Abstract: Water quality prediction is essential for sustainable environmental management and public health. Traditional analytical methods are often laborious and inefficient. This research presents an enhanced deep learning framework (EHDL-WQM) for accurate Water Quality Prediction and Monitoring. The framework integrates Convolutional Neural Networks (CNN) for spatial feature extraction and Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal pattern learning, enhanced by an Attention Mechanism to emphasize significant parameters. The proposed architecture effectively processes multivariate sensor data to predict key indicators, including pH, dissolved oxygen, turbidity, and conductivity. Experimental evaluation demonstrates that EHDL-WQM achieves superior prediction accuracy and faster convergence compared to traditional and baseline deep learning models. The framework provides a scalable, intelligent solution for real-time monitoring and proactive water quality management.

Keywords: Water quality, Machine learning models, Deep learning, Water quality index, Water quality classification

Downloads: | DOI: 10.17148/IARJSET.2025.1211052