Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table
In order to have a good estimate of the current forcing by anthropogenic aerosols, knowledge on past aerosol levels is needed. Aerosol optical depth (AOD) is a good measure for aerosol loading. However, dedicated measurements of AOD are only available from the 1990s onward. One option to lengthen th...
Published in: | Atmospheric Chemistry and Physics |
---|---|
Main Authors: | , , , , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2016
|
Subjects: | |
Online Access: | https://doi.org/10.5194/acp-16-8181-2016 https://doaj.org/article/8f1cba09a131486bb8db71c488645c43 |
id |
ftdoajarticles:oai:doaj.org/article:8f1cba09a131486bb8db71c488645c43 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:8f1cba09a131486bb8db71c488645c43 2023-05-15T13:07:10+02:00 Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table J. Huttunen H. Kokkola T. Mielonen M. E. J. Mononen A. Lipponen J. Reunanen A. V. Lindfors S. Mikkonen K. E. J. Lehtinen N. Kouremeti A. Bais H. Niska A. Arola 2016-07-01T00:00:00Z https://doi.org/10.5194/acp-16-8181-2016 https://doaj.org/article/8f1cba09a131486bb8db71c488645c43 EN eng Copernicus Publications https://www.atmos-chem-phys.net/16/8181/2016/acp-16-8181-2016.pdf https://doaj.org/toc/1680-7316 https://doaj.org/toc/1680-7324 doi:10.5194/acp-16-8181-2016 1680-7316 1680-7324 https://doaj.org/article/8f1cba09a131486bb8db71c488645c43 Atmospheric Chemistry and Physics, Vol 16, Pp 8181-8191 (2016) Physics QC1-999 Chemistry QD1-999 article 2016 ftdoajarticles https://doi.org/10.5194/acp-16-8181-2016 2022-12-31T04:42:35Z In order to have a good estimate of the current forcing by anthropogenic aerosols, knowledge on past aerosol levels is needed. Aerosol optical depth (AOD) is a good measure for aerosol loading. However, dedicated measurements of AOD are only available from the 1990s onward. One option to lengthen the AOD time series beyond the 1990s is to retrieve AOD from surface solar radiation (SSR) measurements taken with pyranometers. In this work, we have evaluated several inversion methods designed for this task. We compared a look-up table method based on radiative transfer modelling, a non-linear regression method and four machine learning methods (Gaussian process, neural network, random forest and support vector machine) with AOD observations carried out with a sun photometer at an Aerosol Robotic Network (AERONET) site in Thessaloniki, Greece. Our results show that most of the machine learning methods produce AOD estimates comparable to the look-up table and non-linear regression methods. All of the applied methods produced AOD values that corresponded well to the AERONET observations with the lowest correlation coefficient value being 0.87 for the random forest method. While many of the methods tended to slightly overestimate low AODs and underestimate high AODs, neural network and support vector machine showed overall better correspondence for the whole AOD range. The differences in producing both ends of the AOD range seem to be caused by differences in the aerosol composition. High AODs were in most cases those with high water vapour content which might affect the aerosol single scattering albedo (SSA) through uptake of water into aerosols. Our study indicates that machine learning methods benefit from the fact that they do not constrain the aerosol SSA in the retrieval, whereas the LUT method assumes a constant value for it. This would also mean that machine learning methods could have potential in reproducing AOD from SSR even though SSA would have changed during the observation period. Article in Journal/Newspaper Aerosol Robotic Network Directory of Open Access Journals: DOAJ Articles Atmospheric Chemistry and Physics 16 13 8181 8191 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Physics QC1-999 Chemistry QD1-999 |
spellingShingle |
Physics QC1-999 Chemistry QD1-999 J. Huttunen H. Kokkola T. Mielonen M. E. J. Mononen A. Lipponen J. Reunanen A. V. Lindfors S. Mikkonen K. E. J. Lehtinen N. Kouremeti A. Bais H. Niska A. Arola Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
topic_facet |
Physics QC1-999 Chemistry QD1-999 |
description |
In order to have a good estimate of the current forcing by anthropogenic aerosols, knowledge on past aerosol levels is needed. Aerosol optical depth (AOD) is a good measure for aerosol loading. However, dedicated measurements of AOD are only available from the 1990s onward. One option to lengthen the AOD time series beyond the 1990s is to retrieve AOD from surface solar radiation (SSR) measurements taken with pyranometers. In this work, we have evaluated several inversion methods designed for this task. We compared a look-up table method based on radiative transfer modelling, a non-linear regression method and four machine learning methods (Gaussian process, neural network, random forest and support vector machine) with AOD observations carried out with a sun photometer at an Aerosol Robotic Network (AERONET) site in Thessaloniki, Greece. Our results show that most of the machine learning methods produce AOD estimates comparable to the look-up table and non-linear regression methods. All of the applied methods produced AOD values that corresponded well to the AERONET observations with the lowest correlation coefficient value being 0.87 for the random forest method. While many of the methods tended to slightly overestimate low AODs and underestimate high AODs, neural network and support vector machine showed overall better correspondence for the whole AOD range. The differences in producing both ends of the AOD range seem to be caused by differences in the aerosol composition. High AODs were in most cases those with high water vapour content which might affect the aerosol single scattering albedo (SSA) through uptake of water into aerosols. Our study indicates that machine learning methods benefit from the fact that they do not constrain the aerosol SSA in the retrieval, whereas the LUT method assumes a constant value for it. This would also mean that machine learning methods could have potential in reproducing AOD from SSR even though SSA would have changed during the observation period. |
format |
Article in Journal/Newspaper |
author |
J. Huttunen H. Kokkola T. Mielonen M. E. J. Mononen A. Lipponen J. Reunanen A. V. Lindfors S. Mikkonen K. E. J. Lehtinen N. Kouremeti A. Bais H. Niska A. Arola |
author_facet |
J. Huttunen H. Kokkola T. Mielonen M. E. J. Mononen A. Lipponen J. Reunanen A. V. Lindfors S. Mikkonen K. E. J. Lehtinen N. Kouremeti A. Bais H. Niska A. Arola |
author_sort |
J. Huttunen |
title |
Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
title_short |
Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
title_full |
Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
title_fullStr |
Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
title_full_unstemmed |
Retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
title_sort |
retrieval of aerosol optical depth from surface solar radiation measurements using machine learning algorithms, non-linear regression and a radiative transfer-based look-up table |
publisher |
Copernicus Publications |
publishDate |
2016 |
url |
https://doi.org/10.5194/acp-16-8181-2016 https://doaj.org/article/8f1cba09a131486bb8db71c488645c43 |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_source |
Atmospheric Chemistry and Physics, Vol 16, Pp 8181-8191 (2016) |
op_relation |
https://www.atmos-chem-phys.net/16/8181/2016/acp-16-8181-2016.pdf https://doaj.org/toc/1680-7316 https://doaj.org/toc/1680-7324 doi:10.5194/acp-16-8181-2016 1680-7316 1680-7324 https://doaj.org/article/8f1cba09a131486bb8db71c488645c43 |
op_doi |
https://doi.org/10.5194/acp-16-8181-2016 |
container_title |
Atmospheric Chemistry and Physics |
container_volume |
16 |
container_issue |
13 |
container_start_page |
8181 |
op_container_end_page |
8191 |
_version_ |
1766038184643264512 |