Eintrag weiter verarbeiten
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks
Gespeichert in:
Zeitschriftentitel: | Journal of Geophysical Research: Atmospheres |
---|---|
Personen und Körperschaften: | , , , |
In: | Journal of Geophysical Research: Atmospheres, 110, 2005, D3 |
Format: | E-Article |
Sprache: | Englisch |
veröffentlicht: |
American Geophysical Union (AGU)
|
Schlagwörter: |
author_facet |
Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. |
---|---|
author |
Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. |
spellingShingle |
Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. Journal of Geophysical Research: Atmospheres Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks Paleontology Space and Planetary Science Earth and Planetary Sciences (miscellaneous) Atmospheric Science Earth-Surface Processes Geochemistry and Petrology Soil Science Water Science and Technology Ecology Aquatic Science Forestry Oceanography Geophysics |
author_sort |
shabanov, n. v. |
spelling |
Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. 0148-0227 American Geophysical Union (AGU) Paleontology Space and Planetary Science Earth and Planetary Sciences (miscellaneous) Atmospheric Science Earth-Surface Processes Geochemistry and Petrology Soil Science Water Science and Technology Ecology Aquatic Science Forestry Oceanography Geophysics http://dx.doi.org/10.1029/2004jd005257 <jats:p>This paper presents an ARTMAP neural network approach for burn detection in Moderate Resolution Imaging Spectroradiometer (MODIS) data using two methods: discrete and continuous classifications. The study area covers the states of Idaho and Montana in the United States, where extensive fire events took place during the months of July and August in the year 2000. The proposed approach differs from commonly used change detection schemes by utilizing a single surface reflectance image instead of time series of satellite data. Burn detection in this study was accomplished by the classification of land into four classes: burns, woody vegetation, herbaceous vegetation, and barren. We performed the discrete classification of coarse (500‐m MODIS data) and high‐resolution (30‐m Enhanced Thematic Mapper (ETM+) data) surface reflectance data with an ARTMAP classifier to evaluate the impact of a land cover mixture on burn detection. The analysis of classification results reveals commission and omission errors in the evaluation of burn area extent at a coarse‐resolution scale. To account for land cover heterogeneity, we utilized the continuous classification of coarse‐resolution data with an ARTMAP mixture model. A training data set on the land cover mixture at 500‐m scale of MODIS data was assembled from the aggregated 30‐m ETM+ classification. The ARTMAP mixture model was trained with MODIS surface reflectance data and land cover mixture information to generate a continuous classification of burns (expressed in percentage of burns per pixel). Data fusion of coarse‐ and high‐resolution satellite data in this study resulted in a more natural and accurate mapping of burns as mixtures with other land cover types.</jats:p> Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks Journal of Geophysical Research: Atmospheres |
doi_str_mv |
10.1029/2004jd005257 |
facet_avail |
Online Free |
finc_class_facet |
Physik Technik Geologie und Paläontologie Geographie Chemie und Pharmazie Land- und Forstwirtschaft, Gartenbau, Fischereiwirtschaft, Hauswirtschaft Biologie Allgemeine Naturwissenschaft |
format |
ElectronicArticle |
fullrecord |
blob:ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAyOS8yMDA0amQwMDUyNTc |
id |
ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAyOS8yMDA0amQwMDUyNTc |
institution |
DE-Zwi2 DE-D161 DE-Gla1 DE-Zi4 DE-15 DE-Pl11 DE-Rs1 DE-105 DE-14 DE-Ch1 DE-L229 DE-D275 DE-Bn3 DE-Brt1 |
imprint |
American Geophysical Union (AGU), 2005 |
imprint_str_mv |
American Geophysical Union (AGU), 2005 |
issn |
0148-0227 |
issn_str_mv |
0148-0227 |
language |
English |
mega_collection |
American Geophysical Union (AGU) (CrossRef) |
match_str |
shabanov2005subpixelburndetectioninmoderateresolutionimagingspectroradiometer500mdatawithartmapneuralnetworks |
publishDateSort |
2005 |
publisher |
American Geophysical Union (AGU) |
recordtype |
ai |
record_format |
ai |
series |
Journal of Geophysical Research: Atmospheres |
source_id |
49 |
title |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_unstemmed |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_full |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_fullStr |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_full_unstemmed |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_short |
Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_sort |
subpixel burn detection in moderate resolution imaging spectroradiometer 500‐m data with artmap neural networks |
topic |
Paleontology Space and Planetary Science Earth and Planetary Sciences (miscellaneous) Atmospheric Science Earth-Surface Processes Geochemistry and Petrology Soil Science Water Science and Technology Ecology Aquatic Science Forestry Oceanography Geophysics |
url |
http://dx.doi.org/10.1029/2004jd005257 |
