Cargando…

Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network

Weeds are a persistent problem on sod farms, and herbicides to control different weed species are one of the largest chemical inputs. Recent advances in unmanned aerial systems (UAS) and artificial intelligence provide opportunities for weed mapping on sod farms. This study investigates the weed typ...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jing, Maleski, Jerome, Jespersen, David, Waltz, F. C., Rains, Glen, Schwartz, Brian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8660967/
https://www.ncbi.nlm.nih.gov/pubmed/34899768
http://dx.doi.org/10.3389/fpls.2021.702626
_version_ 1784613300400553984
author Zhang, Jing
Maleski, Jerome
Jespersen, David
Waltz, F. C.
Rains, Glen
Schwartz, Brian
author_facet Zhang, Jing
Maleski, Jerome
Jespersen, David
Waltz, F. C.
Rains, Glen
Schwartz, Brian
author_sort Zhang, Jing
collection PubMed
description Weeds are a persistent problem on sod farms, and herbicides to control different weed species are one of the largest chemical inputs. Recent advances in unmanned aerial systems (UAS) and artificial intelligence provide opportunities for weed mapping on sod farms. This study investigates the weed type composition and area through both ground and UAS-based weed surveys and trains a convolutional neural network (CNN) for identifying and mapping weeds in sod fields using UAS-based imagery and a high-level application programming interface (API) implementation (Fastai) of the PyTorch deep learning library. The performance of the CNN was overall similar to, and in some classes (broadleaf and spurge) better than, human eyes indicated by the metric recall. In general, the CNN detected broadleaf, grass weeds, spurge, sedge, and no weeds at a precision between 0.68 and 0.87, 0.57 and 0.82, 0.68 and 0.83, 0.66 and 0.90, and 0.80 and 0.88, respectively, when using UAS images at 0.57 cm–1.28 cm pixel(–1) resolution. Recall ranges for the five classes were 0.78–0.93, 0.65–0.87, 0.82–0.93, 0.52–0.79, and 0.94–0.99. Additionally, this study demonstrates that a CNN can achieve precision and recall above 0.9 at detecting different types of weeds during turf establishment when the weeds are mature. The CNN is limited by the image resolution, and more than one model may be needed in practice to improve the overall performance of weed mapping.
format Online
Article
Text
id pubmed-8660967
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-86609672021-12-11 Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network Zhang, Jing Maleski, Jerome Jespersen, David Waltz, F. C. Rains, Glen Schwartz, Brian Front Plant Sci Plant Science Weeds are a persistent problem on sod farms, and herbicides to control different weed species are one of the largest chemical inputs. Recent advances in unmanned aerial systems (UAS) and artificial intelligence provide opportunities for weed mapping on sod farms. This study investigates the weed type composition and area through both ground and UAS-based weed surveys and trains a convolutional neural network (CNN) for identifying and mapping weeds in sod fields using UAS-based imagery and a high-level application programming interface (API) implementation (Fastai) of the PyTorch deep learning library. The performance of the CNN was overall similar to, and in some classes (broadleaf and spurge) better than, human eyes indicated by the metric recall. In general, the CNN detected broadleaf, grass weeds, spurge, sedge, and no weeds at a precision between 0.68 and 0.87, 0.57 and 0.82, 0.68 and 0.83, 0.66 and 0.90, and 0.80 and 0.88, respectively, when using UAS images at 0.57 cm–1.28 cm pixel(–1) resolution. Recall ranges for the five classes were 0.78–0.93, 0.65–0.87, 0.82–0.93, 0.52–0.79, and 0.94–0.99. Additionally, this study demonstrates that a CNN can achieve precision and recall above 0.9 at detecting different types of weeds during turf establishment when the weeds are mature. The CNN is limited by the image resolution, and more than one model may be needed in practice to improve the overall performance of weed mapping. Frontiers Media S.A. 2021-11-26 /pmc/articles/PMC8660967/ /pubmed/34899768 http://dx.doi.org/10.3389/fpls.2021.702626 Text en Copyright © 2021 Zhang, Maleski, Jespersen, Waltz, Rains and Schwartz. https://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
Zhang, Jing
Maleski, Jerome
Jespersen, David
Waltz, F. C.
Rains, Glen
Schwartz, Brian
Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title_full Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title_fullStr Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title_full_unstemmed Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title_short Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
title_sort unmanned aerial system-based weed mapping in sod production using a convolutional neural network
topic Plant Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8660967/
https://www.ncbi.nlm.nih.gov/pubmed/34899768
http://dx.doi.org/10.3389/fpls.2021.702626
work_keys_str_mv AT zhangjing unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT maleskijerome unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT jespersendavid unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT waltzfc unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT rainsglen unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT schwartzbrian unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork