Knowledge-guided machine learning & Physics-informed machine learning — integrating mechanistic/process knowledge with AI (ECAI Lab)
Multimodal & multi-source data fusion — integrating sensor, imagery, weather, management, soil, crop, and livestock data (Digital Agriculture Lab)
Geospatial machine learning & big-data analytics
Transfer learning & domain adaptation — transferring models across laboratories, sensors, farms, regions, and production systems (Digital Agriculture Lab)
Machine learning for high-dimensional data — spectroscopy, imagery, and sensor streams
AI-ready benchmark datasets & data harmonization (UAV3DCrop)
AI-accelerated and multi-objective optimization for agricultural and environmental management
Interpretable, generalizable & trustworthy AI for agricultural applications
Digital livestock sensing & animal phenotyping — cameras, wearable sensors, IoT, spectroscopy, and multimodal systems for animal production, health, behavior, and welfare
Computer vision for livestock monitoring
Proximal soil sensing — soil water, carbon, nutrients, physical properties, and soil processes
Soil spectroscopy & soil health sensing — MIR/Vis-NIR spectroscopy, digital soil survey, and soil-process assessment
Ground-penetrating radar & microwave sensing for subsurface characterization
UAV and proximal crop sensing — crop growth, stress, phenotyping, and management response (Digital Agriculture Lab)
Multi-sensor remote sensing — hyperspectral, multispectral, RGB, LiDAR, and satellite observations (Digital Agriculture Lab)
Remote sensing of soil-water and hydrologic processes
Remote sensing of ecosystem carbon, water & energy exchange (ALIVE)
Cross-scale sensing and sensor-data integration from field sensors to UAVs and satellites
Soil hydrologic & biogeochemical process modeling
Agroecosystem & Earth Systems Modeling — carbon (Liu et al., 2024), water (Yang et al., 2026), nutrient (Yang et al., 2026), greenhouse gases (Liu et al., 2022; Oh et al., 2026; Zhu et al., 2026), energy and land-atmosphere exchange (Ranjbar et al., 2026)
Crop growth, stress & yield prediction (Crop Yield Prediction Tool)
Livestock production, health & welfare prediction
Soil moisture & water-demand forecasting
Climate- and extreme-weather impacts on agricultural systems
Nutrient loss & water-quality prediction under extreme events
Hybrid AI–process modeling & data assimilation
Deep learning for spatiotemporal agricultural prediction
AI-enabled nutrient management — N recommendations, nutrient-use efficiency, manure management, and site-specific management
Sensor-guided variable-rate nutrient management
Precision irrigation & variable-rate irrigation decision support
Crop input optimization — water, fertilizer, and other inputs based on sensing and prediction
Digital livestock decision support for animal production, health, welfare, and farm management
AI-assisted management optimization using process models and predictive AI
Digital agriculture platforms & integrated farm decision support (Crop Yield Prediction Tool)
Robotics-enabled sensing and targeted intervention
Adaptive and closed-loop management systems linking sensing → prediction → decision → action → feedback
Technology implementation & human factors in digital agriculture
Adoption of precision agriculture and digital decision tools
Adoption of nutrient-management and conservation practices
Farm profitability, resource-use efficiency & environmental performance
Accessible technologies for small and mid-sized farms
Digital agriculture for diversified, specialty-crop & organic production systems
Community co-design and producer-centered technology development
LLM-enabled agricultural decision support and human–AI interaction (Cheng et al., 2026)
Scaling technologies from research settings to commercial farms
Producer education & Extension for nutrient management
Producer education for irrigation, precision agriculture & sustainable vegetable production
Digital agriculture education across livestock, crops & environment
AI and data-science training for agricultural students and professionals (PyKGML)
Field-based sensing and digital agriculture training
Open-source AI tools, benchmark datasets & reproducible workflows (PyKGML)
Extension demonstrations & on-farm technology evaluation
Workforce development for AI-enabled agriculture
Community-engaged learning and co-design with farmers, consultants, Extension educators, and agricultural organizations