Integrating GIS and Machine Learning to Prioritise Environmental Monitoring of Water Quality and Antimicrobial Resistance
Year: 2026
Type: preprint
Abstract: Emerging pathogens and antimicrobial resistance (AMR) pose growing One Health challenges, yet limited environmental surveillance hampers identification of priority monitoring locations. Here, we integrate geographic information systems (GIS), machine learning, publicly available bathing water monitoring data (2020--2025) and other environmental datasets to prioritise environmental AMR monitoring in Ireland. Self-organising maps classified sites by faecal contamination, while GIS-based source attribution and source-specific AMR weightings were combined to estimate the spatial distribution of relative environmental AMR risk across coastal waters. Four priority areas were identified. Coastal analysis highlighted wastewater discharges as a major environmental pressure, with aquaculture and recreation representing potential exposure pathways. Inland classification identified two sites with the highest faecal contamination nationally. Catchment analysis identified intensive poultry production as a prominent pressure at one site and multiple potential pressures at the other. This scalable framework demonstrates how existing environmental datasets can inform monitoring priorities, resource allocation and evidence-informed environmental policy.
Source: Research Square
Institution: Ollscoil na Gaillimhe – University of Galway
Language: English
Subfield: Pollution
Field: Environmental Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225908910
