Deep Neural Networks for Aerosol Optical Depth Retrieval
Aerosol Optical Depth (AOD) is a measure of the extinction of solar radiation by aerosols in the atmosphere. Understanding the variations of global AOD is necessary for precisely determining the role of aerosols. Arctic warming is partially caused by aerosols transported from vast distances, includi...
Published in: | Atmosphere |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/atmos13010101 https://doaj.org/article/5a9739e4e466485cb8f96accfe7577f6 |
id |
ftdoajarticles:oai:doaj.org/article:5a9739e4e466485cb8f96accfe7577f6 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:5a9739e4e466485cb8f96accfe7577f6 2023-05-15T14:57:48+02:00 Deep Neural Networks for Aerosol Optical Depth Retrieval Renee Zbizika Paulina Pakszys Tymon Zielinski 2022-01-01T00:00:00Z https://doi.org/10.3390/atmos13010101 https://doaj.org/article/5a9739e4e466485cb8f96accfe7577f6 EN eng MDPI AG https://www.mdpi.com/2073-4433/13/1/101 https://doaj.org/toc/2073-4433 doi:10.3390/atmos13010101 2073-4433 https://doaj.org/article/5a9739e4e466485cb8f96accfe7577f6 Atmosphere, Vol 13, Iss 101, p 101 (2022) aerosol optical depth arctic atmosphere deep neural network maritime aerosol network biomass burning event Meteorology. Climatology QC851-999 article 2022 ftdoajarticles https://doi.org/10.3390/atmos13010101 2022-12-31T14:47:21Z Aerosol Optical Depth (AOD) is a measure of the extinction of solar radiation by aerosols in the atmosphere. Understanding the variations of global AOD is necessary for precisely determining the role of aerosols. Arctic warming is partially caused by aerosols transported from vast distances, including those released during biomass burning events (BBEs). However, measuring AODs is challenging, typically requiring active LIDAR systems or passive sun photometers. Both are limited to cloud-free conditions; sun photometers provide only point measurements, thus requiring more spatial coverage. A more viable method to obtain accurate AOD may be found through machine learning. This study uses DNNs to estimate Svalbard’s AODs using a minimal set of meteorological parameters (temperature, air mass, water vapor, wind speed, latitude, longitude, and time of year). The mean absolute error (MAE) between predicted and true data was 0.00401 for the entire set and 0.0079 for the validation set. It was then shown that the inclusion of BBE data improves predictions by 42.167%. It was demonstrated that AODs may be accurately estimated without the use of expensive instrumentation, using machine learning and minimal data. Similar models may be developed for other regions, allowing immediate improvement of current meteorological models. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic Atmosphere 13 1 101 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
aerosol optical depth arctic atmosphere deep neural network maritime aerosol network biomass burning event Meteorology. Climatology QC851-999 |
spellingShingle |
aerosol optical depth arctic atmosphere deep neural network maritime aerosol network biomass burning event Meteorology. Climatology QC851-999 Renee Zbizika Paulina Pakszys Tymon Zielinski Deep Neural Networks for Aerosol Optical Depth Retrieval |
topic_facet |
aerosol optical depth arctic atmosphere deep neural network maritime aerosol network biomass burning event Meteorology. Climatology QC851-999 |
description |
Aerosol Optical Depth (AOD) is a measure of the extinction of solar radiation by aerosols in the atmosphere. Understanding the variations of global AOD is necessary for precisely determining the role of aerosols. Arctic warming is partially caused by aerosols transported from vast distances, including those released during biomass burning events (BBEs). However, measuring AODs is challenging, typically requiring active LIDAR systems or passive sun photometers. Both are limited to cloud-free conditions; sun photometers provide only point measurements, thus requiring more spatial coverage. A more viable method to obtain accurate AOD may be found through machine learning. This study uses DNNs to estimate Svalbard’s AODs using a minimal set of meteorological parameters (temperature, air mass, water vapor, wind speed, latitude, longitude, and time of year). The mean absolute error (MAE) between predicted and true data was 0.00401 for the entire set and 0.0079 for the validation set. It was then shown that the inclusion of BBE data improves predictions by 42.167%. It was demonstrated that AODs may be accurately estimated without the use of expensive instrumentation, using machine learning and minimal data. Similar models may be developed for other regions, allowing immediate improvement of current meteorological models. |
format |
Article in Journal/Newspaper |
author |
Renee Zbizika Paulina Pakszys Tymon Zielinski |
author_facet |
Renee Zbizika Paulina Pakszys Tymon Zielinski |
author_sort |
Renee Zbizika |
title |
Deep Neural Networks for Aerosol Optical Depth Retrieval |
title_short |
Deep Neural Networks for Aerosol Optical Depth Retrieval |
title_full |
Deep Neural Networks for Aerosol Optical Depth Retrieval |
title_fullStr |
Deep Neural Networks for Aerosol Optical Depth Retrieval |
title_full_unstemmed |
Deep Neural Networks for Aerosol Optical Depth Retrieval |
title_sort |
deep neural networks for aerosol optical depth retrieval |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/atmos13010101 https://doaj.org/article/5a9739e4e466485cb8f96accfe7577f6 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
Atmosphere, Vol 13, Iss 101, p 101 (2022) |
op_relation |
https://www.mdpi.com/2073-4433/13/1/101 https://doaj.org/toc/2073-4433 doi:10.3390/atmos13010101 2073-4433 https://doaj.org/article/5a9739e4e466485cb8f96accfe7577f6 |
op_doi |
https://doi.org/10.3390/atmos13010101 |
container_title |
Atmosphere |
container_volume |
13 |
container_issue |
1 |
container_start_page |
101 |
_version_ |
1766329911680696320 |