2026-10-19T01:12:05Zhttps://ebyu-rdlopen.rawdatalibrary.net/oai/request

oai:ebyu-rdlopen.rawdatalibrary.net:ebyu/110552026-10-18T20:33:45Zopenairedrivercom_ebyu_10000col_ebyu_10001

Model performance evaluation with Siamese neural network in hydrologic modellingDalkilic, Huseyin YildirimBaran, AhmetYilmaz, BarisYildiz, Eyyupdeep learning methodsglobal similarity ratehydrological modellingmodel performance evaluationSiamese neural networkSNNsustainable water managementGlobal warming impacts water resources, altering the hydrological cycle, availability, and quality, posing challenges for sustainable use. This study applied hydrological modelling to evaluate future scenarios in the Fırat Basin using flow data. Gated recurrent unit (GRU) and long short-term memory (LSTM) models were assessed using conventional performance indicators. A Siamese neural network (SNN) with graphical similarity rate (GSR) calculation was introduced to simplify evaluation and reduce parameter complexity. Results showed high model performance, with SNN providing statistically equivalent outcomes to traditional metrics, offering a novel approach to hydrological modelling challenges. Copyright © 2025 Inderscience Enterprises Ltd.Inderscience Publishers2025Articlehttps://rdlopen.rawdatalibrary.net/r/ebyu/11055https://doi.org/10.1504/ijgw.2025.1491491758-2083enInternational Journal of Global Warminginfo:eu-repo/semantics/openAccessinfo:eu-repo/semantics/articlehttps://ebyu-rdlopen.rawdatalibrary.net/tr/items/ebyu/11055