Articles | Volume 15, issue 18
https://doi.org/10.5194/amt-15-5497-2022
https://doi.org/10.5194/amt-15-5497-2022
Research article
 | 
27 Sep 2022
Research article |  | 27 Sep 2022

A new machine-learning-based analysis for improving satellite-retrieved atmospheric composition data: OMI SO2 as an example

Can Li, Joanna Joiner, Fei Liu, Nickolay A. Krotkov, Vitali Fioletov, and Chris McLinden

Related authors

Opinion: Beyond global means – novel space-based approaches to indirectly constrain the concentrations of and trends and variations in the tropospheric hydroxyl radical (OH)
Bryan N. Duncan, Daniel C. Anderson, Arlene M. Fiore, Joanna Joiner, Nickolay A. Krotkov, Can Li, Dylan B. Millet, Julie M. Nicely, Luke D. Oman, Jason M. St. Clair, Joshua D. Shutter, Amir H. Souri, Sarah A. Strode, Brad Weir, Glenn M. Wolfe, Helen M. Worden, and Qindan Zhu
Atmos. Chem. Phys., 24, 13001–13023, https://doi.org/10.5194/acp-24-13001-2024,https://doi.org/10.5194/acp-24-13001-2024, 2024
Short summary
Version 1 NOAA-20/OMPS Nadir Mapper total column SO2 product: continuation of NASA long-term global data record
Can Li, Nickolay A. Krotkov, Joanna Joiner, Vitali Fioletov, Chris McLinden, Debora Griffin, Peter J. T. Leonard, Simon Carn, Colin Seftor, and Alexander Vasilkov
Earth Syst. Sci. Data, 16, 4291–4309, https://doi.org/10.5194/essd-16-4291-2024,https://doi.org/10.5194/essd-16-4291-2024, 2024
Short summary
Estimation of anthropogenic and volcanic SO2 emissions from satellite data in the presence of snow/ice on the ground
Vitali E. Fioletov, Chris A. McLinden, Debora Griffin, Nickolay A. Krotkov, Can Li, Joanna Joiner, Nicolas Theys, and Simon Carn
Atmos. Meas. Tech., 16, 5575–5592, https://doi.org/10.5194/amt-16-5575-2023,https://doi.org/10.5194/amt-16-5575-2023, 2023
Short summary
Use of machine learning and principal component analysis to retrieve nitrogen dioxide (NO2) with hyperspectral imagers and reduce noise in spectral fitting
Joanna Joiner, Sergey Marchenko, Zachary Fasnacht, Lok Lamsal, Can Li, Alexander Vasilkov, and Nickolay Krotkov
Atmos. Meas. Tech., 16, 481–500, https://doi.org/10.5194/amt-16-481-2023,https://doi.org/10.5194/amt-16-481-2023, 2023
Short summary
Ground-level gaseous pollutants (NO2, SO2, and CO) in China: daily seamless mapping and spatiotemporal variations
Jing Wei, Zhanqing Li, Jun Wang, Can Li, Pawan Gupta, and Maureen Cribb
Atmos. Chem. Phys., 23, 1511–1532, https://doi.org/10.5194/acp-23-1511-2023,https://doi.org/10.5194/acp-23-1511-2023, 2023
Short summary

