Skip to main content
ARS Home » Plains Area » College Station, Texas » Southern Plains Agricultural Research Center » Aerial Application Technology Research » Research » Publications at this Location » Publication #390636

Research Project: Improved Aerial Application Technologies for Precise and Effective Delivery of Crop Production Products

Location: Aerial Application Technology Research

Title: GIS-based volunteer cotton habitat prediction and plant-level detection with UAV remote sensing

Author
item WANG, TIANYI - Texas A&M University
item MEI, XIAOHAN - Texas A&M University
item THOMASSON, ALEX - Texas A&M University
item Yang, Chenghai
item HAN, XIONGZHE - Texas A&M University
item YADAV, PAPPU KUMAR - Texas A&M University
item SHI, YEYIN - University Of Nebraska

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/11/2021
Publication Date: 12/27/2021
Citation: Wang, T., Mei, X., Thomasson, A., Yang, C., Han, X., Yadav, P., Shi, Y. 2021. GIS-based volunteer cotton habitat prediction and plant-level detection with UAV remote sensing. Computers and Electronics in Agriculture. 193. Article 106629. https://doi.org/10.1016/j.compag.2021.106629.
DOI: https://doi.org/10.1016/j.compag.2021.106629

Interpretive Summary: The potential habitat for volunteer cotton in southern Texas creates the risk of encroachment of cotton boll weevils. The main objective of this study was to develop a geographic information system (GIS) framework to efficiently locate volunteer cotton plants in the Southern Texas cotton production regions, thus reducing the time and economic costs of their removal. GIS network analysis was applied to estimate the most likely routes for cotton transportation, and a GIS model was created to identify and visualize the potential area of volunteer cotton growth. A method based on unmanned aerial vehicle (UAV) remote sensing was also proposed to detect the precise location of volunteer cotton plants in potential areas for subsequent removal. The results from this study showed that the proposed GIS network analysis model coupled with UAV remote sensing could effectively identify the potential habitat area and precise locations of volunteer cotton.

Technical Abstract: Volunteer cotton is the cotton plant germinated and grown unintentionally at an unwanted location. Volunteer cotton plants can serve as a host for a harmful cotton pest called cotton boll weevil to survive through the winter. The main objective of this study was to develop a geographic information system (GIS) framework to efficiently locate volunteer cotton plants in the cotton production regions in southern Texas, thus reducing the time and economic costs for their removal. A GIS network analysis tool was applied to estimate the most likely routes for cotton transportation, and a GIS model was created to identify and visualize potential areas of volunteer cotton growth. The GIS model indicated that 31 counties in southern Texas may have habitats for volunteer cotton. Hidalgo, Cameron, Nueces, and San Patricio are the riskiest counties. Moreover, a method based on unmanned aerial vehicle (UAV) remote sensing was proposed to detect the precise locations of volunteer cotton plants in potential areas for their subsequent removal. In this study, the UAV only scanned limited samples of potential volunteer cotton growth areas. The UAV results were used to validate the outcome of the GIS model. The results indicated that UAV remote sensing coupled with proposed image analysis methods could accurately identify the precise locations of volunteer cotton, and could potentially assist in the elimination of volunteer cotton caused by cotton module transportation.