The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects

Site-specific weed management (SSWM) may reduce herbicide use by identifying weed patches and weed-free areas. However, one major constraint is robust weed detection algorithms that are able to predict weed infestations outside of the training data. This study investigates the predictive power of re...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Signe M. Jensen, Muhammad Javaid Akhter, Saiful Azim, Jesper Rasmussen
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	prediction models validation weed detection weed monitoring vegetation indices precision agriculture Agriculture S
Acceso en línea:	https://doaj.org/article/8af3983e8d5a492b80e4457298942e6c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8af3983e8d5a492b80e4457298942e6c
record_format	dspace
spelling	oai:doaj.org-article:8af3983e8d5a492b80e4457298942e6c2021-11-25T16:09:58ZThe Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects10.3390/agronomy111122772073-4395https://doaj.org/article/8af3983e8d5a492b80e4457298942e6c2021-11-01T00:00:00Zhttps://www.mdpi.com/2073-4395/11/11/2277https://doaj.org/toc/2073-4395Site-specific weed management (SSWM) may reduce herbicide use by identifying weed patches and weed-free areas. However, one major constraint is robust weed detection algorithms that are able to predict weed infestations outside of the training data. This study investigates the predictive power of regression models trained on drone imagery that are used within fields to predict infestations of annual grass weeds in the late growth stages of cereals. The main objective was to identify the optimum sampling strategy for training regression models based on aerial RGB images. The study showed that training based on sampling from the whole range of weed infestations or the extreme values in the field provided better prediction accuracy than random sampling. Prediction models based on vegetation indices (VIs) offered a useful alternative to a more complex random forest machine-learning algorithm. For binary decision-making, linear regression utilizing weed density information resulted in higher accuracy than a logistic regression approach that only relied on information regarding the presence/absence of weeds. Across six fields, the average balanced accuracy based on linear regression was in the range of 75–83%, with the highest accuracy found when the sampling was from the extreme values in the field, and with the lowest accuracy found for random sampling. For future work on training weed prediction models, choosing training sets covering the entire sample space is recommended in favor of random sampling.Signe M. JensenMuhammad Javaid AkhterSaiful AzimJesper RasmussenMDPI AGarticleprediction modelsvalidationweed detectionweed monitoringvegetation indicesprecision agricultureAgricultureSENAgronomy, Vol 11, Iss 2277, p 2277 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	prediction models validation weed detection weed monitoring vegetation indices precision agriculture Agriculture S
spellingShingle	prediction models validation weed detection weed monitoring vegetation indices precision agriculture Agriculture S Signe M. Jensen Muhammad Javaid Akhter Saiful Azim Jesper Rasmussen The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
description	Site-specific weed management (SSWM) may reduce herbicide use by identifying weed patches and weed-free areas. However, one major constraint is robust weed detection algorithms that are able to predict weed infestations outside of the training data. This study investigates the predictive power of regression models trained on drone imagery that are used within fields to predict infestations of annual grass weeds in the late growth stages of cereals. The main objective was to identify the optimum sampling strategy for training regression models based on aerial RGB images. The study showed that training based on sampling from the whole range of weed infestations or the extreme values in the field provided better prediction accuracy than random sampling. Prediction models based on vegetation indices (VIs) offered a useful alternative to a more complex random forest machine-learning algorithm. For binary decision-making, linear regression utilizing weed density information resulted in higher accuracy than a logistic regression approach that only relied on information regarding the presence/absence of weeds. Across six fields, the average balanced accuracy based on linear regression was in the range of 75–83%, with the highest accuracy found when the sampling was from the extreme values in the field, and with the lowest accuracy found for random sampling. For future work on training weed prediction models, choosing training sets covering the entire sample space is recommended in favor of random sampling.
format	article
author	Signe M. Jensen Muhammad Javaid Akhter Saiful Azim Jesper Rasmussen
author_facet	Signe M. Jensen Muhammad Javaid Akhter Saiful Azim Jesper Rasmussen
author_sort	Signe M. Jensen
title	The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
title_short	The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
title_full	The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
title_fullStr	The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
title_full_unstemmed	The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects
title_sort	predictive power of regression models to determine grass weed infestations in cereals based on drone imagery—statistical and practical aspects
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8af3983e8d5a492b80e4457298942e6c
work_keys_str_mv	AT signemjensen thepredictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT muhammadjavaidakhter thepredictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT saifulazim thepredictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT jesperrasmussen thepredictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT signemjensen predictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT muhammadjavaidakhter predictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT saifulazim predictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects AT jesperrasmussen predictivepowerofregressionmodelstodeterminegrassweedinfestationsincerealsbasedondroneimagerystatisticalandpracticalaspects
_version_	1718413328088301568

The Predictive Power of Regression Models to Determine Grass Weed Infestations in Cereals Based on Drone Imagery—Statistical and Practical Aspects

Ejemplares similares