Survey on Water Disease Detection Using Deep Learning

Abstract

Waterborne infections are a major public health threat, especially in developing countries where access to clean water is poor. Conventional detection techniques, such as culture-based and chemical methods, are accurate but often time-consuming, expensive, and not ideal for online monitoring. Recent breakthroughs in artificial intelligence, particularly deep learning, open new opportunities for rapid and precise determination of water quality. This paper summarises different detection methods, rule-based, statistical, and deep learning, and highlights how models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Physics-Informed Neural Networks (PINNs) improve pathogen detection using image, sensor, and genomic information. The integration of AI with IoT-enabled devices and intelligent dashboards also facilitates real-time monitoring and predictive maintenance of domestic water supplies. Though challenges such as data scarcity and model interpretability persist, deep learning-based solutions are highly promising for revolutionising water safety management and mitigating the outbreak of waterborne diseases.