Articles | Volume 14, issue 12
https://doi.org/10.5194/gmd-14-7411-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-14-7411-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
02 Dec 2021
Model description paper |
| 02 Dec 2021
| 02 Dec 2021
Machine-learning models to replicate large-eddy simulations of air pollutant concentrations along boulevard-type streets
Moritz Lange
Department of Computer Science, University of Helsinki, Helsinki, Finland
Henri Suominen
Department of Computer Science, University of Helsinki, Helsinki, Finland
Mona Kurppa
Institute of Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, Helsinki, Finland
Leena Järvi
Institute of Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, Helsinki, Finland
Helsinki Institute of Sustainability Science, University of Helsinki, Helsinki, Finland
Emilia Oikarinen
Department of Computer Science, University of Helsinki, Helsinki, Finland
Rafael Savvides
Department of Computer Science, University of Helsinki, Helsinki, Finland
Department of Computer Science, University of Helsinki, Helsinki, Finland
Institute of Atmospheric and Earth System Research (INAR)/Physics, University of Helsinki, Helsinki, Finland
Related authors
No articles found.
Aino Ovaska, Daniel Holmberg, Elio Rauth, Mansour Alghamdi, Paulo Artaxo, Eija Asmi, John Backman, Benjamin Bergmans, Matthew Boyer, Liezl Bredenkamp, Maurizio Busetto, Delano Campos De Oliveira, Juan Andrés Casquero-Vera, Darius Ceburnis, Tak Chan, Tommy Chan, Sebastien Conil, Daniele Contini, Suzanne Crumeyrolle, Valentin Duflot, Kostas Eleftheriadis, Johan Esveld, Ekaterina Ezhova, Markus Fiebig, Shahzad Gani, Olga Garmash, Francisco Gómez-Moreno, Roy M. Harrison, Andras Hoffer, Rakesh Hooda, Antti Hyvärinen, Tareq Hussein, Jorma Joutsensaari, Nikos Kalivitis, Heinz Kaminski, Jutta Kesti, Radovan Krejci, Adam Kristensson, Chongai Kuang, Markku Kulmala, Lauri Laakso, Ari Leskinen, Heikki Lihavainen, Andreas Massling, Maik Merkel, Steffen Noe, Jakub Ondracek, Noemí Perez, Jean-Eudes Petit, Tuukka Petäjä, Michael Pikridas, Christopher Pöhlker, Mira Pöhlker, Jean-Philippe Putaud, Ximeng Qi, Cristina Reche, Sergio Rodríguez, Petr Roztocil, Jean Sciare, Karine Sellegri, Dongjie Shang, Ashish Singh, Mikko Sipilä, Henrik Skov, Mar Sorribas, Tamanna Subba, Junying Sun, Peter Tunved, Ville Vakkari, Pieter G. Van Zyl, Aki Virkkula, Jens Voigtländer, Kay Weinhold, Alfred Wiedensohler, Hee-Jung Yoo, Putian Zhou, Kai Puolamäki, Tuomo Nieminen, Veli-Matti Kerminen, Victoria A. Sinclair, and Pauli Paasonen
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2026-415, https://doi.org/10.5194/essd-2026-415, 2026
Preprint under review for ESSD
Short summary
Short summary
All clouds form around aerosol particles, and their abundance influences cloud properties. In turn, clouds affect climate by changing how energy moves through the atmosphere, making them important for climate change. To better understand these interactions, we need accurate information on how many aerosol particles are in the atmosphere. Therefore, we have developed a new 21-year global dataset of particle concentrations relevant for cloud formation.
Alohotsy Rafalimanana, Thomas Lauvaux, Charbel Abdallah, Mali Chariot, Michel Ramonet, Josselin Doc, Olivier Laurent, Morgan Lopez, Anja Raznjevic, Maarten Krol, Leena Järvi, Andreas Christen, Dana Looschelders, Leslie David, Olivier Sanchez, Laura Bignotti, Benjamin Loubet, Sue Grimmond, and William Morrison
EGUsphere, https://doi.org/10.5194/egusphere-2026-2109, https://doi.org/10.5194/egusphere-2026-2109, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
This study explores how city design and buildings affect CO2 levels in the air over Paris. Using a transport model, we tested different urban canopy models to represent the city environment and its influence on air motion. We found that realistic descriptions of urban surfaces are crucial, especially in winter, for accurately showing how CO2 builds up and disperses, leading to better satellite monitoring of city CO2 emissions.
