Prediction of daily water level using new hybridized GS-GMDH and ANFIS-FCM models

Accurate prediction of water level (WL) is essential for the optimal management different resource projects. The development a reliable model WL remains challenging task in resources management. In this study, novel hybrid models, namely, Generalized Structure-Group Method Data Handling (GS-GMDH) and Adaptive Neuro-Fuzzy Inference System with Fuzzy C-Means (ANFIS-FCM) were proposed to predict daily at Telom Bertam stations located Cameron Highlands Malaysia. Different percentage ratio data division i.e. 50%–50% (scenario-1), 60%–40% (scenario-2), 70%–30% (scenario-3) adopted training testing these models. To show efficiency their results compared standalone models that include Gene Expression Programming (GEP) Group (GMDH). investigation revealed GS-GMDH ANFIS-FCM outperformed GEP GMDH both study sites. addition, indicate best performance was obtained scenario-3 (70%–30%). summary, highlight better suitability supremacy prediction, can, serve as robust predictive tools region.