Our Research

Our research program is grounded in the development and application of advanced tools for precision agriculture practices, integrating sensing technologies, automation, analytics, and decision-making frameworks to enhance crop management, productivity, and environmental stewardship.

Research Areas

Remote Sensing

Remote Sensing

Use of diverse sensing platforms—including drones (UAVs), satellites, and handheld sensors—for crop monitoring and spatial analysis. Applications include multispectral mapping, vegetation indices, stress detection, and field variability assessment.

Artificial Intelligence

Artificial Intelligence

Application of artificial intelligence and machine learning techniques for data analysis, pattern recognition, and the development of predictive models supporting yield estimation, crop quality assessment, and management decisions.

Agricultural Robotics

Robotics

Development and implementation of robotic systems for agricultural applications, including automated data collection, crop monitoring, and site-specific crop management operations.

Decision Support Systems

Decision Support Systems

Design and implementation of intuitive, user-friendly decision support systems (DSSs) that enable stakeholders to visualize complex datasets and make informed, timely, and data-driven management decisions.

Ongoing Projects

Integrating Multi-Sensor Systems and AI for Monitoring Peanut Variety Performance

This project introduces a range of sensors and platforms for intensive monitoring of peanut crops. The approach focuses on modeling plant growth patterns and yield potential using sensor-derived data combined with AI-based analysis.

Smart Monitoring of Peanut Harvest: Data-Driven Insights into Yield Loss and Quality

This project integrates precision agriculture strategies for data collection and decision-making related to peanut harvest quality. A range of sensors and data collection approaches are used to better understand field parameters that impact yield losses during harvest operations.

3D Modeling of Cotton Plant Structure to Support Smarter Variable Rate Applications

This project utilizes drone-based data to generate 3D digital maps of plant attributes such as plant height and canopy volume under field conditions. These parameters are used to support variable rate application (VRA) decisions.

Unsupervised Learning and High-Resolution Satellite Imagery for Soybean Yield Monitoring

This project integrates satellite imagery with unsupervised learning techniques to monitor soybean yield variability at large field scales. A wide range of image-based information is used, including spectral and texture data.