiam; Pongbavorn Rattanapant; Pawit Kraisornnukhor; Papis Wongchaisuwat

doi:10.1016/j.wse.2025.11.001

Volume 19 Issue 1

Mar. 2026

Turn off MathJax

Article Contents

Article Navigation > Water Science and Engineering > 2026 > 19(1): 11-22

Wandee Thaisiam, Pongbavorn Rattanapant, Pawit Kraisornnukhor, Papis Wongchaisuwat. 2026: Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM. Water Science and Engineering, 19(1): 11-22. doi: 10.1016/j.wse.2025.11.001

Citation:

Wandee Thaisiam, Pongbavorn Rattanapant, Pawit Kraisornnukhor, Papis Wongchaisuwat. 2026: Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM. Water Science and Engineering, 19(1): 11-22. doi: 10.1016/j.wse.2025.11.001

Citation:

Wandee Thaisiam, Pongbavorn Rattanapant, Pawit Kraisornnukhor, Papis Wongchaisuwat. 2026: Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM. Water Science and Engineering, 19(1): 11-22. doi: 10.1016/j.wse.2025.11.001

PDF( 0 KB)

Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM

doi: 10.1016/j.wse.2025.11.001

a. Department of Water Resources Engineering, Kasetsart University, Bangkok 10900, Thailand;
b. Department of Industrial Engineering, Kasetsart University, Bangkok 10900, Thailand

Received Date: 2025-04-20
Accepted Date: 2025-09-24

Available Online: 2026-03-28

Abstract

Abstract

Effective management of multi-purpose reservoirs requires precise planning and accurate data to balance competing objectives and constraints. Reservoir inflow forecasting is critical in this process, with deep learning models increasingly applied across various time scales, from hourly to annual predictions. This study integrated a two-layer stacked long short-term memory network with decomposed data and a rolling window technique to enhance multi-day reservoir inflow forecasting accuracy. The proposed framework was applied to the Lam Takhong Dam in northeastern Thailand, a tropical monsoon region characterized by distinct wet and dry seasons. The dataset included daily reservoir inflow, river discharge, and average rainfall records spanning multiple years. Four forecasting strategies were compared for up to 7-d predictions: multi-step prediction, rolling prediction, multi-step prediction with decomposition, and rolling prediction with decomposition. The results indicated that while all models performed similarly for short-term predictions, accuracy declined over longer forecasting horizons. The rolling window approach with decomposition consistently outperformed others, achieving an average correlation coefficient of 0.92 and an average Nash—Sutcliffe model efficiency coefficient of 0.78 at the 7-d forecasting horizon. These findings demonstrate the practical advantages of integrating decomposition into a dynamic forecasting framework, particularly in reducing error accumulation in extended hydrological predictions.
- Reservoir inflow forecasting,
- Deep learning,
- Long short-term memory network,
- Rolling window,
- Decomposition

FullText(HTML)

References(40)

