Articles | Volume 16, issue 7
https://doi.org/10.5194/gmd-16-2037-2023
https://doi.org/10.5194/gmd-16-2037-2023
Development and technical paper
 | 
14 Apr 2023
Development and technical paper |  | 14 Apr 2023

Accelerating models for multiphase chemical kinetics through machine learning with polynomial chaos expansion and neural networks

Thomas Berkemeier, Matteo Krüger, Aryeh Feinberg, Marcel Müller, Ulrich Pöschl, and Ulrich K. Krieger

Related authors

Ice-nucleating properties of glassy organic and organosulfate aerosol
Christopher N. Rapp, Sining Niu, N. Cazimir Armstrong, Xiaoli Shen, Thomas Berkemeier, Jason D. Surratt, Yue Zhang, and Daniel J. Cziczo
Atmos. Chem. Phys., 25, 5519–5536, https://doi.org/10.5194/acp-25-5519-2025,https://doi.org/10.5194/acp-25-5519-2025, 2025
Short summary
Improved vapor pressure predictions using group contribution-assisted graph convolutional neural networks (GC2NN)
Matteo Krüger, Tommaso Galeazzo, Ivan Eremets, Bertil Schmidt, Ulrich Pöschl, Manabu Shiraiwa, and Thomas Berkemeier
EGUsphere, https://doi.org/10.5194/egusphere-2025-1191,https://doi.org/10.5194/egusphere-2025-1191, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Heterogeneous reaction kinetics influencing benzo(a)pyrene global atmospheric distribution and related lifetime lung cancer risk
Mega Octaviani, Benjamin A. Musa Bandowe, Qing Mu, Jake Wilson, Holger Tost, Hang Su, Yafang Cheng, Manabu Shiraiwa, Ulrich Pöschl, Thomas Berkemeier, and Gerhard Lammel
EGUsphere, https://doi.org/10.5194/egusphere-2025-186,https://doi.org/10.5194/egusphere-2025-186, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Desorption lifetimes and activation energies influencing gas–surface interactions and multiphase chemical kinetics
Daniel A. Knopf, Markus Ammann, Thomas Berkemeier, Ulrich Pöschl, and Manabu Shiraiwa
Atmos. Chem. Phys., 24, 3445–3528, https://doi.org/10.5194/acp-24-3445-2024,https://doi.org/10.5194/acp-24-3445-2024, 2024
Short summary
Volatile oxidation products and secondary organosiloxane aerosol from D5 + OH at varying OH exposures
Hyun Gu Kang, Yanfang Chen, Yoojin Park, Thomas Berkemeier, and Hwajin Kim
Atmos. Chem. Phys., 23, 14307–14323, https://doi.org/10.5194/acp-23-14307-2023,https://doi.org/10.5194/acp-23-14307-2023, 2023
Short summary

Related subject area

Atmospheric sciences
Quantification of CO2 hotspot emissions from OCO-3 SAM CO2 satellite images using deep learning methods
Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Grégoire Broquet, Gerrit Kuhlmann, and Marc Bocquet
Geosci. Model Dev., 18, 3607–3622, https://doi.org/10.5194/gmd-18-3607-2025,https://doi.org/10.5194/gmd-18-3607-2025, 2025
Short summary
Diagnosis of winter precipitation types using the spectral bin model (version 1DSBM-19M): comparison of five methods using ICE-POP 2018 field experiment data
Wonbae Bang, Jacob T. Carlin, Kwonil Kim, Alexander V. Ryzhkov, Guosheng Liu, and GyuWon Lee
Geosci. Model Dev., 18, 3559–3581, https://doi.org/10.5194/gmd-18-3559-2025,https://doi.org/10.5194/gmd-18-3559-2025, 2025
Short summary
Improving winter condition simulations in SURFEX-TEB v9.0 with a multi-layer snow model and ice
Gabriel Colas, Valéry Masson, François Bouttier, Ludovic Bouilloud, Laura Pavan, and Virve Karsisto
Geosci. Model Dev., 18, 3453–3472, https://doi.org/10.5194/gmd-18-3453-2025,https://doi.org/10.5194/gmd-18-3453-2025, 2025
Short summary
UA-ICON with the NWP physics package (version ua-icon-2.1): mean state and variability of the middle atmosphere
Markus Kunze, Christoph Zülicke, Tarique A. Siddiqui, Claudia C. Stephan, Yosuke Yamazaki, Claudia Stolle, Sebastian Borchert, and Hauke Schmidt
Geosci. Model Dev., 18, 3359–3385, https://doi.org/10.5194/gmd-18-3359-2025,https://doi.org/10.5194/gmd-18-3359-2025, 2025
Short summary
Integrated Methane Inversion (IMI) 2.0: an improved research and stakeholder tool for monitoring total methane emissions with high resolution worldwide using TROPOMI satellite observations
Lucas A. Estrada, Daniel J. Varon, Melissa Sulprizio, Hannah Nesser, Zichong Chen, Nicholas Balasus, Sarah E. Hancock, Megan He, James D. East, Todd A. Mooring, Alexander Oort Alonso, Joannes D. Maasakkers, Ilse Aben, Sabour Baray, Kevin W. Bowman, John R. Worden, Felipe J. Cardoso-Saldaña, Emily Reidy, and Daniel J. Jacob
Geosci. Model Dev., 18, 3311–3330, https://doi.org/10.5194/gmd-18-3311-2025,https://doi.org/10.5194/gmd-18-3311-2025, 2025
Short summary

Cited articles

Allotey, J., Butler, K. T., and Thiyagalingam, J.: Entropy-based active learning of graph neural network surrogate models for materials properties, J. Chem. Phys., 155, 174116, https://doi.org/10.1063/5.0065694, 2021. a
Almeida, L. B.: Multilayer Perceptrons, in: The Algebraic Mind: Integrating Connectionism and Cognitive Science, The MIT Press, https://doi.org/10.7551/mitpress/1187.003.0004, 2001. a, b
Berkemeier, T., Huisman, A. J., Ammann, M., Shiraiwa, M., Koop, T., and Pöschl, U.: Kinetic regimes and limiting cases of gas uptake and heterogeneous reactions in atmospheric aerosols and clouds: a general classification scheme, Atmos. Chem. Phys., 13, 6663–6686, https://doi.org/10.5194/acp-13-6663-2013, 2013. a
Berkemeier, T., Steimer, S. S., Krieger, U. K., Peter, T., Pöschl, U., Ammann, M., and Shiraiwa, M.: Ozone uptake on glassy, semi-solid and liquid organic matter and the role of reactive oxygen intermediates in atmospheric aerosol chemistry, Phys. Chem. Chem. Phys., 18, 12662–12674, https://doi.org/10.1039/C6CP00634E, 2016. a
Download
Short summary
Kinetic multi-layer models (KMs) successfully describe heterogeneous and multiphase atmospheric chemistry. In applications requiring repeated execution, however, these models can be too expensive. We trained machine learning surrogate models on output of the model KM-SUB and achieved high correlations. The surrogate models run orders of magnitude faster, which suggests potential applicability in global optimization tasks and as sub-modules in large-scale atmospheric models.
Share