Grey Wolf Optimizer with Deep Learning Modified Neural Network for Groundwater Quality Index Classification

Groundwater quantity and quality are the necessities for sustaining human life and society. The Water Quality Index (WQI) is the generally utilized parameter to define water quality globally. But, the typical method for computation of WQI was frequently difficult and time consuming while it needs control massive datasets and contains the computation of many sub-indices. Accordingly, it is vital to measure the quality of groundwater for drinking and agricultural activities, both its current use and its potential to develop a reliable water supply for individuals. Therefore, this manuscript offers the design of Grey Wolf Optimizer with Deep Learning Modified Neural Network (GWO-DLMNN) approach for Groundwater Quality Index Classification in Thiruvallur district, India. The major aim of the GWO-DLMNN technique lies in the proper classification of WQI. In the presented GWO-DLMNN model, three major processes are involved. Firstly, the GWO-DLMNN model technique performs data normalization. Secondly, the DLMNN model carries out the WQI classification process. Thirdly, the GWO algorithm is exploited for adjusting the hyperparameter values of the DLMNN model. To determine the enhanced performance of the GWO-DLMNN method, extensive simulations were involved. The experimental results stated the better performance of the GWO-DLMNN model.