Artificial intelligence and data science in environment health and surveillance: Early detection and risk-reduction strategies

EHS (EHS) is undergoing rapid transformation through the integration of artificial intelligence (AI) and data science. In Africa, particularly Nigeria, rapid urbanization, industrialization, climate variability, and population growth have intensified environmental health threats while exposing limitations in traditional surveillance systems. This review synthesizes current evidence on the application of AI-driven methods in EHS, with emphasis on early detection and risk-reduction strategies. Drawing from studies indexed in Scopus, PubMed, Web of Science, and IEEE Xplore, the review examines methodological approaches including machine learning, deep learning, geospatial artificial intelligence (GeoAI), natural language processing, time-series forecasting, and multimodal data integration. Particular attention is given to the applicability of remote sensing, wearable technologies, health records, and administrative datasets in supporting predictive and preventive environmental health systems. The review further evaluates applications across air quality monitoring, water and soil contamination, vector-borne disease surveillance, and climate-driven hazards. Findings indicate that AI-enabled systems improve anomaly detection, exposure prediction, spatial risk mapping, and decision-support capacity. However, persistent challenges related to data quality, interoperability, explainability, ethical governance, infrastructural inequities, and contextual generalizability constrain implementation in low-resource settings. The article argues that the future of EHS lies not only in technological sophistication but also in transparent methodologies, equitable data infrastructures, and integration of AI outputs into operational public-health workflows. When responsibly implemented, AI and data science can shift EHS from reactive monitoring toward anticipatory prevention and resilient risk management.