Advancing Reservoir Water Level Predictions: Evaluating Conventional, Ensemble and Integrated Swarm Machine Learning Approaches

Accurate estimation of reservoir water level fluctuation (WLF) is crucial for effective dam operation and environmental management. In this study, seven machine learning (ML) models, including conventional, integrated swarm, and ensemble learning methods, were employed to estimate daily reservoir WLF. The models comprise multi-linear regression (MLR), shallow neural network (SNN), deep neural network (DNN), support vector regression (SVR) integrated with homonuclear molecules optimization (HMO) and particle swarm optimization (PSO) meta-heuristic algorithms, classification and regression tree (CART), and random forest (RF). These models were trained and evaluated using in situ data from three embankment dams in Algeria: the Kramis dam, the Bougous dam, and the Fontaine Gazelles dam. Performance evaluation was conducted using statistical indices, scatter plots, violin plots, and Taylor diagrams. The results revealed superior prediction accuracy for the Fontaine Gazelles dam compared to Kramis and Bougous dams. Particularly, the RF, DNN, and SVR-HMO models exhibited consistent and excellent predictive performance for WLF at the Fontaine Gazelles dam with RMSE values of 0.502 m, 0.536 m, and 0.57 m, respectively. The RF model demonstrates remarkable accuracy across all three case studies. This can be attributed to the ensemble structure of RF, as evidenced by the results. This study underscores the significance of considering factors such as seepage flow intensity in understanding WLF variability. Furthermore, the proposed ML models offer promising capabilities in WLF prediction, highlighting their potential utility in enhancing reservoir management practices and addressing the limitations of traditional regression models. Keys words. Embankment dam, Water level fluctuations, Seepage, Artificial neural network, meta-heuristic algorithm.