Nahid Atashi, Xiaoyu Li, Sasu Karttunen, Riku Viri, Roy Harrison, Jani Strömberg, Aino Kaltianen, Matti Leinonen, Laura Ruotsalainen, and Leena Järvi
EGUsphere, https://doi.org/10.5194/egusphere-2026-341, https://doi.org/10.5194/egusphere-2026-341, 2026
Short summary
Short summary
We studied how switching to electric cars affects air quality in a new Helsinki neighborhood. Using advanced computer models, we found that a full shift to electric vehicles by 2040 will cut the number of tiny harmful particles by 60 % because tailpipe exhaust is removed. However, the total weight of these particles will actually increase by 15 % due to heavier vehicles causing more tire and road wear. This shows that urban planners must look beyond just engines maintain urban air quality.
Aino Ovaska, Elio Rauth, Daniel Holmberg, Paulo Artaxo, John Backman, Benjamin Bergmans, Don Collins, Marco Aurélio Franco, Shahzad Gani, Roy M. Harrison, Rakesh K. Hooda, Tareq Hussein, Antti-Pekka Hyvärinen, Kerneels Jaars, Adam Kristensson, Markku Kulmala, Lauri Laakso, Ari Laaksonen, Nikolaos Mihalopoulos, Colin O'Dowd, Jakub Ondracek, Tuukka Petäjä, Kristina Plauškaitė, Mira Pöhlker, Ximeng Qi, Peter Tunved, Ville Vakkari, Alfred Wiedensohler, Kai Puolamäki, Tuomo Nieminen, Veli-Matti Kerminen, Victoria A. Sinclair, and Pauli Paasonen
Aerosol Research, 3, 589–618, https://doi.org/10.5194/ar-3-589-2025, https://doi.org/10.5194/ar-3-589-2025, 2025
Short summary
Short summary
We trained machine learning models to estimate the number of aerosol particles large enough to form clouds and generated daily estimates for the entire globe. The models performed well in many continental regions but struggled in remote and marine areas. Still, this approach offers a way to quantify these particles in areas that lack direct measurements, helping us understand their influence on clouds and climate on a global scale.
Sasu Karttunen, Matthias Sühring, Ewan O'Connor, and Leena Järvi
Geosci. Model Dev., 18, 5725–5757, https://doi.org/10.5194/gmd-18-5725-2025, https://doi.org/10.5194/gmd-18-5725-2025, 2025
Short summary
Short summary
This paper presents PALM-SLUrb, a single-layer urban canopy model for the PALM model system, designed to simulate urban–atmosphere interactions without resolving flow around individual buildings. The model is described in detail and evaluated against grid-resolved urban canopy simulations, demonstrating its ability to model urban surfaces accurately. By bridging the gap between computational efficiency and physical detail, PALM-SLUrb broadens PALM's potential for urban climate research.
Stavros Stagakis, Dominik Brunner, Junwei Li, Leif Backman, Anni Karvonen, Lionel Constantin, Leena Järvi, Minttu Havu, Jia Chen, Sophie Emberger, and Liisa Kulmala
Biogeosciences, 22, 2133–2161, https://doi.org/10.5194/bg-22-2133-2025, https://doi.org/10.5194/bg-22-2133-2025, 2025
Short summary
Short summary
The balance between CO2 uptake and emissions from urban green areas is still not well understood. This study evaluated for the first time the urban park CO2 exchange simulations with four different types of biosphere model by comparing them with observations. Even though some advantages and disadvantages of the different model types were identified, there was no strong evidence that more complex models performed better than simple ones.
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
Short summary
Cities aim for carbon neutrality and seek to understand urban vegetation's role as a carbon sink. Direct measurements are challenging, so models are used to estimate the urban carbon cycle. We evaluated model performance at estimating carbon sequestration in lawns, park trees, and urban forests in Helsinki, Finland. Models captured seasonal and annual variations well. Trees had higher sequestration rates than lawns, and irrigation often enhanced carbon sinks.
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
Short summary
We measured and modelled soil respiration, a key part of the biogenic carbon cycle, in different urban green space types to assess its dynamics in urban areas. We discovered surprisingly similar soil respiration across the green space types despite differences in some of its drivers and that irrigation of green spaces notably elevates soil respiration. Our results encourage further research on the topic and especially on the role of irrigation in controlling urban soil respiration.
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
Short summary
We present a Bayesian non-negative matrix factorization model that performs better on our test datasets than currently widely used models. Its advantages are better use of time information and providing a direct error estimation. We believe this could lead to better estimates of emission sources from measurements.
