Research
Hydrologic and Water Quality Modeling
We develop and apply physically based watershed models to simulate hydrologic processes, water quality dynamics, and environmental responses across agricultural and natural systems. By integrating field observations, geospatial data, remote sensing, and advanced modeling frameworks, we evaluate management scenarios, assess best management practices (BMPs), and support decision-making for sustainable water resource management and watershed resilience.
AI and Earth Observation for Environmental Risk Assessment
From Data to Actionable Insights
Our research develops artificial intelligence and geospatial modeling frameworks to identify, predict, and explain environmental risks across complex landscapes. By integrating Earth observation, environmental data, and deep learning architectures, we generate high-resolution maps of flood susceptibility, groundwater vulnerability, and other environmental hazards. These approaches not only provide accurate spatial predictions but also improve model transparency through explainable AI techniques that identify the environmental factors driving risk patterns. The resulting products support risk assessment, resource management, climate resilience planning, and science-based decision making across agricultural and natural systems.
Decision Support Systems and Digital Agriculture
Integrating Data, Models, and Stakeholder Input for Better Decisions
Our research develops stakeholder-oriented decision support systems that integrate field monitoring, remote sensing, artificial intelligence, and environmental modeling to support sustainable agricultural management. Current efforts focus on digital tools for pasture and biomass assessment, combining UAV imagery, field observations, and geospatial analytics to improve grazing management and resource-use efficiency. By linking environmental monitoring, watershed modeling, and management scenarios, we provide practical tools that help producers make data-driven decisions.