Daily reservoir inflow prediction using stacking ensemble of machine learning algorithms

Abstract

The present study aims to evaluate the potentiality of Bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Networks (CNNs), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and Random Forest (RF) for predicting daily inflows to the Sri Ram Sagar Project (SRSP), Telangana, India. Inputs to the model are rainfall, evaporation, time lag inflows, and climate indices. Seven combinations (S1–S7) of inputs were made. Fifteen and a half years of data were considered, out of which 11 years were used for training. Hyperparameter tuning is performed with the Tree-Structured Parzen Estimator. The performance of the algorithms is assessed using Kling–Gupta efficiency (KGE). Results indicate that Bi-LSTM with combination S7 performed better than others, as evident from KGE values of 0.92 and 0.87 during the training and testing, respectively. Furthermore, the Stacking Ensemble Mechanism (SEM) has also been employed to ascertain its efficacy over other chosen algorithms, resulting in KGE values of 0.94 and 0.89 during training and testing. It has also been able to simulate peak inflow events satisfactorily. Thus, SEM is a better alternative for reservoir inflow predictions. HIGHLIGHTS The Stacking Ensemble mechanism (SEM) has performed better than other ML algorithms (Bi-LSTM, CNN, RF, XGBoost, LGBM) in simulating the daily inflow to the Sri Ram Sagar Project, with KGE values of 0.94 and 0.89 in the training and testing.; The optimal combination of climate indices attributing to reservoir inflow was found using Shannon's entropy weighted measure.; SEM has performed satisfactorily in replicating the peak inflow events.;

Keywords

• hyperparameter tuning
• inflow prediction
• machine learning
• sri ram sagar project
• stacking