My work centers on structured inference—graph-based learning, probabilistic modeling, and scalable feature selection—for high-dimensional, heterogeneous biological and environmental systems.

I now work on integrating genomic, microbiome-scale, physiological, and environmental sensing data to build predictive and interpretable models for decision support.

Current research develops AI-enabled computational frameworks for surveillance and risk modeling in animal production systems. In specific: (i) pangenome graph-based machine learning for Salmonella pathogen detection and antimicrobial resistance prediction, (ii) spatiotemporal models for avian influenza risk forecasting, and (iii) representation learning approaches for metabolic and production-state modeling. Complementary efforts in UAV and hyperspectral sensing extend these methods to field-scale monitoring.