Collaborative Research: FEC: AI-Enabled Environmental Surveillance of Microbial and Chemical Threats to Food Production Systems

Microbial pathogens and chemical pollutants pose significant threats to food production systems. Current monitoring approaches often detect such threats only after disease outbreaks occur or contaminants reach critical levels. There is an urgent societal need to develop and validate AI-enabled environmental surveillance technologies that provide early warning of biological and chemical hazards in food production systems. This Focused EPSCoR Collaborations (FEC) project will leverage and enhance the research capacities of the University of Hawaiʻi at Mānoa and the University of Nebraska–Lincoln to advance use-inspired research aimed at safeguarding food production systems in the respective jurisdictions. The project will strengthen research capacity and infrastructure in both EPSCoR jurisdictions while establishing a sustainable interdisciplinary partnership focused on food system security. The goal of this FEC project is to integrate artificial intelligence (AI) with environmental sampling, metagenomics, and high-resolution mass spectrometry (HRMS) to detect and quantify microbial pathogens and chemical contaminants in aquaculture, livestock, and related agricultural environments. The project advances use-inspired research by addressing long-standing challenges in environmental surveillance through the convergence of water engineering, environmental science, and AI. Novel AI models will be developed to improve signal detection, facilitate interpretation of complex metagenomic and non-targeted HRMS datasets, and forecast risks associated with pathogen emergence and contaminant accumulation. System integration and field testing will demonstrate the effectiveness of these technologies in protecting animal health, enhancing food safety, and improving the resilience of food production systems. This goal will be achieved through five thematic areas. Theme 1 will evaluate environmental surveillance methodologies for the collection and detection of microbial pathogens and chemical pollutants in aquaculture and beef cattle production systems. Theme 2 will develop novel AI models to enhance signal detection and forecast risk of diseases from microbial pathogens and chemical contaminants using environmental surveillance data. Theme 3 will integrate the resulting technologies and conduct field testing of AI-enabled environmental surveillance systems to protect aquaculture and livestock health and improve food safety. Theme 4 will strengthen the long-term sustainability and broader impacts of the collaboration through education and workforce development activities. Theme 5 will assess project progress and impacts relative to the overall project goal. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.