publishDate |
2005 |
physical |
|
description |
<jats:p>This paper presents an ARTMAP neural network approach for burn detection in Moderate Resolution Imaging Spectroradiometer (MODIS) data using two methods: discrete and continuous classifications. The study area covers the states of Idaho and Montana in the United States, where extensive fire events took place during the months of July and August in the year 2000. The proposed approach differs from commonly used change detection schemes by utilizing a single surface reflectance image instead of time series of satellite data. Burn detection in this study was accomplished by the classification of land into four classes: burns, woody vegetation, herbaceous vegetation, and barren. We performed the discrete classification of coarse (500‐m MODIS data) and high‐resolution (30‐m Enhanced Thematic Mapper (ETM+) data) surface reflectance data with an ARTMAP classifier to evaluate the impact of a land cover mixture on burn detection. The analysis of classification results reveals commission and omission errors in the evaluation of burn area extent at a coarse‐resolution scale. To account for land cover heterogeneity, we utilized the continuous classification of coarse‐resolution data with an ARTMAP mixture model. A training data set on the land cover mixture at 500‐m scale of MODIS data was assembled from the aggregated 30‐m ETM+ classification. The ARTMAP mixture model was trained with MODIS surface reflectance data and land cover mixture information to generate a continuous classification of burns (expressed in percentage of burns per pixel). Data fusion of coarse‐ and high‐resolution satellite data in this study resulted in a more natural and accurate mapping of burns as mixtures with other land cover types.</jats:p> |
container_issue |
D3 |
container_start_page |
0 |
container_title |
Journal of Geophysical Research: Atmospheres |
container_volume |
110 |
format_de105 |
Article, E-Article |
format_de14 |
Article, E-Article |
format_de15 |
Article, E-Article |
format_de520 |
Article, E-Article |
format_de540 |
Article, E-Article |
format_dech1 |
Article, E-Article |
format_ded117 |
Article, E-Article |
format_degla1 |
E-Article |
format_del152 |
Buch |
format_del189 |
Article, E-Article |
format_dezi4 |
Article |
format_dezwi2 |
Article, E-Article |
format_finc |
Article, E-Article |
format_nrw |
Article, E-Article |
_version_ |
1792335539388547082 |
geogr_code |
not assigned |
last_indexed |
2024-03-01T14:46:09.974Z |
geogr_code_person |
not assigned |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Subpixel+burn+detection+in+Moderate+Resolution+Imaging+Spectroradiometer+500%E2%80%90m+data+with+ARTMAP+neural+networks&rft.date=2005-02-16&genre=article&issn=0148-0227&volume=110&issue=D3&jtitle=Journal+of+Geophysical+Research%3A+Atmospheres&atitle=Subpixel+burn+detection+in+Moderate+Resolution+Imaging+Spectroradiometer+500%E2%80%90m+data+with+ARTMAP+neural+networks&aulast=Myneni&aufirst=R.+B.&rft_id=info%3Adoi%2F10.1029%2F2004jd005257&rft.language%5B0%5D=eng |
SOLR | |
_version_ | 1792335539388547082 |
author | Shabanov, N. V., Lo, K., Gopal, S., Myneni, R. B. |
author_facet | Shabanov, N. V., Lo, K., Gopal, S., Myneni, R. B., Shabanov, N. V., Lo, K., Gopal, S., Myneni, R. B. |
author_sort | shabanov, n. v. |
container_issue | D3 |
container_start_page | 0 |
container_title | Journal of Geophysical Research: Atmospheres |
container_volume | 110 |
description | <jats:p>This paper presents an ARTMAP neural network approach for burn detection in Moderate Resolution Imaging Spectroradiometer (MODIS) data using two methods: discrete and continuous classifications. The study area covers the states of Idaho and Montana in the United States, where extensive fire events took place during the months of July and August in the year 2000. The proposed approach differs from commonly used change detection schemes by utilizing a single surface reflectance image instead of time series of satellite data. Burn detection in this study was accomplished by the classification of land into four classes: burns, woody vegetation, herbaceous vegetation, and barren. We performed the discrete classification of coarse (500‐m MODIS data) and high‐resolution (30‐m Enhanced Thematic Mapper (ETM+) data) surface reflectance data with an ARTMAP classifier to evaluate the impact of a land cover mixture on burn detection. The analysis of classification results reveals commission and omission errors in the evaluation of burn area extent at a coarse‐resolution scale. To account for land cover heterogeneity, we utilized the continuous classification of coarse‐resolution data with an ARTMAP mixture model. A training data set on the land cover mixture at 500‐m scale of MODIS data was assembled from the aggregated 30‐m ETM+ classification. The ARTMAP mixture model was trained with MODIS surface reflectance data and land cover mixture information to generate a continuous classification of burns (expressed in percentage of burns per pixel). Data fusion of coarse‐ and high‐resolution satellite data in this study resulted in a more natural and accurate mapping of burns as mixtures with other land cover types.</jats:p> |
