AI & Digital Intelligence at the Core of Our Research
Where AI Meets the Field
AI-Powered Agricultural Water Management
Advanced AI-driven frameworks for optimizing irrigation scheduling, controlled drainage, and hydrologic system design to enhance water-use efficiency, productivity, and environmental sustainability.
AI-Based Crop Health, Stress Diagnostics, and Physiological Response Modeling
Intelligent sensing and modeling systems for real-time diagnosis of crop stress, physiological responses, and nutrient dynamics to enable proactive, adaptive crop management.
Intelligent Variable-Rate Input Optimization and Precision Application Technologies
Development of AI-enabled variable-rate irrigation, fertigation, and nutrient management systems for spatially targeted, resource-efficient input delivery.
Autonomous Decision Support Systems for Smart Agriculture
Creation of real-time, adaptive decision support platforms that integrate sensing, modeling, and AI for predictive farm management and operational optimization.
GeoAI-Based Geospatial Intelligence and Predictive Modeling for Sustainable Agroecosystems
Spatial AI frameworks for multi-scale geospatial modeling, risk assessment, and system-level optimization of agroecosystems under climate and environmental constraints.
Integrated Remote Sensing and AI Systems for Precision Agriculture
Fusion of satellite, UAV, and in-field sensing with AI and process-based models to deliver scalable, real-time monitoring, analytics, and decision intelligence for crop and water management.
AI-Driven Crop Phenotyping and Biophysical Parameter Estimation
Development of AI models using remote sensing, proximal sensing, and sensor fusion to accurately estimate key crop parameters such as crop height, LAI, biomass, canopy cover, phenology, and growth dynamics.
AI-Enabled Disease Detection and Early Warning Systems in Agricultural Production
Integration of remote sensing, proximal sensing, and deep learning for early detection, risk forecasting, and precision management of crop diseases across diverse cropping systems.