Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model
The spatial coverage of satellite aerosol classification was improved using a random forest (RF) model trained with observational data including target (aerosol type) and input (satellite measurement) variables. The AErosol RObotic NETwork (AERONET) aerosol-type dataset was used for the target varia...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13071268 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/13/7/1268/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/13/7/1268/ 2023-08-20T03:59:10+02:00 Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model Wonei Choi Hanlim Lee Daewon Kim Serin Kim 2021-03-26 application/pdf https://doi.org/10.3390/rs13071268 EN eng Multidisciplinary Digital Publishing Institute Atmospheric Remote Sensing https://dx.doi.org/10.3390/rs13071268 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 13; Issue 7; Pages: 1268 aerosol classification aerosol remote sensing space-borne remote sensing aerosol type machine learning TROPOMI MODIS AERONET AOD Text 2021 ftmdpi https://doi.org/10.3390/rs13071268 2023-08-01T01:22:24Z The spatial coverage of satellite aerosol classification was improved using a random forest (RF) model trained with observational data including target (aerosol type) and input (satellite measurement) variables. The AErosol RObotic NETwork (AERONET) aerosol-type dataset was used for the target variables. Satellite input variables with many missing data or low mean-decrease accuracy were excluded from the final input variable set, and good performance in aerosol-type classification was achieved. The performance of the RF-based model was evaluated on the basis of the wavelength dependence of single-scattering albedo (SSA) and fine-mode-fraction values from AERONET. Typical SSA wavelength dependence for individual aerosol types was consistent with that obtained for aerosol types by the RF-based model. The spatial coverage of the RF-based model was also compared with that of previously developed models in a global-scale case study. The study demonstrates that the RF-based model allows satellite aerosol classification with improved spatial coverage, with a performance similar to that of previously developed models. Text Aerosol Robotic Network MDPI Open Access Publishing Remote Sensing 13 7 1268 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
aerosol classification aerosol remote sensing space-borne remote sensing aerosol type machine learning TROPOMI MODIS AERONET AOD |
spellingShingle |
aerosol classification aerosol remote sensing space-borne remote sensing aerosol type machine learning TROPOMI MODIS AERONET AOD Wonei Choi Hanlim Lee Daewon Kim Serin Kim Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
topic_facet |
aerosol classification aerosol remote sensing space-borne remote sensing aerosol type machine learning TROPOMI MODIS AERONET AOD |
description |
The spatial coverage of satellite aerosol classification was improved using a random forest (RF) model trained with observational data including target (aerosol type) and input (satellite measurement) variables. The AErosol RObotic NETwork (AERONET) aerosol-type dataset was used for the target variables. Satellite input variables with many missing data or low mean-decrease accuracy were excluded from the final input variable set, and good performance in aerosol-type classification was achieved. The performance of the RF-based model was evaluated on the basis of the wavelength dependence of single-scattering albedo (SSA) and fine-mode-fraction values from AERONET. Typical SSA wavelength dependence for individual aerosol types was consistent with that obtained for aerosol types by the RF-based model. The spatial coverage of the RF-based model was also compared with that of previously developed models in a global-scale case study. The study demonstrates that the RF-based model allows satellite aerosol classification with improved spatial coverage, with a performance similar to that of previously developed models. |
format |
Text |
author |
Wonei Choi Hanlim Lee Daewon Kim Serin Kim |
author_facet |
Wonei Choi Hanlim Lee Daewon Kim Serin Kim |
author_sort |
Wonei Choi |
title |
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
title_short |
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
title_full |
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
title_fullStr |
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
title_full_unstemmed |
Improving Spatial Coverage of Satellite Aerosol Classification Using a Random Forest Model |
title_sort |
improving spatial coverage of satellite aerosol classification using a random forest model |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13071268 |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_source |
Remote Sensing; Volume 13; Issue 7; Pages: 1268 |
op_relation |
Atmospheric Remote Sensing https://dx.doi.org/10.3390/rs13071268 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs13071268 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
7 |
container_start_page |
1268 |
_version_ |
1774717621125513216 |