doi_str_mv | 10.1029/2004jd005257 |
facet_avail | Online, Free |
finc_class_facet | Physik, Technik, Geologie und Paläontologie, Geographie, Chemie und Pharmazie, Land- und Forstwirtschaft, Gartenbau, Fischereiwirtschaft, Hauswirtschaft, Biologie, Allgemeine Naturwissenschaft |
format | ElectronicArticle |
format_de105 | Article, E-Article |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_de520 | Article, E-Article |
format_de540 | Article, E-Article |
format_dech1 | Article, E-Article |
format_ded117 | Article, E-Article |
format_degla1 | E-Article |
format_del152 | Buch |
format_del189 | Article, E-Article |
format_dezi4 | Article |
format_dezwi2 | Article, E-Article |
format_finc | Article, E-Article |
format_nrw | Article, E-Article |
geogr_code | not assigned |
geogr_code_person | not assigned |
id | ai-49-aHR0cDovL2R4LmRvaS5vcmcvMTAuMTAyOS8yMDA0amQwMDUyNTc |
imprint | American Geophysical Union (AGU), 2005 |
imprint_str_mv | American Geophysical Union (AGU), 2005 |
institution | DE-Zwi2, DE-D161, DE-Gla1, DE-Zi4, DE-15, DE-Pl11, DE-Rs1, DE-105, DE-14, DE-Ch1, DE-L229, DE-D275, DE-Bn3, DE-Brt1 |
issn | 0148-0227 |
issn_str_mv | 0148-0227 |
language | English |
last_indexed | 2024-03-01T14:46:09.974Z |
match_str | shabanov2005subpixelburndetectioninmoderateresolutionimagingspectroradiometer500mdatawithartmapneuralnetworks |
mega_collection | American Geophysical Union (AGU) (CrossRef) |
physical | |
publishDate | 2005 |
publishDateSort | 2005 |
publisher | American Geophysical Union (AGU) |
record_format | ai |
recordtype | ai |
series | Journal of Geophysical Research: Atmospheres |
source_id | 49 |
spelling | Shabanov, N. V. Lo, K. Gopal, S. Myneni, R. B. 0148-0227 American Geophysical Union (AGU) Paleontology Space and Planetary Science Earth and Planetary Sciences (miscellaneous) Atmospheric Science Earth-Surface Processes Geochemistry and Petrology Soil Science Water Science and Technology Ecology Aquatic Science Forestry Oceanography Geophysics http://dx.doi.org/10.1029/2004jd005257 <jats:p>This paper presents an ARTMAP neural network approach for burn detection in Moderate Resolution Imaging Spectroradiometer (MODIS) data using two methods: discrete and continuous classifications. The study area covers the states of Idaho and Montana in the United States, where extensive fire events took place during the months of July and August in the year 2000. The proposed approach differs from commonly used change detection schemes by utilizing a single surface reflectance image instead of time series of satellite data. Burn detection in this study was accomplished by the classification of land into four classes: burns, woody vegetation, herbaceous vegetation, and barren. We performed the discrete classification of coarse (500‐m MODIS data) and high‐resolution (30‐m Enhanced Thematic Mapper (ETM+) data) surface reflectance data with an ARTMAP classifier to evaluate the impact of a land cover mixture on burn detection. The analysis of classification results reveals commission and omission errors in the evaluation of burn area extent at a coarse‐resolution scale. To account for land cover heterogeneity, we utilized the continuous classification of coarse‐resolution data with an ARTMAP mixture model. A training data set on the land cover mixture at 500‐m scale of MODIS data was assembled from the aggregated 30‐m ETM+ classification. The ARTMAP mixture model was trained with MODIS surface reflectance data and land cover mixture information to generate a continuous classification of burns (expressed in percentage of burns per pixel). Data fusion of coarse‐ and high‐resolution satellite data in this study resulted in a more natural and accurate mapping of burns as mixtures with other land cover types.</jats:p> Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks Journal of Geophysical Research: Atmospheres |
spellingShingle | Shabanov, N. V., Lo, K., Gopal, S., Myneni, R. B., Journal of Geophysical Research: Atmospheres, Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks, Paleontology, Space and Planetary Science, Earth and Planetary Sciences (miscellaneous), Atmospheric Science, Earth-Surface Processes, Geochemistry and Petrology, Soil Science, Water Science and Technology, Ecology, Aquatic Science, Forestry, Oceanography, Geophysics |
title | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_full | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_fullStr | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_full_unstemmed | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_short | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
title_sort | subpixel burn detection in moderate resolution imaging spectroradiometer 500‐m data with artmap neural networks |
title_unstemmed | Subpixel burn detection in Moderate Resolution Imaging Spectroradiometer 500‐m data with ARTMAP neural networks |
topic | Paleontology, Space and Planetary Science, Earth and Planetary Sciences (miscellaneous), Atmospheric Science, Earth-Surface Processes, Geochemistry and Petrology, Soil Science, Water Science and Technology, Ecology, Aquatic Science, Forestry, Oceanography, Geophysics |
url | http://dx.doi.org/10.1029/2004jd005257 |