Performance of Data-Driven Models Based on Seasonal-Trend Decomposition for Streamflow Forecasting in Different Climate Regions of Türkiye

Abstract

This study examines the ability of different methods such as machine learning, ensemble models, and meta- heuristic algorithms to predict streamflow. For this purpose, five different methods were used: Artificial Neural Networks (ANN), Support Vector Machines (SVM), Adaptive Boosting, Particle Swarm Optimization (PSO), and BSPSO hybridized with Band Similarity (BS), a relatively new method. Additionally, the impact of seasonality and trend components obtained through Seasonal-Trend decomposition using LOESS (locally weighted regression and scatterplot smoothing) (STL) data decomposition technique on prediction success was investigated. Models were developed in three basins with three different climate characteristics: continental, temperate, and arid. The results showed higher prediction success in input structures including seasonality and trend components. While higher prediction successes were achieved at Karasu in the continental climate class and Kork & uuml;n in the temperate climate class, model performances were lower at K & uuml;& ccedil;& uuml;k Muhsine in the arid climate class. While the most successful modeling for K & uuml;& ccedil;& uuml;k Muhsine (NSE = 0.696) and Karasu stations (NSE = 0.811) was obtained with the BSPSO method, the SVM method produced the best results for Kork & uuml;n station (NSE = 0.818). Moreover, BSPSO models outperformed the prediction successes obtained by using PSO alone for each scenario at all three stations. The percentages of the BSPSO method improving the prediction success according to the NSE metric ranged from 3.53% to 17.40% at K & uuml;& ccedil;& uuml;k Muhsine, 0.49%-3.72% at Karasu, and 1.24%-7.24% at Kork & uuml;n. The competitive results achieved by the BSPSO approach compared to ANN and SVM in flow prediction constitute the innovative aspect of this study.