Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability

Many important ecological processes play out over large geographic ranges, and accurate large-scale monitoring of populations is a requirement for their effective management. Of particular interest are agricultural weeds, which cause widespread economic and ecological damage. However, the scale of w...

Full description

Saved in:
Bibliographic Details
Main Authors: Robert M. Goodsell, Shaun Coutts, William Oxford, Helen Hicks, David Comont, Robert P. Freckleton, Dylan Z. Childs
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/24/4749
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102841056296960
author Robert M. Goodsell
Shaun Coutts
William Oxford
Helen Hicks
David Comont
Robert P. Freckleton
Dylan Z. Childs
author_facet Robert M. Goodsell
Shaun Coutts
William Oxford
Helen Hicks
David Comont
Robert P. Freckleton
Dylan Z. Childs
author_sort Robert M. Goodsell
collection DOAJ
description Many important ecological processes play out over large geographic ranges, and accurate large-scale monitoring of populations is a requirement for their effective management. Of particular interest are agricultural weeds, which cause widespread economic and ecological damage. However, the scale of weed population data collection is limited by an inevitable trade-off between quantity and quality. Remote sensing offers a promising route to the large-scale collection of population state data. However, a key challenge is to collect high enough resolution data and account for between-site variability in environmental (i.e., radiometric) conditions that may make prediction of population states in new data challenging. Here, we use a multi-site hyperspectral image dataset in conjunction with ensemble learning techniques in an attempt to predict densities of an arable weed (<i>Alopecurus myosuroides</i>, Huds) across an agricultural landscape. We demonstrate reasonable predictive performance (using the geometric mean score-GMS) when classifiers are used to predict new data from the same site (GMS = 0.74-low density, GMS = 0.74-medium density, GMS = 0.7-High density). However, even using flexible ensemble techniques to account for variability in spectral data, we show that out-of-field predictive performance is poor (GMS = 0.06-low density, GMS = 0.13-medium density, GMS = 0.08-High density). This study highlights the difficulties in identifying weeds in situ, even using high quality image data from remote sensing.
format Article
id doaj-art-349c3a9c678f4707a14ad6bd6a72266f
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-349c3a9c678f4707a14ad6bd6a72266f2024-12-27T14:51:05ZengMDPI AGRemote Sensing2072-42922024-12-011624474910.3390/rs16244749Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site VariabilityRobert M. Goodsell0Shaun Coutts1William Oxford2Helen Hicks3David Comont4Robert P. Freckleton5Dylan Z. Childs6Ecology and Evolutionary Biology, School of Biosciences, University of Sheffield, Sheffield S10 2TN, UKLincoln Institute for Agri-Food Technology, College of Science, Lincoln LN2 2BJ, UK2Excel Aviation Ltd., Hangar 3, Fourth Avenue, Doncaster DN9 3GE, UKSchool of Animal Rural & Environmental Sciences, Nottingham Trent University, 50 Shakespeare St., Nottingham NG1 4FQ, UKRothamsted Research, Harpenden, Hertfordshire AL5 2JQ, UKEcology and Evolutionary Biology, School of Biosciences, University of Sheffield, Sheffield S10 2TN, UKEcology and Evolutionary Biology, School of Biosciences, University of Sheffield, Sheffield S10 2TN, UKMany important ecological processes play out over large geographic ranges, and accurate large-scale monitoring of populations is a requirement for their effective management. Of particular interest are agricultural weeds, which cause widespread economic and ecological damage. However, the scale of weed population data collection is limited by an inevitable trade-off between quantity and quality. Remote sensing offers a promising route to the large-scale collection of population state data. However, a key challenge is to collect high enough resolution data and account for between-site variability in environmental (i.e., radiometric) conditions that may make prediction of population states in new data challenging. Here, we use a multi-site hyperspectral image dataset in conjunction with ensemble learning techniques in an attempt to predict densities of an arable weed (<i>Alopecurus myosuroides</i>, Huds) across an agricultural landscape. We demonstrate reasonable predictive performance (using the geometric mean score-GMS) when classifiers are used to predict new data from the same site (GMS = 0.74-low density, GMS = 0.74-medium density, GMS = 0.7-High density). However, even using flexible ensemble techniques to account for variability in spectral data, we show that out-of-field predictive performance is poor (GMS = 0.06-low density, GMS = 0.13-medium density, GMS = 0.08-High density). This study highlights the difficulties in identifying weeds in situ, even using high quality image data from remote sensing.https://www.mdpi.com/2072-4292/16/24/4749black-grassmachine learningweedshyperspectral imagery
spellingShingle Robert M. Goodsell
Shaun Coutts
William Oxford
Helen Hicks
David Comont
Robert P. Freckleton
Dylan Z. Childs
Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
Remote Sensing
black-grass
machine learning
weeds
hyperspectral imagery
title Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
title_full Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
title_fullStr Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
title_full_unstemmed Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
title_short Black-Grass Monitoring Using Hyperspectral Image Data Is Limited by Between-Site Variability
title_sort black grass monitoring using hyperspectral image data is limited by between site variability
topic black-grass
machine learning
weeds
hyperspectral imagery
url https://www.mdpi.com/2072-4292/16/24/4749
work_keys_str_mv AT robertmgoodsell blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT shauncoutts blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT williamoxford blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT helenhicks blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT davidcomont blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT robertpfreckleton blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability
AT dylanzchilds blackgrassmonitoringusinghyperspectralimagedataislimitedbybetweensitevariability