Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390
Much remote sensing (RS) research focuses on fusing, i.e., combining, multi-resolution/multi-sensor imagery for land use/land cover (LULC) classification. In relation to this topic, Sun and Schulz [1] recently found that a combination of visible-to-near infrared (VNIR; 30 m spatial resolution) and...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/7/10/13436 |
id |
doaj-0a51d9905e014068910afaff76502ac4 |
---|---|
record_format |
Article |
spelling |
doaj-0a51d9905e014068910afaff76502ac42020-11-24T23:26:31ZengMDPI AGRemote Sensing2072-42922015-10-01710134361343910.3390/rs71013436rs71013436Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390Brian A. Johnson0Institute for Global Environmental Strategies, 2108-11 Kamiyamaguchi, Hayama, Kanagawa 240-0115, JapanMuch remote sensing (RS) research focuses on fusing, i.e., combining, multi-resolution/multi-sensor imagery for land use/land cover (LULC) classification. In relation to this topic, Sun and Schulz [1] recently found that a combination of visible-to-near infrared (VNIR; 30 m spatial resolution) and thermal infrared (TIR; 100–120 m spatial resolution) Landsat data led to more accurate LULC classification. They also found that using multi-temporal TIR data alone for classification resulted in comparable (and in some cases higher) classification accuracies to the use of multi-temporal VNIR data, which contrasts with the findings of other recent research [2]. This discrepancy, and the generally very high LULC accuracies achieved by Sun and Schulz (up to 99.2% overall accuracy for a combined VNIR/TIR classification result), can likely be explained by their use of an accuracy assessment procedure which does not take into account the multi-resolution nature of the data. Sun and Schulz used 10-fold cross-validation for accuracy assessment, which is not necessarily inappropriate for RS accuracy assessment in general. However, here it is shown that the typical pixel-based cross-validation approach results in non-independent training and validation data sets when the lower spatial resolution TIR images are used for classification, which causes classification accuracy to be overestimated.http://www.mdpi.com/2072-4292/7/10/13436image fusioncross-validationmulti-resolutionmulti-sensorLandsat 8 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Brian A. Johnson |
spellingShingle |
Brian A. Johnson Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 Remote Sensing image fusion cross-validation multi-resolution multi-sensor Landsat 8 |
author_facet |
Brian A. Johnson |
author_sort |
Brian A. Johnson |
title |
Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 |
title_short |
Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 |
title_full |
Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 |
title_fullStr |
Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 |
title_full_unstemmed |
Scale Issues Related to the Accuracy Assessment of Land Use/Land Cover Maps Produced Using Multi-Resolution Data: Comments on “The Improvement of Land Cover Classification by Thermal Remote Sensing”. Remote Sens. 2015, 7(7), 8368–8390 |
title_sort |
scale issues related to the accuracy assessment of land use/land cover maps produced using multi-resolution data: comments on “the improvement of land cover classification by thermal remote sensing”. remote sens. 2015, 7(7), 8368–8390 |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2015-10-01 |
description |
Much remote sensing (RS) research focuses on fusing, i.e., combining, multi-resolution/multi-sensor imagery for land use/land cover (LULC) classification. In relation to this topic, Sun and Schulz [1] recently found that a combination of visible-to-near infrared (VNIR; 30 m spatial resolution) and thermal infrared (TIR; 100–120 m spatial resolution) Landsat data led to more accurate LULC classification. They also found that using multi-temporal TIR data alone for classification resulted in comparable (and in some cases higher) classification accuracies to the use of multi-temporal VNIR data, which contrasts with the findings of other recent research [2]. This discrepancy, and the generally very high LULC accuracies achieved by Sun and Schulz (up to 99.2% overall accuracy for a combined VNIR/TIR classification result), can likely be explained by their use of an accuracy assessment procedure which does not take into account the multi-resolution nature of the data. Sun and Schulz used 10-fold cross-validation for accuracy assessment, which is not necessarily inappropriate for RS accuracy assessment in general. However, here it is shown that the typical pixel-based cross-validation approach results in non-independent training and validation data sets when the lower spatial resolution TIR images are used for classification, which causes classification accuracy to be overestimated. |
topic |
image fusion cross-validation multi-resolution multi-sensor Landsat 8 |
url |
http://www.mdpi.com/2072-4292/7/10/13436 |
work_keys_str_mv |
AT brianajohnson scaleissuesrelatedtotheaccuracyassessmentoflanduselandcovermapsproducedusingmultiresolutiondatacommentsontheimprovementoflandcoverclassificationbythermalremotesensingremotesens20157783688390 |
_version_ |
1725554743806263296 |