Prediction of lake water-level fluctuations using adaptive neuro-fuzzy inference system hybridized with metaheuristic optimization algorithms

Abstract Lakes help increase the sustainability of natural environment and decrease food chain risk, agriculture, ecosystem services, leisure recreational activities locally globally. Reliable simulation monthly lake water levels is still an ongoing demand for multiple environmental hydro-informatics engineering applications. The current research aims to utilize newly developed hybrid data-intelligence models based on ensemble adaptive neuro-fuzzy inference system (ANFIS) coupled with metaheuristics algorithms water-level by considering effect seasonality Titicaca Lake fluctuations. classical ANFIS model was trained using three nature-inspired optimization algorithms, including genetic algorithm (ANFIS-GA), particle swarm optimizer (ANFIS-PSO), whale (ANFIS-WOA). For determining best set input variables, evolutionary approach several lag months has been utilized prior process models. proposed were investigated accurately simulating at Lake. ANFIS-WOA exhibited prediction performance pattern measurement in this study. scenario (the inputs $${X}_{t-1},\; {X}_{t-2}, \;{X}_{t-3}, \;{X}_{t-4}, \; {X}_{t-12}$$ X t - 1 , 2 3 4 12 ) attained root mean square error (RMSE $$\approx$$ ? 0.08 m), absolute (MAE 0.06 coefficient determination ( R 2 0.96). Also, results showed that long-term seasonal memory suitable so dynamic 1-year time series data estimating level