Palmer Amaranth (Amaranthus palmeri S. Watson) Identification Using Hyperspectral Imaging Technology
Date of Award
2020
Publisher
North Dakota State University
Document Type
Thesis
Degree Awarded
Master of Science (MS)
Program
Agricultural and Biosystems Engineering
Department
Agricultural and Biosystems Engineering
College
Agriculture, Food Systems and Natural Resources
Faculty Advisor
Sun, Xin
Description
Palmer amaranth is a troublesome weed in modern day agriculture. Timely identification, along with adoption of site-specific weed management practices, will enable farmers to reduce Palmer amaranth control costs and improve efficacy. The feasibility of collecting hyperspectral imagery to identify Palmer amaranth and soybean was evaluated in the greenhouse and field. Hyperspectral images were collected across 224 spectral bands onPalmer amaranth and soybean twice weekly from the one to three-leaf growth stage in three different runs (28 replications per run) temporally separated in a greenhouse. Partial least squares-discriminant analysis and soft independent modelling of class analogy models were developed to identify Palmer amaranth and soybean plants and had cumulative variations of 60% and 85%, and predictive abilities of 60% and 82%, respectively. This study concluded that hyperspectral imaging could be a potential tool to decipher Palmer amaranth from soybean plants.
Recommended Citation
Barros da Costa, Cristiano Manuel, "Palmer Amaranth (Amaranthus palmeri S. Watson) Identification Using Hyperspectral Imaging Technology" (2020). Agribusiness and Biosystems Engineering. 34.
https://digitalcommons.ndsu.edu/agribusiness-biosystems-engi/34
Rights
NDSU Policy 190.6.2
Rights Link
https://www.ndsu.edu/fileadmin/policy/190.pdf
Handle Identifier
https://hdl.handle.net/10365/32276