Puri, DikshaSihag, ParveenSadeghifar, TayebDursun, Omer FarukThakur, Mohindra Singh2024-08-042024-08-0420232520-81602520-8179https://doi.org/10.1007/s41939-023-00153-0https://hdl.handle.net/11616/101277This study compares the efficacy of soft computing techniques namely, Random Forest, M5P tree and Adaptive Neuro Fuzzy Inference System to predict the aeration efficiency through a combined dataset of Parshall and modified Venturi Flumes. For the development and validation of the model, in all, 99 experimental observations were used. The model's development and validation were done by utilizing six independent variables, discharge, throat width, throat length, sill height, oxygen deficit ratio and the exponent factor as inputs whereas aeration efficiency was considered as a target. The performance of developed models is measured using six different goodness of fit parameters which are correlation coefficient, coefficient of determination, mean absolute error, mean squared error, root mean square error and mean absolute percentage error. Outcomes of the present analysis revealed that all developed models are capable of handling prediction due to their higher correlation coefficient (CC) values. However, Random Forest model outperformed other soft computing-based models for estimating the aeration efficiency with a correlation coefficient of 0.9981, mean absolute error value of 0.0023, and a mean squared error being 0.00 in the testing stage. Further, results obtained from sensitivity investigation indicate that the oxygen deficit ratio which contains the elements of saturated oxygen concentration, upstream oxygen concentration, and downstream oxygen concentration is the most effective input variable for estimating the aeration efficiency using this data set. Since oxygen deficit is highly sensitive to aeration efficiency, the values of saturated oxygen concentration, upstream and downstream oxygen concentration require due consideration.eninfo:eu-repo/semantics/closedAccessParshall flumeModified Venturi flumesAdaptive neuro fuzzy inference systemM5PRandom forestArticle6340141310.1007/s41939-023-00153-02-s2.0-85151920706Q3WOS:000967294800002Q2