Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning
Quantitative measurements of aerosol absorptive properties, e.g., the absorbing aerosol optical depth (AAOD) and the single scattering albedo (SSA), are important to reduce uncertainties of aerosol climate radiative forcing assessments. Currently, global retrievals of AAOD and SSA are mainly provide...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Other Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1109/JSTARS.2021.3108669 |
id |
ftncar:oai:drupal-site.org:articles_24793 |
---|---|
record_format |
openpolar |
spelling |
ftncar:oai:drupal-site.org:articles_24793 2024-04-28T07:53:23+00:00 Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning Sun, Jiyunting (author) Veefkind, Pepijn (author) van Velthoven, Peter (author) Levelt, Pieternel F. (author) 2021-08-30 https://doi.org/10.1109/JSTARS.2021.3108669 en eng IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing--IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing--1939-1404--2151-1535 articles:24793 doi:10.1109/JSTARS.2021.3108669 ark:/85065/d7n01b0j Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. article Text 2021 ftncar https://doi.org/10.1109/JSTARS.2021.3108669 2024-04-04T17:33:50Z Quantitative measurements of aerosol absorptive properties, e.g., the absorbing aerosol optical depth (AAOD) and the single scattering albedo (SSA), are important to reduce uncertainties of aerosol climate radiative forcing assessments. Currently, global retrievals of AAOD and SSA are mainly provided by the ground-based aerosol robotic network (AERONET), whereas it is still challenging to retrieve them from space. However, we found the AERONET AAOD has a relatively strong correlation with the satellite retrieved ultra-violet aerosol index (UVAI). Based on this, a numerical relation is built by a deep neural network (DNN) to predict global AAOD and SSA over land from the long-term UVAI record (2006-2019) provided by the ozone monitoring instrument (OMI) onboard Aura. The DNN predicted aerosol absorption is satisfying for samples with AOD at 550 nm larger than 0.1, and the DNN model performance is better for smaller absorbing aerosols (e.g., smoke) than larger ones (e.g., mineral dust). The comparison of the DNN predictions with AERONET shows a high correlation coefficient of 0.90 and a root mean square of 0.005 for the AAOD, and over 80% of samples are within the expected uncertainty of AERONET SSA (+/- 0.03). Article in Journal/Newspaper Aerosol Robotic Network OpenSky (NCAR/UCAR - National Center for Atmospheric Research/University Corporation for Atmospheric Research) IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 9692 9710 |
institution |
Open Polar |
collection |
OpenSky (NCAR/UCAR - National Center for Atmospheric Research/University Corporation for Atmospheric Research) |
op_collection_id |
ftncar |
language |
English |
description |
Quantitative measurements of aerosol absorptive properties, e.g., the absorbing aerosol optical depth (AAOD) and the single scattering albedo (SSA), are important to reduce uncertainties of aerosol climate radiative forcing assessments. Currently, global retrievals of AAOD and SSA are mainly provided by the ground-based aerosol robotic network (AERONET), whereas it is still challenging to retrieve them from space. However, we found the AERONET AAOD has a relatively strong correlation with the satellite retrieved ultra-violet aerosol index (UVAI). Based on this, a numerical relation is built by a deep neural network (DNN) to predict global AAOD and SSA over land from the long-term UVAI record (2006-2019) provided by the ozone monitoring instrument (OMI) onboard Aura. The DNN predicted aerosol absorption is satisfying for samples with AOD at 550 nm larger than 0.1, and the DNN model performance is better for smaller absorbing aerosols (e.g., smoke) than larger ones (e.g., mineral dust). The comparison of the DNN predictions with AERONET shows a high correlation coefficient of 0.90 and a root mean square of 0.005 for the AAOD, and over 80% of samples are within the expected uncertainty of AERONET SSA (+/- 0.03). |
author2 |
Sun, Jiyunting (author) Veefkind, Pepijn (author) van Velthoven, Peter (author) Levelt, Pieternel F. (author) |
format |
Article in Journal/Newspaper |
title |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
spellingShingle |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
title_short |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
title_full |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
title_fullStr |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
title_full_unstemmed |
Aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
title_sort |
aerosol absorption over land derived from the ultra-violet aerosol index by deep learning |
publishDate |
2021 |
url |
https://doi.org/10.1109/JSTARS.2021.3108669 |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_relation |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing--IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing--1939-1404--2151-1535 articles:24793 doi:10.1109/JSTARS.2021.3108669 ark:/85065/d7n01b0j |
op_rights |
Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
op_doi |
https://doi.org/10.1109/JSTARS.2021.3108669 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
14 |
container_start_page |
9692 |
op_container_end_page |
9710 |
_version_ |
1797568013879214080 |