Articles | Volume 14, issue 12
https://doi.org/10.5194/gmd-14-7411-2021
https://doi.org/10.5194/gmd-14-7411-2021
Model description paper
 | 
02 Dec 2021
Model description paper |  | 02 Dec 2021

Machine-learning models to replicate large-eddy simulations of air pollutant concentrations along boulevard-type streets

Moritz Lange, Henri Suominen, Mona Kurppa, Leena Järvi, Emilia Oikarinen, Rafael Savvides, and Kai Puolamäki

Related authors

Carbon sequestration in different urban vegetation types in Southern Finland
Laura Thölix, Leif Backman, Minttu Havu, Esko Karvinen, Jesse Soininen, Justine Trémeau, Olli Nevalainen, Joyson Ahongshangbam, Leena Järvi, and Liisa Kulmala
Biogeosciences, 22, 725–749, https://doi.org/10.5194/bg-22-725-2025,https://doi.org/10.5194/bg-22-725-2025, 2025
Short summary
PALM-SLUrb v24.04: A single-layer urban canopy model for the PALM model system – Model description and first evaluation
Sasu Karttunen, Matthias Sühring, Ewan O'Connor, and Leena Järvi
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-235,https://doi.org/10.5194/gmd-2024-235, 2024
Preprint under review for GMD
Short summary
Intercomparison of biogenic CO2 flux models in four urban parks in the city of Zurich
Stavros Stagakis, Dominik Brunner, Junwei Li, Leif Backman, Anni Karvonen, Lionel Constantin, Leena Järvi, Minttu Havu, Jia Chen, Sophie Emberger, and Liisa Kulmala
EGUsphere, https://doi.org/10.5194/egusphere-2024-2475,https://doi.org/10.5194/egusphere-2024-2475, 2024
Short summary
Soil respiration across a variety of tree-covered urban green spaces in Helsinki, Finland
Esko Karvinen, Leif Backman, Leena Järvi, and Liisa Kulmala
SOIL, 10, 381–406, https://doi.org/10.5194/soil-10-381-2024,https://doi.org/10.5194/soil-10-381-2024, 2024
Short summary
A novel probabilistic source apportionment approach: Bayesian auto-correlated matrix factorization
Anton Rusanen, Anton Björklund, Manousos I. Manousakas, Jianhui Jiang, Markku T. Kulmala, Kai Puolamäki, and Kaspar R. Daellenbach
Atmos. Meas. Tech., 17, 1251–1277, https://doi.org/10.5194/amt-17-1251-2024,https://doi.org/10.5194/amt-17-1251-2024, 2024
Short summary

Related subject area

Numerical methods
Hydro-geomorphological modelling of leaky wooden dam efficacy from reach to catchment scale with CAESAR-Lisflood 1.9j
Joshua M. Wolstenholme, Christopher J. Skinner, David Milan, Robert E. Thomas, and Daniel R. Parsons
Geosci. Model Dev., 18, 1395–1411, https://doi.org/10.5194/gmd-18-1395-2025,https://doi.org/10.5194/gmd-18-1395-2025, 2025
Short summary
Enhancing single precision with quasi-double precision: achieving double-precision accuracy in the Model for Prediction Across Scales – Atmosphere (MPAS-A) version 8.2.1
Jiayi Lai, Lanning Wang, Qizhong Wu, Yizhou Yang, and Fang Wang
Geosci. Model Dev., 18, 1089–1102, https://doi.org/10.5194/gmd-18-1089-2025,https://doi.org/10.5194/gmd-18-1089-2025, 2025
Short summary
Advances in land surface forecasting: a comparison of LSTM, gradient boosting, and feed-forward neural networks as prognostic state emulators in a case study with ecLand
Marieke Wesselkamp, Matthew Chantry, Ewan Pinnington, Margarita Choulga, Souhail Boussetta, Maria Kalweit, Joschka Bödecker, Carsten F. Dormann, Florian Pappenberger, and Gianpaolo Balsamo
Geosci. Model Dev., 18, 921–937, https://doi.org/10.5194/gmd-18-921-2025,https://doi.org/10.5194/gmd-18-921-2025, 2025
Short summary
Subgrid corrections for the linear inertial equations of a compound flood model – a case study using SFINCS 2.1.1 Dollerup release
Maarten van Ormondt, Tim Leijnse, Roel de Goede, Kees Nederhoff, and Ap van Dongeren
Geosci. Model Dev., 18, 843–861, https://doi.org/10.5194/gmd-18-843-2025,https://doi.org/10.5194/gmd-18-843-2025, 2025
Short summary
Introducing Iterative Model Calibration (IMC) v1.0: a generalizable framework for numerical model calibration with a CAESAR-Lisflood case study
Chayan Banerjee, Kien Nguyen, Clinton Fookes, Gregory Hancock, and Thomas Coulthard
Geosci. Model Dev., 18, 803–818, https://doi.org/10.5194/gmd-18-803-2025,https://doi.org/10.5194/gmd-18-803-2025, 2025
Short summary

Cited articles

Adams, M. D. and Kanaroglou, P. S.: Mapping real-time air pollution health risk for environmental management: Combining mobile and stationary air pollution monitoring with neural network models, J. Environ. Manag., 168, 133–141, https://doi.org/10.1016/j.jenvman.2015.12.012, 2016. a, b, c
Araki, S., Shima, M., and Yamamoto, K.: Spatiotemporal land use random forest model for estimating metropolitan NO2 exposure in Japan, Sci. Total Environ., 634, 1269–1277, https://doi.org/10.1016/j.scitotenv.2018.03.324, 2018. a
Auvinen, M., Boi, S., Hellsten, A., Tanhuanpää, T., and Järvi, L.: Study of realistic urban boundary layer turbulence with high-resolution large-eddy simulation, Atmosphere, 11, 201, https://doi.org/10.3390/atmos11020201, 2020. a
Benoit, K.: Linear regression models with logarithmic transformations, London School of Economics, London, 22, 23–36, 2011. a
Britter, R. E. and Hanna, S. R.: Flow and dispersion in urban areas, Ann. Rev. Fluid Mech., 35, 469–496, https://doi.org/10.1146/annurev.fluid.35.101101.161147, 2003. a
Download
Short summary
This study aims to replicate computationally expensive high-resolution large-eddy simulations (LESs) with regression models to simulate urban air quality and pollutant dispersion. The model development, including feature selection, model training and cross-validation, and detection of concept drift, has been described in detail. Of the models applied, log-linear regression shows the best performance. A regression model can replace LES unless high accuracy is needed.
Share