Search

This study looked into the variability of seasonal rainfall in the semi-arid Konya Closed Basin (KCB), a water-limited region with high exploitation demand for water resources due to agricultural activities. In the study, seasonal precipitation data of eleven stations in the basin for the period 1971–2020 were used and analyzed with four trend methods (Şen-ITA, CWTSD, IPTA, and TPSC). Visual and statistical findings from the analyses showed generally increasing trends in winter and summer precipitation and decreasing trends in spring precipitation in the basin. In autumn precipitation, according to Şen-ITA, there is an increasing trend in seven stations and a decreasing trend in four stations, while according to CWTSD, there is an increasing trend in six stations and a decreasing trend in five stations. Based on the arithmetic mean IPTA graphs, Winter-Spring transitions in all stations occur from a rising trend region to a falling trend region, but Spring-Summer transitions take the reverse direction. In the standard deviation IPTA graphs, similar transitions in the trend regions are predominant. To the mean and standard deviation TPSC graphs, most of the stations generally have similar behavior. Spring-Summer transition arrows are dominant in Zone III, while Summer-Autumn and Autumn-Winter transitions are dominant in Zone I. Although Winter-Spring transitions are variable, they are more intense in Zone I and III. CWTSD and Şen-ITA methods are also consistent with the results obtained from IPTA graphs, both visually and numerically. • The seasonal variability of rainfall in the Konya Closed Basin was investigated by innovative graphical trend methods. • Strong irregularity in seasonal rainfall was detected. • An increase in winter and summer and a decrease in spring precipitation were generally observed throughout the basin. [ABSTRACT FROM AUTHOR]

This study examines the ability of different methods such as machine learning, ensemble models, and metaheuristic 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 Körkün in the temperate climate class, model performances were lower at Küçük Muhsine in the arid climate class. While the most successful modeling for Küçük Muhsine (NSE = 0.696) and Karasu stations (NSE = 0.811) was obtained with the BSPSO method, the SVM method produced the best results for Körkün 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 Küçük Muhsine, 0.49%–3.72% at Karasu, and 1.24%–7.24% at Körkün. The competitive results achieved by the BSPSO approach compared to ANN and SVM in flow prediction constitute the innovative aspect of this study. • ANN, SVM, AdaBoost, PSO, BSPSO methods were used to estimate the streamflow. • Stations in climatic zones continental, temperate and arid were studied. • The impact of seasonality and trend components on estimation success was explored. • Input structures that include seasonality and trend components were more successful. • The hybrid BSPSO method achieved competitive and successful results. [ABSTRACT FROM AUTHOR]