Related subject area

Subject: Gases | Technique: Remote Sensing | Topic: Data Processing and Information Retrieval
The differences between remote sensing and in situ air pollutant measurements over the Canadian oil sands
Xiaoyi Zhao, Vitali Fioletov, Debora Griffin, Chris McLinden, Ralf Staebler, Cristian Mihele, Kevin Strawbridge, Jonathan Davies, Ihab Abboud, Sum Chi Lee, Alexander Cede, Martin Tiefengraber, and Robert Swap
Atmos. Meas. Tech., 17, 6889–6912, https://doi.org/10.5194/amt-17-6889-2024,https://doi.org/10.5194/amt-17-6889-2024, 2024
Short summary
NitroNet – a machine learning model for the prediction of tropospheric NO2 profiles from TROPOMI observations
Leon Kuhn, Steffen Beirle, Sergey Osipov, Andrea Pozzer, and Thomas Wagner
Atmos. Meas. Tech., 17, 6485–6516, https://doi.org/10.5194/amt-17-6485-2024,https://doi.org/10.5194/amt-17-6485-2024, 2024
Short summary
Improved convective cloud differential (CCD) tropospheric ozone from S5P-TROPOMI satellite data using local cloud fields
Swathi Maratt Satheesan, Kai-Uwe Eichmann, John P. Burrows, Mark Weber, Ryan Stauffer, Anne M. Thompson, and Debra Kollonige
Atmos. Meas. Tech., 17, 6459–6484, https://doi.org/10.5194/amt-17-6459-2024,https://doi.org/10.5194/amt-17-6459-2024, 2024
Short summary
Atmospheric propane (C3H8) column retrievals from ground-based FTIR observations in Xianghe, China
Minqiang Zhou, Pucai Wang, Bart Dils, Bavo Langerock, Geoff Toon, Christian Hermans, Weidong Nan, Qun Cheng, and Martine De Mazière
Atmos. Meas. Tech., 17, 6385–6396, https://doi.org/10.5194/amt-17-6385-2024,https://doi.org/10.5194/amt-17-6385-2024, 2024
Short summary
Can the remote sensing of combustion phase improve estimates of landscape fire smoke emission rate and composition?
Farrer Owsley-Brown, Martin J. Wooster, Mark J. Grosvenor, and Yanan Liu
Atmos. Meas. Tech., 17, 6247–6264, https://doi.org/10.5194/amt-17-6247-2024,https://doi.org/10.5194/amt-17-6247-2024, 2024
Short summary

Cited articles

Bhartia, P. K.: OMI/Aura Ozone (O3) Total Column 1-Orbit L2 Swath 13x24 km V003, Goddard Earth Sciences Data and Information Services Center (GES DISC) [data set], Greenbelt, MD, USA, https://doi.org/10.5067/Aura/OMI/DATA2024, 2005. 
Castellanos, P. and da Silva, A.: A neural network correction to the scalar approximation in radiative transfer, J. Atmos. Ocean. Tech., 36, 819–832, https://doi.org/10.1175/JTECH-D-18-0003.1, 2019. 
Chan, K. L., Khorsandi, E., Liu, S., Baier, F., and Valks, P.: Estimation of surface NO2 concentrations over Germany from TROPOMI satellite observations using a machine learning method, Remote Sens., 13, 969, https://doi.org/10.3390/rs13050969, 2021. 
Chimot, J., Veefkind, J. P., Vlemmix, T., de Haan, J. F., Amiridis, V., Proestakis, E., Marinou, E., and Levelt, P. F.: An exploratory study on the aerosol height retrieval from OMI measurements of the 477 nm O2 – O2 spectral band using a neural network approach, Atmos. Meas. Tech., 10, 783–809, https://doi.org/10.5194/amt-10-783-2017, 2017. 
De Santis, D., Petracca, I., Corradini, S., Guerrieri, L., Picchiani, M., Merucci, L., Stelitano, D., Del Frate, F., Prata, F., and Schiavon, G.: Volcanic SO2 near-real time retrieval using TROPOMI data and neural networks: The December 2018 Etna test case, 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 12–16 July 2021, 8480–8483, https://doi.org/10.1109/IGARSS47720.2021.9554915, 2021. 
Download
Short summary
Satellite observations provide information on the sources of SO2, an important pollutant that affects both air quality and climate. However, these observations suffer from relatively poor data quality due to weak signals of SO2. Here, we use a machine learning technique to analyze satellite SO2 observations in order to reduce the noise and artifacts over relatively clean areas while keeping the signals near pollution sources. This leads to significant improvement in satellite SO2 data.