References

[1]	Ahmad, S., Hossain, F., 2019. A generic data-driven technique for forecasting of reservoir inflow: Application for hydropower maximization. Environmental Modelling & Software 119, 147-165. https://doi.org/10.1016/j.envsoft.2019.06.008.
[2]	Ahmadi, F., Tohidi, M., Sadrianzade, M., 2023. Streamflow prediction using a hybrid methodology based on variational mode decomposition (VMD) and machine learning approaches. Applied Water Science 13(6), 135. https://doi.org/10.1007/s13201-023-01943-0.
[3]	Apaydin, H., Feizi, H., Sattari, M.T., Colak, M.S., Shamshirband, S., Chau, K.-W., 2020. Comparative analysis of recurrent neural network architectures for reservoir inflow forecasting. Water 12(5), 1500. https://doi.org/10.3390/w12051500.
[4]	Bak, G., Bae, Y., 2023. Deep learning algorithm development for river flow prediction: PNP algorithm. Soft Computing 27(18), 13487-13515. https://doi.org/10.1007/s00500-023-08254-1.
[5]	Basha, C.Z., Bhavana, N., Bhavya, P.S.V., 2020. Rainfall prediction using machine learning & deep learning techniques. In: Proceedings of the 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC). ICESC, Coimbatore, pp. 92-97. https://doi.org/10.1109/ICESC48915.2020.9155896.
[6]	Bell, B., Wallace, B., Zhang, D., 2012. Forecasting river runoff through support vector machines. In: Proceedings of the 2012 IEEE 11th International Conference on Cognitive Informatics and Cognitive Computing. IEEE, Kyoto, pp. 58-64. https://doi.org/10.1109/ICCI-CC.2012.6311127.
[7]	Bergmeir, C., Benitez, J.M., 2012. On the use of cross-validation for time series predictor evaluation. Information Sciences 191, 192-213. https://doi.org/10.1016/j.ins.2011.12.028.
[8]	Chang, F.-J., Chang, Y.-T., 2006. Adaptive neuro-fuzzy inference system for prediction of water level in reservoir. Advances in Water Resources 29(1), 1-10. https://doi.org/10.1016/j.advwatres.2005.04.015.
[9]	Chen, C., Jiang, J., Liao, Z., Zhou, Y., Wang, H., Pei, Q., 2022. A short-term flood prediction based on spatial deep learning network: A case study for Xi County, China. Journal of Hydrology 607, 127535. https://doi.org/10.1016/j.jhydrol.2022.127535.
[10]	Chen, J., Wei, X., Liu, Y., Zhao, C., Liu, Z., Bao, Z., 2024. Deep learning for water quality prediction-A case study of the Huangyang Reservoir. Applied Sciences 14(19), 8755. https://doi.org/10.3390/app14198755.
[11]	Cheng, M., Fang, F., Kinouchi, T., Navon, I.M., Pain, C.C., 2020. Long lead-time daily and monthly streamflow forecasting using machine learning methods. Journal of Hydrology 590, 125376. https://doi.org/10.1016/j.jhydrol.2020.125376.
[12]	Choong, S.-M., El-Shafie, A., 2015. State-of-the-art for modelling reservoir inflows and management optimization. Water Resources Management 29(4), 1267-1282. https://doi.org/10.1007/s11269-014-0872-z.
[13]	Ehteram, M., Ahmed, A.N., Sherif, M., El-Shafie, A., 2024. An advanced deep learning model for predicting water quality index. Ecological Indicators 160, 111806. https://doi.org/10.1016/j.ecolind.2024.111806.
[14]	Fan, M., Liu, S., Lu, D., 2023. Advancing subseasonal reservoir inflow forecasts using an explainable machine learning method. Journal of Hydrology: Regional Studies 50, 101584. https://doi.org/10.1016/j.ejrh.2023.101584.
[15]	Granata, F., Di Nunno, F., Pham, Q.B., 2024. A novel additive regression model for streamflow forecasting in German rivers. Results in Engineering 22, 102104. https://doi.org/10.1016/j.rineng.2024.102104.
[16]	Guo, J., Zhou, J., Qin, H., Zou, Q., Li, Q., 2011. Monthly streamflow forecasting based on improved support vector machine model. Expert Systems with Applications 38(10), 13073-13081. https://doi.org/10.1016/j.eswa.2011.04.114.
[17]	Heddam, S., Ptak, M., Sojka, M., Kim, S., Malik, A., Kisi, O., Zounemat-Kermani, M., 2022. Least square support vector machine-based variational mode decomposition: A new hybrid model for daily river water temperature modeling. Environmental Science and Pollution Research 29(47), 71555-71582. https://doi.org/10.1007/s11356-022-20953-0.
[18]	Herbert, Z., Asghar, Z., Oroza, C., 2021. Long-term reservoir inflow forecasts: Enhanced water supply and inflow volume accuracy using deep learning. Journal of Hydrology 601, 126676. https://doi.org/10.1016/j.jhydrol.2021.126676.
[19]	Jothiprakash, V., Magar, R.B., 2012. Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data. Journal of Hydrology 450-451, 293-307. https://doi.org/10.1016/j.jhydrol.2012.04.045.
[20]	Latif, S.D., Ahmed, A.N., Sathiamurthy, E., Huang, Y.F., El-Shafie, A., 2021. Evaluation of deep learning algorithm for inflow forecasting: A case study of Durian Tunggal Reservoir, Peninsular Malaysia. Natural Hazards 109(1), 351-369. https://doi.org/10.1007/s11069-021-04839-x.
[21]	Lee, S., Kim, J., 2021. Predicting inflow rate of the Soyang River Dam using deep learning techniques. Water 13(17), 2447. https://doi.org/10.3390/w13172447.
[22]	Liao, S., Liu, Z., Liu, B., Cheng, C., Jin, X., Zhao, Z., 2020. Multistep-ahead daily inflow forecasting using the ERA-Interim reanalysis data set based on gradient-boosting regression trees. Hydrol. Earth Syst. Sci. 24(5), 2343-2363. https://doi.org/10.5194/hess-24-2343-2020.
