ECE Research Seminar – September 19, 12:00 – 1:00 pm
September 15, 2025
Please join us for our September 2025 ECE Research Seminar
September 19, 2025, Friday, 12:00 – 1:00 pm, Simrall 104
https://msstate.webex.com/msstate/j.php?MTID=mf61adba5612d62a96afc328c8af0613d
UAS Remote Sensing for Soil Moisture and Yield Estimation
Using Multi-Sensor Receiver Systems and ML in Corn and Cotton Fields
Mohammad Abdus Shahid Rafi | mr2153@msstate.edu
Abstract: Accurate soil moisture (SM) measurement and crop yield estimation are critical components of modern precision agriculture (PA) management. Efficiently observing SM at high resolution can enhance irrigation planning and management, leading to the conservation of environmental resources. Yield predictions provide insights into expected production, optimizing resource allocation, management strategies, and profitability. Unmanned Aircraft Systems (UAS) based multi-sensor receiver systems offer promising solutions in obtaining high-resolution SM measurements and timely yield estimation over corn and cotton. This study has developed a UAS-based passive GNSS-R (Global Navigation Satellite Systems Reflectometry) receiver system for SM retrievals at the sub-field scale to identify relevant features and normalization techniques. From the 3-year field campaign over a 2.31-hectare field, incorporating GNSS-R, multispectral imaging, LiDAR (Light Detection and Ranging), and in-situ SM measurements, the impact of receiver antenna characteristics, surface factors, and GNSS constellations on GNSS-R measurements is investigated. The results highlighted both the potential and the challenges of using a GNSS-R receiver system from a UAS platform for accurate and reliable high-resolution SM measurement. Next, A multi-sensory dataset (34 features over 22 weeks) was collected using multispectral cameras and LiDAR sensors mounted on UAS, along with soil moisture and temperature data from volumetric probes and environmental data from a nearby weather station. This subsequent study outlines the methodology for feature selection and investigates the application of machine learning (ML) techniques for predicting crop yields. The proposed approach, validated through year-based and field-wise cross-validation methods using percentile performance metrics, demonstrates the effectiveness of using UAS-collected multi-sensory data for accurate crop yield estimation.
Mohammad Abdus Shahid Rafi is currently a Ph.D. Candidate in Electrical and Computer Engineering at Mississippi State University. He has worked as a graduate research assistant at the Geosystems Research Institute, HPC2, and IMPRESS Lab. His research interests include remote sensing, unmanned aircraft systems, precision agriculture, signal of opportunity (SoOp), among others. He is a student member of IEEE, the IEEE Geoscience and Remote Sensing Society, and SPIE. He received the 2024 and 2025 MSU Graduate Research Symposium Awards.
* For further information, contact: For WebEx access, scan the QR code:
Dr. Jenny Du | du@ece.msstate.edu | 5-2035 