A novel hybridized neuro-fuzzy model with an optimal input combination for dissolved oxygen estimation

Dissolved oxygen (DO) is one of the main prerequisites to protect amphibian biological systems and support powerful administration choices. This research investigated applicability Shannon’s entropy theory correlation in obtaining combination optimum inputs, then abstracted input variables were used develop three novel intelligent hybrid models, namely, NF-GWO (neuro-fuzzy with grey wolf optimizer), NF-SC (subtractive clustering), NF-FCM (fuzzy c-mean), for estimation DO concentration. Seven different combinations water quality variables, including temperature (TE), specific conductivity (SC), turbidity (Tu), pH, prediction models at two stations California. The performance proposed was assessed using statistical metrics visual interpretation. results revealed better all than other where its improved by 24.2–66.2% 14.9–31.2% terms CC (correlation coefficient) WI (Willmott index) compared standalone NF combinations. Additionally, MAE (mean absolute error) RMSE (root mean model reduced 9.9–46.0% 8.9–47.5%, respectively. Therefore, as can be considered optimal predicting concentration stations. In contrast, performed worst most violin plot NF-GWO-predicted found similar observed data. dissimilarity high model. this study promotes intelligence predict accurately resolve complex hydro-environmental problems.