Authors:
M. Arunadevi Thirumalraj, V. Revathi, R. J. Anandhi, Prasanna Ranjith Christodoss
Addresses:
Department of Computer Science and Engineering, Karunya Institute of Technology and Science, Coimbatore, Tamil Nadu, India. Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Research and Development, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Information Science and Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Computing, Mathematics and Physics, Messiah University, One University Ave, Mechanicsburg, Pennsylvania, United States of America.
Abstract:
Improving the management of water resources globally, particularly in arid regions, requires evaluating the quality of the water. This study's objective is to evaluate and track groundwater quality using artificial intelligence (AI) techniques in conjunction with hydrochemical parameters. The scientific community has increasingly focused on groundwater quality monitoring over the past few decades. While the WQI is a useful instrument for evaluating groundwater quality, its classification accuracy isn't always optimal, particularly in large-scale databases. Consequently, this manuscript develops an ACBLSTM model for classifying groundwater quality. After applying Min-Max and Z-score normalisation methods to data collected from Indian and real-time water quality databases, the WQI calculation and data elimination are complete. The RLGWO method is employed to select the best features from the denoised data samples. Strong tolerance-based search direction adjustment and opposite-based learning reinforce this algorithm, which mimics the social hierarchy and hunting techniques of natural grey wolves. The suggested model has classified data from the Indian water quality database and real-time database with approximately 95% accuracy.
Keywords: Robust Learning Grey Wolf Optimisation (RLGWO); Water Quality Index (WQI); Convolutional Neural Network; Attention-based Convolutional Neural Network with Bidirectional Long-Short Term Memory (ACBLSTM); Groundwater Quality Monitoring.
Received: 07/11/2024, Revised: 14/02/2025, Accepted: 13/04/2025, Published: 09/09/2025
DOI: 10.64091/ATICS.2025.000198
AVE Trends in Intelligent Computing Systems, 2025 Vol. 2 No. 3 , Pages: 142-154