Yılmaz, VolkanKoyceğiz, CihangirBüyükyıldız, Meral2024-09-222024-09-2220242040-22442408-9354https://doi.org/10.2166/wcc.2024.420https://hdl.handle.net/20.500.13091/6248This study is based on the investigation of the performance of the band similarity (BS) method, which is quite new in the literature, in the prediction of flow and in determining the memory properties of the flow phenomenon. For this purpose, flow prediction models for the monthly flow data of the Sar & imath;z station, located in the Seyhan Basin in T & uuml;rkiye, were produced first with the particle swarm optimization (PSO) algorithm. Second, these models were used in the BS method to create the BSPSO approach. Then, flow prediction was made for the same data set with support vector regression (SVR). In the test period, the standalone PSO, BSPSO, and SVR models achieved the most successful Nash-Sutcliffe efficiency (NSE) values of 0.516, 0.691, and 0.659, respectively. As a result, it was seen that BS increased the success of PSO by approximately 35% and the BSPSO produced the best results (mean absolute error = 1.205 m(3)/s, root mean square error = 1.895 m(3)/s, NSE = 0.691, and R-2 = 0.734). With the BSPSO approach, it has been observed that there is a memory mechanism within the flow phenomenon. It was concluded that the 5-month variation played an important role in the memory and a stronger memory existed especially in water years when low flow values were observed.eninfo:eu-repo/semantics/openAccessband similaritymemoryparticle swarm optimizationstreamflowsupport vector regressionModelArticle10.2166/wcc.2024.4202-s2.0-85206940525