Big Data Analytics for Optimizing Sustainable Water Resource Management in Disease-Endemic Regions: A Narrative Review

Abstract

In cholera-, typhoid fever-, and schistosomiasis-endemic regions, unsafe and irregularly monitored water supplies remain a major driver of waterborne and water-related disease. As of 2024, an estimated 2.1 billion people worldwide still lacked access to safely managed drinking water (WHO/UNICEF Joint Monitoring Programme, 2025). Conventional water-quality surveillance, based on scheduled grab-sampling and laboratory analysis, is often too slow to support timely public health action. This narrative review synthesizes recent literature on the application of big data analytics — Internet of Things (IoT) sensor networks, satellite remote sensing, and machine learning — to water resource management in disease-endemic settings. The reviewed literature indicates that machine learning models — particularly ensemble methods such as random forest and XGBoost — have reported high accuracy for forecasting cholera outbreaks and predicting water-quality parameters, while low-cost IoT sensors and satellite-derived climate variables are increasingly used to fill monitoring gaps in resource-limited settings. Recurrent limitations include a predominance of geographically narrow studies, limited integration of real-time multi-sensor data with clinical surveillance, and persistent infrastructure, connectivity, and data-governance barriers in the lowest-resource settings that carry the greatest disease burden. We conclude that big data analytics holds considerable promise for shifting water-related disease management from reactive to anticipatory, but that this promise remains only partially realized and depends on sustained investment in local infrastructure and data governance.