Date of Award:
8-2026
Document Type:
Thesis
Degree Name:
Master of Science (MS)
Department:
Applied Sciences, Technology, and Education
Committee Chair(s)
Aaron Etienne
Committee
Aaron Etienne
Committee
Rhonda Miller
Committee
Eric Westra
Committee
Sierra Young
Abstract
Weeds cost global agriculture over $32 billion annually and reduce crop yields by nearly one-third. Current weed control relies heavily on spraying herbicides uniformly across entire fields, leading to herbicide-resistant weeds, environmental harm, and increasing costs for farmers. A smarter approach is detecting weeds from the air and spraying only where they are present. This could dramatically reduce herbicide use while protecting crop yields. This thesis developed a complete system for identifying weeds in corn fields using drone-captured images and artificial intelligence. Working in commercial forage corn fields in Cache Valley, Utah, high-resolution aerial images were collected and used to build USU-CornWeedDB. To the author’s knowledge, USU-CornWeedDB is the first publicly available corn weed image dataset for the Intermountain West region. The dataset includes 800 images with hand-drawn labels identifying three common weed species (common lambsquarters, redroot pigweed, and green foxtail) alongside 8,000 additional unlabeled images. Twenty-eight AI detection models were tested to find which could most accurately and efficiently identify these weeds. A lightweight model called YOLOv9s achieved the best balance of accuracy and efficiency, making it well-suited for real-time processing on small, drone-mounted computers. Additionally, six methods that learn from unlabeled images were evaluated to reduce the need for time and resource-intensive manual labeling. Results showed that simpler learning approaches performed more reliably than complex ones in the challenging visual conditions of real agricultural fields. This research lays the groundwork for an autonomous drone-based weed management system that can help farmers reduce chemical inputs, lower costs, and farm more sustainably.
Checksum
228aaf11699bb9029d58eba9487dca2e
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Bhandari, Utsav, "Multispecies Weed Detection Using Unmanned Aerial Vehicles and Deep Learning Object Detection Models in Utah Forage Crop Corn Field" (2026). All Graduate Theses and Dissertations, Fall 2023 to Present. 838.
https://digitalcommons.usu.edu/etd2023/838
Included in
Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .