Antimicrobial resistance (AMR) is a global health crisis that increasingly involves the environment as a key contributor to resistance emergence and spread. This project focuses on wastewater and agricultural runoff—environments where antibiotics, heavy metals, and nutrients interact with microbes and mobile genetic elements to drive AMR. Current surveillance efforts mostly report gene presence, offering limited insight into how resistance arises or spreads. By combining high-resolution genomic sequencing, targeted chemical analysis, and machine learning, this research will identify the environmental and ecological drivers of AMR. The Windsor-Essex region, with its mix of urban and agricultural land use, offers an ideal setting to build this integrated risk prediction framework. The resulting system will support early warning and risk assessment tools to improve AMR monitoring across Canada.

This project will create a predictive, AI-driven framework that links environmental stressors with AMR emergence, advancing surveillance from simple detection to actionable risk modeling. Its outputs will help inform targeted mitigation strategies and contribute directly to One Health–aligned public health efforts in Canada.