The global rise of microbial infections that are difficult or impossible to treat poses a growing threat, causing increased animal suffering and the loss of human life and livelihoods. Antimicrobial resistance (AMR) has spread between species and across borders highlighting the interconnectedness of human and animal ecosystems and driving a multidisciplinary One Health research effort to curb its spread. Aquatic environments play a key role in the circulation and persistence of AMR. However, breaking this chain of transmission requires a detailed, time and location-specific understanding of the underlying drivers and pathways. The lack of routine, nationwide environmental AMR monitoring represents a major barrier to achieving this. EU legislation ensures that geospatial environmental datasets, including livestock distributions, bathing water quality, and wastewater records, are publicly available across Member States. This creates an opportunity to reinterpret routine bathing water microbiological monitoring data in the context of surrounding geospatial and temporal anthropogenic pressures at individual monitoring sites. Here, we apply GIS and machine-learning approaches to historical bathing water quality and environmental datasets to model AMR risk in Irish coastal waters. By combining pathogen source attribution with source-specific AMR risk weighting, we generate a national-scale map of potential AMR risk to support the strategic targeting of surveillance and mitigation efforts where they are likely to achieve the greatest impact. More broadly, this framework provides a transferable and cost-effective approach to AMR surveillance planning and evidence-based policymaking aimed at limiting the spread of AMR.