[23]	Liu, J., Xu, T., Lu, C., Yang, J., Xie, Y., 2024. Variational mode decomposition coupled LSTM with encoder-decoder framework: An efficient method for daily streamflow forecasting. Earth Science Informatics 18(1), 38. https://doi.org/10.1007/s12145-024-01569-z.
[24]	Luo, B., Fang, Y., Wang, H., Zang, D., 2020. Reservoir inflow prediction using a hybrid model based on deep learning. IOP Conference Series: Materials Science and Engineering 715, 012044. https://doi.org/10.1088/1757-899X/715/1/012044.
[25]	Muhammad, S., Li, X., Bashir, H., Azam, M.I., 2021. A hybrid model for runoff prediction using variational mode decomposition and artificial neural network. Water Resources 48(5), 701-712. https://doi.org/10.1134/S0097807821050171.
[26]	Papamichail, D., 2001. Seasonal ARIMA inflow models for reservoir sizing. Journal of the American Water Resources Association 37(4), 877-885. https://doi.org/10.1111/j.1752-1688.2001.tb05519.x.
[27]	Paul, T., Raghavendra, S., Ueno, K., Ni, F., Shin, H., Nishino, K., Shingaki, R., 2021. Forecasting of reservoir inflow by the combination of deep learning and conventional machine learning. In: Proceedings of the 2021 International Conference on Data Mining Workshops (ICDMW). ICDMW, Auckland, pp. 558-565. https://doi.org/10.1109/ICDMW53433.2021.00074.
[28]	Sankaranarayanan, S., Prabhakar, M., Satish, S., Jain, P., Ramprasad, A., Krishnan, A., 2019. Flood prediction based on weather parameters using deep learning. Journal of Water and Climate Change 11(4), 1766-1783. https://doi.org/10.2166/wcc.2019.321.
[29]	Shafaei, M., Kisi, O., 2016. Lake level forecasting using wavelet-SVR, wavelet-ANFIS and wavelet-ARMA conjunction models. Water Resources Management 30, 79-97. https://doi.org/10.1007/s11269-015-1147-z.
[30]	Taghi Sattari, M., Yurekli, K., Pal, M., 2012. Performance evaluation of artificial neural network approaches in forecasting reservoir inflow. Applied Mathematical Modelling 36(6), 2649-2657. https://doi.org/10.1016/j.apm.2011.09.048.
[31]	Thaisiam, W., Saelo, W., Wongchaisuwat, P., 2022. Enhancing a multi-step discharge prediction with deep learning and a response time parameter. Water 14(18), 2898. https://doi.org/10.3390/w14182898.
[32]	Thaisiam, W., Yomwilai, K., Wongchaisuwat, P., 2024. Utilizing sequential modeling in collaborative method for flood forecasting. Journal of Hydrology 636, 131290. https://doi.org/10.1016/j.jhydrol.2024.131290.
[33]	Valipour, M., Banihabib, M.E., Behbahani, S.M.R., 2012. Parameters estimate of autoregressive moving average and autoregressive integrated moving average models and compare their ability for inflow forecasting. Journal of Mathematics and Statistics 8(3), 330-338. https://doi.org/10.3844/jmssp.2012.330.338.
[34]	Wang, W., Nie, X., Qiu, L., 2010. Support vector machine with particle swarm optimization for reservoir annual inflow forecasting. In: Proceedings of the 2010 International Conference on Artificial Intelligence and Computational Intelligence. IEEE, Sanya, pp. 184-188. https://doi.org/10.1109/AICI.2010.45.
[35]	Wani, O.A., Mahdi, S.S., Yeasin, M., Kumar, S.S., Gagnon, A.S., Danish, F., Al-Ansari, N., El-Hendawy, S., Mattar, M.A., 2024. Predicting rainfall using machine learning, deep learning, and time series models across an altitudinal gradient in the northwestern Himalayas. Scientific Reports 14(1), 27876. https://doi.org/10.1038/s41598-024-77687-x.
[36]	Yu, Q., Tolson, B.A., Shen, H., Han, M., Mai, J., Lin, J., 2024. Enhancing long short-term memory (LSTM)-based streamflow prediction with a spatially distributed approach. Hydrol. Earth Syst. Sci. 28(9), 2107-2122. https://doi.org/10.5194/hess-28-2107-2024.
[37]	Zhang, G.P., 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159-175. https://doi.org/10.1016/S0925-2312(01)00702-0.
[38]	Zhang, X., Wang, H., Peng, A., Wang, W., Li, B., Huang, X., 2020. Quantifying the uncertainties in data-driven models for reservoir inflow prediction. Water Resources Management 34(4), 1479-1493. https://doi.org/10.1007/s11269-020-02514-7.
[39]	Zhao, L., Li, Z., Qu, L., Zhang, J., Teng, B., 2023. A hybrid VMD-LSTM/GRU model to predict non-stationary and irregular waves on the east coast of China. Ocean Engineering 276, 114136. https://doi.org/10.1016/j.oceaneng.2023.114136.
[40]	Zhou, L., Long, G., Hu, C., Zhang, K., 2025. Reservoir water level prediction using combined CEEMDAN-FE and RUN-SVM-RBFNN machine learning algorithms. Water Science and Engineering 18(2), 177-186. https://doi.org/10.1016/j.wse.2025.01.002.

Relative Articles

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(2)

Get Citation

PDF

XML

Article Metrics

Article views (19) PDF downloads(0)

Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM

doi: 10.1016/j.wse.2025.11.001

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Multi-step reservoir inflow prediction using a rolling window strategy and decomposed LSTM

doi: 10.1016/j.wse.2025.11.001

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Export File

Citation

Format

Content