An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters
Satellite remote sensing of PM 2.5 (fine particulate matter) mass concentration has become one of the most popular atmospheric research aspects, resulting in the development of different models. Among them, the semi-empirical physical approach constructs the transformation relationship between the a...
Published in: | Geoscientific Model Development |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/gmd-16-4137-2023 https://gmd.copernicus.org/articles/16/4137/2023/ |
id |
ftcopernicus:oai:publications.copernicus.org:gmd106556 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:gmd106556 2023-08-20T03:59:12+02:00 An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters Jin, Caiyi Yuan, Qiangqiang Li, Tongwen Wang, Yuan Zhang, Liangpei 2023-07-24 application/pdf https://doi.org/10.5194/gmd-16-4137-2023 https://gmd.copernicus.org/articles/16/4137/2023/ eng eng doi:10.5194/gmd-16-4137-2023 https://gmd.copernicus.org/articles/16/4137/2023/ eISSN: 1991-9603 Text 2023 ftcopernicus https://doi.org/10.5194/gmd-16-4137-2023 2023-07-31T16:24:18Z Satellite remote sensing of PM 2.5 (fine particulate matter) mass concentration has become one of the most popular atmospheric research aspects, resulting in the development of different models. Among them, the semi-empirical physical approach constructs the transformation relationship between the aerosol optical depth (AOD) and PM 2.5 based on the optical properties of particles, which has strong physical significance. Also, it performs the PM 2.5 retrieval independently of the ground stations. However, due to the complex physical relationship, the physical parameters in the semi-empirical approach are difficult to calculate accurately, resulting in relatively limited accuracy. To achieve the optimization effect, this study proposes a method of embedding machine learning into a semi-physical empirical model (RF-PMRS). Specifically, based on the theory of the physical PM 2.5 remote sensing (PMRS) approach, the complex parameter (VE f , a columnar volume-to-extinction ratio of fine particles) is simulated by the random forest (RF) model. Also, a fine-mode fraction product with higher quality is applied to make up for the insufficient coverage of satellite products. Experiments in North China (35 ∘ –45 ∘ N, 110 ∘ –120 ∘ E) show that the surface PM 2.5 concentration derived by RF-PMRS has an average annual value of 57.92 µ g m −3 vs. the ground value of 60.23 µ g m −3 . Compared with the original method, RMSE decreases by 39.95 µ g m −3 , and the relative deviation is reduced by 44.87 %. Moreover, validation at two Aerosol Robotic Network (AERONET) sites presents a time series change closer to the true values, with an R of about 0.80. This study is also a preliminary attempt to combine model-driven and data-driven models, laying the foundation for further atmospheric research on optimization methods. Text Aerosol Robotic Network Copernicus Publications: E-Journals Geoscientific Model Development 16 14 4137 4154 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Satellite remote sensing of PM 2.5 (fine particulate matter) mass concentration has become one of the most popular atmospheric research aspects, resulting in the development of different models. Among them, the semi-empirical physical approach constructs the transformation relationship between the aerosol optical depth (AOD) and PM 2.5 based on the optical properties of particles, which has strong physical significance. Also, it performs the PM 2.5 retrieval independently of the ground stations. However, due to the complex physical relationship, the physical parameters in the semi-empirical approach are difficult to calculate accurately, resulting in relatively limited accuracy. To achieve the optimization effect, this study proposes a method of embedding machine learning into a semi-physical empirical model (RF-PMRS). Specifically, based on the theory of the physical PM 2.5 remote sensing (PMRS) approach, the complex parameter (VE f , a columnar volume-to-extinction ratio of fine particles) is simulated by the random forest (RF) model. Also, a fine-mode fraction product with higher quality is applied to make up for the insufficient coverage of satellite products. Experiments in North China (35 ∘ –45 ∘ N, 110 ∘ –120 ∘ E) show that the surface PM 2.5 concentration derived by RF-PMRS has an average annual value of 57.92 µ g m −3 vs. the ground value of 60.23 µ g m −3 . Compared with the original method, RMSE decreases by 39.95 µ g m −3 , and the relative deviation is reduced by 44.87 %. Moreover, validation at two Aerosol Robotic Network (AERONET) sites presents a time series change closer to the true values, with an R of about 0.80. This study is also a preliminary attempt to combine model-driven and data-driven models, laying the foundation for further atmospheric research on optimization methods. |
format |
Text |
author |
Jin, Caiyi Yuan, Qiangqiang Li, Tongwen Wang, Yuan Zhang, Liangpei |
spellingShingle |
Jin, Caiyi Yuan, Qiangqiang Li, Tongwen Wang, Yuan Zhang, Liangpei An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
author_facet |
Jin, Caiyi Yuan, Qiangqiang Li, Tongwen Wang, Yuan Zhang, Liangpei |
author_sort |
Jin, Caiyi |
title |
An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
title_short |
An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
title_full |
An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
title_fullStr |
An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
title_full_unstemmed |
An optimized semi-empirical physical approach for satellite-based PM2.5 retrieval: embedding machine learning to simulate complex physical parameters |
title_sort |
optimized semi-empirical physical approach for satellite-based pm2.5 retrieval: embedding machine learning to simulate complex physical parameters |
publishDate |
2023 |
url |
https://doi.org/10.5194/gmd-16-4137-2023 https://gmd.copernicus.org/articles/16/4137/2023/ |
genre |
Aerosol Robotic Network |
genre_facet |
Aerosol Robotic Network |
op_source |
eISSN: 1991-9603 |
op_relation |
doi:10.5194/gmd-16-4137-2023 https://gmd.copernicus.org/articles/16/4137/2023/ |
op_doi |
https://doi.org/10.5194/gmd-16-4137-2023 |
container_title |
Geoscientific Model Development |
container_volume |
16 |
container_issue |
14 |
container_start_page |
4137 |
op_container_end_page |
4154 |
_version_ |
1774720051686932480 |