Kentucky State University (KSU) alumnus, Lalit Pun Magar, is pioneering a new study in soybean. His research primarily focuses on integrating manual and high throughput aerial phenotyping to identify the most effective sensor, indices, and timing to study morphophysiological parameters and yield prediction in soybean. His research utilizes Unmanned Aerial Vehicles or drones (DJI Mavic 3M and DJI Matrice 300 RTK) mounted with advanced sensors like RGB, multispectral, and LiDAR to collect aerial data to validate against the manually measured plant parameters in the soybean field. No previous studies in soybean have integrated such a variety of sensors within a single field experiment.

Pun Magar, who recently graduated with a Master of Science in Environmental Studies in Spring 2025, joined the KSU Agronomy and crop Physiology Lab in Fall 2023. Since then, he has been exploring drone data, satellite data, and their relationship with ground truth measurements and is currently continuing the study as a Research Associate with Dr. Anuj Chiluwal.

“Working independently from pre-processing and post-processing drone data using advanced software, Mr. Pun Magar achieved a significant milestone by identifying the most effective UAV-based sensor for estimating soybean plant height. His technically rigorous approach and findings play a vital role in addressing key phenotyping bottlenecks in soybean research,” said Dr. Chiluwal.

Pun Magar has already published a peer-reviewed paper as the first author titled, “Plant height measurement using UAV-based aerial RGB and LiDAR images in soybean,” in the esteemed Frontiers in Plant Science journal under the section Technical Advances in Plant Science. The full paper can be accessed following the link: https://doi.org/10.3389/fpls.2025.1488760. 

Before this study, there was considerable uncertainty among growers, researchers, agronomists, and breeders regarding the most appropriate sensor for estimating plant height in soybean.  Pun Magar’s research findings suggest that UAV-based LiDAR as the most suitable sensor for estimating soybean plant height, particularly during pod development and seed filling. Additionally, a low-cost RGB camera showed comparatively higher accuracy for plant height estimation in soybean during physiological maturity. 

“These significant findings make a valuable contribution to the field of precision agriculture, supporting more informed decisions on sensor selection based on budget, crop growth stage, and the required level of precision,” said Pun Magar. 

Pun Magar has also conducted numerous other studies on vegetation health assessments using drone-based aerial imagery data and preparing multiple other manuscripts for submission to peer-reviewed journals. These studies were funded by the USDA-NIFA 1890 Capacity Building Grant (Award Number 2023-38821-39960) titled, “Optimizing Nitrogen Management in Soybean Integrating Manual and High Throughput Aerial Phenotyping.” 

“Mr. Pun Magar has conducted multiple studies, already published a peer-reviewed article in a reputable journal and is currently preparing several more manuscripts. Achieving all this in less than two years is truly remarkable and reflects his exceptional productivity, passion, and dedication,” said Dr. Chiluwal.