Articles | Volume 17, issue 21
https://doi.org/10.5194/amt-17-6485-2024
https://doi.org/10.5194/amt-17-6485-2024
Research article
 | 
13 Nov 2024
Research article |  | 13 Nov 2024

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

Related authors

Validation of GEMS tropospheric NO2 columns and their diurnal variation with ground-based DOAS measurements
Kezia Lange, Andreas Richter, Tim Bösch, Bianca Zilker, Miriam Latsch, Lisa K. Behrens, Chisom M. Okafor, Hartmut Bösch, John P. Burrows, Alexis Merlaud, Gaia Pinardi, Caroline Fayt, Martina M. Friedrich, Ermioni Dimitropoulou, Michel Van Roozendael, Steffen Ziegler, Simona Ripperger-Lukosiunaite, Leon Kuhn, Bianca Lauster, Thomas Wagner, Hyunkee Hong, Donghee Kim, Lim-Seok Chang, Kangho Bae, Chang-Keun Song, Jong-Uk Park, and Hanlim Lee
Atmos. Meas. Tech., 17, 6315–6344, https://doi.org/10.5194/amt-17-6315-2024,https://doi.org/10.5194/amt-17-6315-2024, 2024
Short summary
On the influence of vertical mixing, boundary layer schemes, and temporal emission profiles on tropospheric NO2 in WRF-Chem – comparisons to in situ, satellite, and MAX-DOAS observations
Leon Kuhn, Steffen Beirle, Vinod Kumar, Sergey Osipov, Andrea Pozzer, Tim Bösch, Rajesh Kumar, and Thomas Wagner
Atmos. Chem. Phys., 24, 185–217, https://doi.org/10.5194/acp-24-185-2024,https://doi.org/10.5194/acp-24-185-2024, 2024
Short summary
The NO2 camera based on gas correlation spectroscopy
Leon Kuhn, Jonas Kuhn, Thomas Wagner, and Ulrich Platt
Atmos. Meas. Tech., 15, 1395–1414, https://doi.org/10.5194/amt-15-1395-2022,https://doi.org/10.5194/amt-15-1395-2022, 2022
Short summary

Related subject area

Subject: Gases | Technique: Remote Sensing | Topic: Data Processing and Information Retrieval
Assimilation of volcanic sulfur dioxide products from IASI and TROPOMI into the chemical transport model MOCAGE: case study of the 2021 La Soufrière Saint Vincent eruption with the March 2022 version of MOCAGE
Mickaël Bacles, Jonathan Améric, and Vincent Guidard
Atmos. Meas. Tech., 18, 2659–2680, https://doi.org/10.5194/amt-18-2659-2025,https://doi.org/10.5194/amt-18-2659-2025, 2025
Short summary
In-flight estimation of instrument spectral response functions using sparse representations
Jihanne El Haouari, Jean-Michel Gaucel, Christelle Pittet, Jean-Yves Tourneret, and Herwig Wendt
Atmos. Meas. Tech., 18, 2573–2590, https://doi.org/10.5194/amt-18-2573-2025,https://doi.org/10.5194/amt-18-2573-2025, 2025
Short summary
Robustness of atmospheric trace gas retrievals obtained from low-spectral-resolution Fourier transform infrared absorption spectra under variations of interferogram length
Bavo Langerock, Martine De Mazière, Filip Desmet, Pauli Heikkinen, Rigel Kivi, Mahesh Kumar Sha, Corinne Vigouroux, Minqiang Zhou, Gopala Krishna Darbha, and Mohmmed Talib
Atmos. Meas. Tech., 18, 2439–2446, https://doi.org/10.5194/amt-18-2439-2025,https://doi.org/10.5194/amt-18-2439-2025, 2025
Short summary
Retrieval of NO2 profiles from 3 years of Pandora MAX-DOAS measurements in Toronto, Canada
Ramina Alwarda, Kristof Bognar, Xiaoyi Zhao, Vitali Fioletov, Jonathan Davies, Sum Chi Lee, Debora Griffin, Alexandru Lupu, Udo Frieß, Alexander Cede, Yushan Su, and Kimberly Strong
Atmos. Meas. Tech., 18, 2397–2423, https://doi.org/10.5194/amt-18-2397-2025,https://doi.org/10.5194/amt-18-2397-2025, 2025
Short summary
A channel selection methodology for enhancing volcanic SO2 monitoring using FY-3E/HIRAS-II hyperspectral data
Xinyu Li, Lin Zhu, Hongfu Sun, Jun Li, Ximing Lv, Chengli Qi, and Huanhuan Yan
Atmos. Meas. Tech., 18, 2333–2352, https://doi.org/10.5194/amt-18-2333-2025,https://doi.org/10.5194/amt-18-2333-2025, 2025
Short summary

Cited articles

Anderson, G.: Error propagation by the Monte Carlo method in geochemical calculations, Geochim. Cosmochim. Acta, 40, 1533–1538, https://doi.org/10.1016/0016-7037(76)90092-2, 1976. a
Ardizzone, L., Kruse, J., Wirkert, S., Rahner, D., Pellegrini, E. W., Klessen, R. S., Maier-Hein, L., Rother, C., and Köthe, U.: Analyzing Inverse Problems with Invertible Neural Networks, https://doi.org/10.48550/ARXIV.1808.04730, 2018. a
Beckwith, M., Bates, E., Gillah, A., and Carslaw, N.: NO2 hotspots: Are we measuring in the right places?, Atmos. Environ. X, 2, 100025, https://doi.org/10.1016/j.aeaoa.2019.100025, 2019. a
Beirle, S., Dörner, S., Donner, S., Remmers, J., Wang, Y., and Wagner, T.: The Mainz profile algorithm (MAPA), Atmos. Meas. Tech., 12, 1785–1806, https://doi.org/10.5194/amt-12-1785-2019, 2019. a, b, c
Bergstra, J. and Bengio, Y.: Random Search for Hyper-Parameter Optimization, J. Mach. Learn. Res., 13, 281–305, 2012. a, b
Download
Short summary
This paper presents a new machine learning model that allows us to compute NO2 concentration profiles from satellite observations. A neural network was trained on synthetic data from the regional chemistry and transport model WRF-Chem. This is the first model of its kind. We present a thorough model validation study, covering various seasons and regions of the world.
Share