A comparison of protocols for high-throughput weeds mapping

Authors: Casanova, Joaquin; BERGMANN, NICHOLAS - Washington State University; KALIN, JESSICA - Washington State University; Heineck, Garett; BURKE, IAN - Washington State University

Submitted to: Smart Agricultural Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/4/2025
Publication Date: 6/5/2025
Citation: Casanova, J.J., Bergmann, N., Kalin, J., Heineck, G.C., Burke, I. 2025. A comparison of protocols for high-throughput weeds mapping. Smart Agricultural Technology. 12. Article 101076. https://doi.org/10.1016/j.atech.2025.101076.
DOI: https://doi.org/10.1016/j.atech.2025.101076

Interpretive Summary: Weeds in the US are becoming resistant to common herbicides. To manage weeds, farmers need non-chemical alternative methods and more precise herbicide application help. This means weeds are exposed to multiple modes of action, decreasing the formation of resistant populations. However, generating spray maps and testing non-chemical methods require field-scale mapping of weeds. Typical methods for weeds mapping are time-consuming scouting on foot and easily miss weeds. To give fast, accuate maps, this paper compares 12 total methods. Overall, the drone imaging with above-ground weed counts outperformed other methods and can be recommended as a pipeline for rapid mapping weeds in field crops. This work is of interest to both farmers and researchers managing or studying weeds.

Technical Abstract: Increasing herbicide resistance in the US demands novel approaches to integrated pest management. More targeted chemical applications and non-chemical alternative methods help expose weeds to multiple modes of action, decreasing the formation of resistant populations. However, generating prescription maps and evaluating non-chemical methods require field-scale mapping of weeds. Typical methods for weeds mapping either involve laborious mapping on the ground or impractical low-altitude UAV imaging. Additionally, the literature describes an array of imaging techniques demonstrated in very select circumstances. To give clear guidelines for future research, this paper compares three imaging techniques, two weed count model types, and two ground validation methods (quadrat counts and seedbank counts) for remote weeds mapping on five sites experiencing infestations of different common weed species. Overall, the multispectral imaging techniques using Poisson count models and weed counts in quadrats as ground truth outperformed other methods and can be recommended as a pipeline for rapid mapping weeds in row crops. However, seedbank density did not map well when using imagery, but 50 seedbank samples were adequate for assessing seedbank.