Cargando…

Identification of Weeds Based on Hyperspectral Imaging and Machine Learning

Weeds can be major environmental and economic burdens in New Zealand. Traditional methods of weed control including manual and chemical approaches can be time consuming and costly. Some chemical herbicides may have negative environmental and human health impacts. One of the proposed important steps...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yanjie, Al-Sarayreh, Mahmoud, Irie, Kenji, Hackell, Deborah, Bourdot, Graeme, Reis, Marlon M., Ghamkhar, Kioumars
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7868399/
https://www.ncbi.nlm.nih.gov/pubmed/33569069
http://dx.doi.org/10.3389/fpls.2020.611622
_version_ 1783648443351171072
author Li, Yanjie
Al-Sarayreh, Mahmoud
Irie, Kenji
Hackell, Deborah
Bourdot, Graeme
Reis, Marlon M.
Ghamkhar, Kioumars
author_facet Li, Yanjie
Al-Sarayreh, Mahmoud
Irie, Kenji
Hackell, Deborah
Bourdot, Graeme
Reis, Marlon M.
Ghamkhar, Kioumars
author_sort Li, Yanjie
collection PubMed
description Weeds can be major environmental and economic burdens in New Zealand. Traditional methods of weed control including manual and chemical approaches can be time consuming and costly. Some chemical herbicides may have negative environmental and human health impacts. One of the proposed important steps for providing alternatives to these traditional approaches is the automated identification and mapping of weeds. We used hyperspectral imaging data and machine learning to explore the possibility of fast, accurate and automated discrimination of weeds in pastures where ryegrass and clovers are the sown species. Hyperspectral images from two grasses (Setaria pumila [yellow bristle grass] and Stipa arundinacea [wind grass]) and two broad leaf weed species (Ranunculus acris [giant buttercup] and Cirsium arvense [Californian thistle]) were acquired and pre-processed using the standard normal variate method. We trained three classification models, namely partial least squares-discriminant analysis, support vector machine, and Multilayer Perceptron (MLP) using whole plant averaged (Av) spectra and superpixels (Sp) averaged spectra from each weed sample. All three classification models showed repeatable identification of four weeds using both Av and Sp spectra with a range of overall accuracy of 70–100%. However, MLP based on the Sp method produced the most reliable and robust prediction result (89.1% accuracy). Four significant spectral regions were found as highly informative for characterizing the four weed species and could form the basis for a rapid and efficient methodology for identifying weeds in ryegrass/clover pastures.
format Online
Article
Text
id pubmed-7868399
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78683992021-02-09 Identification of Weeds Based on Hyperspectral Imaging and Machine Learning Li, Yanjie Al-Sarayreh, Mahmoud Irie, Kenji Hackell, Deborah Bourdot, Graeme Reis, Marlon M. Ghamkhar, Kioumars Front Plant Sci Plant Science Weeds can be major environmental and economic burdens in New Zealand. Traditional methods of weed control including manual and chemical approaches can be time consuming and costly. Some chemical herbicides may have negative environmental and human health impacts. One of the proposed important steps for providing alternatives to these traditional approaches is the automated identification and mapping of weeds. We used hyperspectral imaging data and machine learning to explore the possibility of fast, accurate and automated discrimination of weeds in pastures where ryegrass and clovers are the sown species. Hyperspectral images from two grasses (Setaria pumila [yellow bristle grass] and Stipa arundinacea [wind grass]) and two broad leaf weed species (Ranunculus acris [giant buttercup] and Cirsium arvense [Californian thistle]) were acquired and pre-processed using the standard normal variate method. We trained three classification models, namely partial least squares-discriminant analysis, support vector machine, and Multilayer Perceptron (MLP) using whole plant averaged (Av) spectra and superpixels (Sp) averaged spectra from each weed sample. All three classification models showed repeatable identification of four weeds using both Av and Sp spectra with a range of overall accuracy of 70–100%. However, MLP based on the Sp method produced the most reliable and robust prediction result (89.1% accuracy). Four significant spectral regions were found as highly informative for characterizing the four weed species and could form the basis for a rapid and efficient methodology for identifying weeds in ryegrass/clover pastures. Frontiers Media S.A. 2021-01-25 /pmc/articles/PMC7868399/ /pubmed/33569069 http://dx.doi.org/10.3389/fpls.2020.611622 Text en Copyright © 2021 Li, Al-Sarayreh, Irie, Hackell, Bourdot, Reis and Ghamkhar. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Plant Science
Li, Yanjie
Al-Sarayreh, Mahmoud
Irie, Kenji
Hackell, Deborah
Bourdot, Graeme
Reis, Marlon M.
Ghamkhar, Kioumars
Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title_full Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title_fullStr Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title_full_unstemmed Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title_short Identification of Weeds Based on Hyperspectral Imaging and Machine Learning
title_sort identification of weeds based on hyperspectral imaging and machine learning
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7868399/
https://www.ncbi.nlm.nih.gov/pubmed/33569069
http://dx.doi.org/10.3389/fpls.2020.611622
work_keys_str_mv AT liyanjie identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT alsarayrehmahmoud identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT iriekenji identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT hackelldeborah identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT bourdotgraeme identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT reismarlonm identificationofweedsbasedonhyperspectralimagingandmachinelearning
AT ghamkharkioumars identificationofweedsbasedonhyperspectralimagingandmachinelearning