Reservoir Inflow Forecasting at Tarbela Dam Using Machine Learning Algorithms
Keywords:
Reservoir inflow, Machine learning, Upper Indus Basin (UIB), XGBoost, Climate changeAbstract
This study focuses on predicting reservoir inflows at the Tarbela Dam using various machine learning algorithms under historical and projected climate scenarios. Daily hydrometeorological data from 14 stations across the upper Indus basin were used as inputs, including precipitation, maximum and minimum temperature, relative humidity, and solar radiation. Historical inflow data from 1981–2015 was used for training, and 2015-2020 was used for testing, while 2021 to 2024 was used for an independent validation set. Among the ML models, Catboost achieved the highest accuracy (R² = 0.92, RMSE = 291.42 m³/s on training; R² = 0.87, RMSE = 811.00 m³/s on testing), while XGBoost also performed well (R² = 0.92, RMSE = 317.77 m³/s on training; R² = 0.88, RMSE = 817.64 m³/s on testing). Future inflows were projected using the trained models under CMIP6 scenarios SSP2-4.5 and SSP5-8.5 for the period 2025–2100 in future simulations (2025–2100), Catboost remained the top performer under both SSP2-4.5 and SSP5-8.5 scenarios, achieving R² values above 0.90 and RMSE values below 750 m³/s.
References
Bernardes, J., Jr., Santos, M., Abreu, T., Prado, L., Jr., Miranda, D., Julio, R., Viana, P., Fonseca, M., Bortoni, E., & Bastos, G. S. (2022). Hydropower operation optimization using machine learning: A systematic review. AI, 3(1), 78–99. https://doi.org/10.3390/ai3010006
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785
Dampage, S., Rathnayake, U., & Rajapaksha, R. (2020). Application of artificial neural networks in rainfall–runoff modeling: A case study in the Nilwala River Basin, Sri Lanka. Journal of Water and Climate Change, 11(3), 743–757. https://doi.org/10.2166/wcc.2019.091
Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139. https://doi.org/10.1006/jcss.1997.1504
Gupta, A., Khare, D. & Shukla, R. 2022. Comparative analysis of machine learning models for streamflow prediction: Case study using XGBoost, Random Forest, and Support Vector Regression. Journal of Hydrology, 606, 127503. https://doi.org/10.1016/j.jhydrol.2022.127503
Haykin, S. S. (2009). Neural networks and learning machines (3rd ed.). Pearson.
Jan, S. (2025). Reservoir inflow prediction using machine learning techniques. Jurnal Civil Engineering Study, 5(2), 53–62. https://doi.org/10.34001/ces.v5i02.1225
Jan, S., Khan, U., Khalil, A., Khan, A. A., Jan, H. A., & Ullah, I. (2024). Use of machine learning techniques in predicting inflow in Tarbela reservoir of Upper Indus Basin. Journal of Agrometeorology, 26(4), 501–504. https://doi.org/10.54386/jam.v26i4.2676
Khan, A., & Koch, M. (2020). River flow forecasting with Random Forest and Support Vector Regression models in the Upper Indus Basin. Water, 12(4), 936. https://doi.org/10.3390/w12040936
Khan, A. J. (2024). Bias corrected and downscaled climate projections over Upper Indus Basin (based on CORDEX-RCM's) [Data set]. HydroShare. https://doi.org/10.4211/hs.bd2b1ec6ac94441db3acdfddb97c1bfa
Khan, M. M., Sarwar, M. K., Zafar, M. A., Rashid, M., Tariq, M. A. U. R., Haider, S., Okasha, A. M., Dewidar, A. Z., Mattar, M. A., & Salem, A. (2025). Comparative analysis of inflow forecasting using machine learning and statistical techniques: Case study of Mangla reservoir and Marala Headworks. Frontiers in Environmental Science, 13, 1590346. https://doi.org/10.3389/fenvs.2025.1590346
Maier, H. R., Jain, A., Dandy, G. C., & Sudheer, K. P. (2010). Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions. Environmental Modelling & Software, 25(8), 891–909. https://doi.org/10.1016/j.envsoft.2010.02.003
Mosaffa, H., Sadeghi, M., Mallakpour, I., Naghdyzadegan Jahromi, M., & Pourghasemi, H. R. (2022). Application of machine learning algorithms in hydrology. In Computers in Earth and Environmental Sciences (pp. 585–591). Elsevier. https://doi.org/10.1016/B978-0-323-89861-4.00027-0
Mosavi, A., Ozturk, P., & Chau, K.-W. (2018). Flood prediction using machine learning models: Literature review. Water, 10(11), 1536. https://doi.org/10.3390/w10111536
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. In Advances in Neural Information Processing Systems 31 (pp. 6638–6648).
Sireesha, M., Mahammood, V., & Rao, K. N. (2023). Prediction of soil salinity in the Upputeru river estuary catchment, India, using machine learning techniques. Environmental Monitoring and Assessment, 195, 1006. https://doi.org/10.1007/s10661-023-11613-y
Vapnik, V.N. 1995. The Nature of Statistical Learning Theory. Springer. https://doi.org/10.1007/978-1-4757-2440-0
Zarei, M., Bozorg-Haddad, O., Baghban, S., Delpasand, M., Goharian, E., & Loáiciga, H. A. (2021). Machine-learning algorithms for forecast-informed reservoir operation (FIRO) to reduce flood damages. Scientific Reports, 11, 24295. https://doi.org/10.1038/s41598-021-03699-6
Munir, M. M., Shakir, A. S., Rehman, H.-U., Khan, N. M., Rashid, M. U., Tariq, M. A. U. R., & Sarwar, M. K. (2022). Simulation-optimization of Tarbela Reservoir operation to enhance multiple benefits and to achieve Sustainable Development Goals. Water, 14(16), 2512. https://doi.org/10.3390/w14162512
Dibike, Y. B., Velickov, S., Solomatine, D., & Abbott, M. B. (2001). Model induction with support vector machines: Introduction and applications. Journal of Computing in Civil Engineering, 15(3), 208–216. https://doi.org/10.1061/(ASCE)0887-3801(2001)15:3(208)
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
Rauf, A.U., Rafi, M.S., Ali, I., & Muhammad, U.W. (2016). Temperature trend detection in Upper Indus Basin by using Mann-Kendall test. Advances in Science, Technology and Engineering Systems Journal, 1(4), 5–13. https://doi.org/10.25046/aj010402
Wang, L., Wu, J., Zhang, W., Wang, L., & Cui, W. (2021). Efficient Seismic Stability Analysis of Embankment Slopes Subjected to Water Level Changes Using Gradient Boosting Algorithms. Frontiers in Earth Science, 9, 807317. https://doi.org/10.3389/feart.2021.807317.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
