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

Guardado en:
Detalles Bibliográficos
Autores principales: Jing Zhang, Jerome Maleski, David Jespersen, F. C. Waltz, Glen Rains, Brian Schwartz
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/daf9bf860603469f842428ae02c0ee6f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:daf9bf860603469f842428ae02c0ee6f
record_format dspace
spelling oai:doaj.org-article:daf9bf860603469f842428ae02c0ee6f2021-12-01T05:33:43ZUnmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network1664-462X10.3389/fpls.2021.702626https://doaj.org/article/daf9bf860603469f842428ae02c0ee6f2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fpls.2021.702626/fullhttps://doaj.org/toc/1664-462XWeeds 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.Jing ZhangJerome MaleskiDavid JespersenF. C. WaltzGlen RainsBrian SchwartzFrontiers Media S.A.articleBermudagrassartificial intelligenceFastaiResNetRGB imageryPlant cultureSB1-1110ENFrontiers in Plant Science, Vol 12 (2021)
institution DOAJ
collection DOAJ
language EN
topic Bermudagrass
artificial intelligence
Fastai
ResNet
RGB imagery
Plant culture
SB1-1110
spellingShingle Bermudagrass
artificial intelligence
Fastai
ResNet
RGB imagery
Plant culture
SB1-1110
Jing Zhang
Jerome Maleski
David Jespersen
F. C. Waltz
Glen Rains
Brian Schwartz
Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network
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 article
author Jing Zhang
Jerome Maleski
David Jespersen
F. C. Waltz
Glen Rains
Brian Schwartz
author_facet Jing Zhang
Jerome Maleski
David Jespersen
F. C. Waltz
Glen Rains
Brian Schwartz
author_sort Jing Zhang
title 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_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_sort unmanned aerial system-based weed mapping in sod production using a convolutional neural network
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/daf9bf860603469f842428ae02c0ee6f
work_keys_str_mv AT jingzhang unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT jeromemaleski unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT davidjespersen unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT fcwaltz unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT glenrains unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
AT brianschwartz unmannedaerialsystembasedweedmappinginsodproductionusingaconvolutionalneuralnetwork
_version_ 1718405508594925568