Application of soft computing approaches to predict gabion weir oxygen aeration efficiency

Abstract

ABSTRACT Aeration is a physical process through which air is brought into contact with water, and thereby both times of contact and contact area between water and air are enhanced. Gabion weirs are eco-friendly alternative structures having the least negative environmental impact. The paper examines the performance of the neuro-fuzzy, neural network, and Gaussian process regression (GPR) models in estimating the gabion weir oxygen aeration efficiency using the test data sets with regards to the evaluation indicators. The model utilizes non-dimensional inputs: Froude number, Reynolds number, the ratio of mean size to weir length, and porosity of gabion weir particles. The GPR with normalized poly kernel model having the highest value of correlation coefficient (CC), 0.9132, and value of root mean square error (RMSE), 0.392, outperforms all applied models and is followed by the neural network model with CC 0.8952 and RMSE 0.398. The neuro-fuzzy triangular shape with CC 0.8865 and RMSE 0.07576 is an equally performing model; nevertheless, all applied AI-based models are mostly performing well, but all mathematical models are exceptionally performing poorly except the nonlinear model with CC 0.8612 and RMSE 0.0029. To assess the relative relevance of input parameters on the output results, sensitivity and parametric analysis are also performed.