Hybridization of artificial intelligence models with nature inspired optimization algorithms for lake water level prediction and uncertainty analysis

In the present study, an improved adaptive neuro fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models are hybridized with a sunflower optimization (SO) algorithm introduced for lake water level simulation. The Urmia Lake is predicted assessed using potential of proposed advanced artificial intelligence (AI) models. implemented to find optimal tuning parameters. results indicated that ANFIS-SO model combination three lags rainfall temperature as input attributes attained best predictability performance. minimal values root mean square error were RMSE = 1.89 m 1.92 training testing modeling phases, respectively. worst prediction capacity was long lead (i.e., six months lag times). uncertainty analysis showed had less based on percentage more responses in confidence band lower bandwidth. Also, different scenarios harvesting investigated consideration environmental restrictions fair allocation stakeholders. Further, studying displayed 30% scenario improves lake’s level.