Joyson Ahongshangbam, Liisa Kulmala, Jesse Soininen, Yasmin Frühauf, Esko Karvinen, Yann Salmon, Anna Lintunen, Anni Karvonen, and Leena Järvi
Biogeosciences, 20, 4455–4475, https://doi.org/10.5194/bg-20-4455-2023, https://doi.org/10.5194/bg-20-4455-2023, 2023
Short summary
Short summary
Urban vegetation is important for removing urban CO2 emissions and cooling. We studied the response of urban trees' functions (photosynthesis and transpiration) to a heatwave and drought at four urban green areas in the city of Helsinki. We found that tree water use was increased during heatwave and drought periods, but there was no change in the photosynthesis rates. The heat and drought conditions were severe at the local scale but were not excessive enough to restrict urban trees' functions.
Jani Strömberg, Xiaoyu Li, Mona Kurppa, Heino Kuuluvainen, Liisa Pirjola, and Leena Järvi
Atmos. Chem. Phys., 23, 9347–9364, https://doi.org/10.5194/acp-23-9347-2023, https://doi.org/10.5194/acp-23-9347-2023, 2023
Short summary
Short summary
We conclude that with low wind speeds, solar radiation has a larger decreasing effect (53 %) on pollutant concentrations than aerosol processes (18 %). Additionally, our results showed that with solar radiation included, pollutant concentrations were closer to observations (−13 %) than with only aerosol processes (+98 %). This has implications when planning simulations under calm conditions such as in our case and when deciding whether or not simulations need to include these processes.
Yingqi Zheng, Minttu Havu, Huizhi Liu, Xueling Cheng, Yifan Wen, Hei Shing Lee, Joyson Ahongshangbam, and Leena Järvi
Geosci. Model Dev., 16, 4551–4579, https://doi.org/10.5194/gmd-16-4551-2023, https://doi.org/10.5194/gmd-16-4551-2023, 2023
Short summary
Short summary
The performance of the Surface Urban Energy and Water Balance Scheme (SUEWS) is evaluated against the observed surface exchanges (fluxes) of heat and carbon dioxide in a densely built neighborhood in Beijing. The heat flux modeling is noticeably improved by using the observed maximum conductance and by optimizing the vegetation phenology modeling. SUEWS also performs well in simulating carbon dioxide flux.
Mathew Lipson, Sue Grimmond, Martin Best, Winston T. L. Chow, Andreas Christen, Nektarios Chrysoulakis, Andrew Coutts, Ben Crawford, Stevan Earl, Jonathan Evans, Krzysztof Fortuniak, Bert G. Heusinkveld, Je-Woo Hong, Jinkyu Hong, Leena Järvi, Sungsoo Jo, Yeon-Hee Kim, Simone Kotthaus, Keunmin Lee, Valéry Masson, Joseph P. McFadden, Oliver Michels, Wlodzimierz Pawlak, Matthias Roth, Hirofumi Sugawara, Nigel Tapper, Erik Velasco, and Helen Claire Ward
Earth Syst. Sci. Data, 14, 5157–5178, https://doi.org/10.5194/essd-14-5157-2022, https://doi.org/10.5194/essd-14-5157-2022, 2022
Short summary
Short summary
We describe a new openly accessible collection of atmospheric observations from 20 cities around the world, capturing 50 site years. The observations capture local meteorology (temperature, humidity, wind, etc.) and the energy fluxes between the land and atmosphere (e.g. radiation and sensible and latent heat fluxes). These observations can be used to improve our understanding of urban climate processes and to test the accuracy of urban climate models.
Chao Yan, Yicheng Shen, Dominik Stolzenburg, Lubna Dada, Ximeng Qi, Simo Hakala, Anu-Maija Sundström, Yishuo Guo, Antti Lipponen, Tom V. Kokkonen, Jenni Kontkanen, Runlong Cai, Jing Cai, Tommy Chan, Liangduo Chen, Biwu Chu, Chenjuan Deng, Wei Du, Xiaolong Fan, Xu-Cheng He, Juha Kangasluoma, Joni Kujansuu, Mona Kurppa, Chang Li, Yiran Li, Zhuohui Lin, Yiliang Liu, Yuliang Liu, Yiqun Lu, Wei Nie, Jouni Pulliainen, Xiaohui Qiao, Yonghong Wang, Yifan Wen, Ye Wu, Gan Yang, Lei Yao, Rujing Yin, Gen Zhang, Shaojun Zhang, Feixue Zheng, Ying Zhou, Antti Arola, Johanna Tamminen, Pauli Paasonen, Yele Sun, Lin Wang, Neil M. Donahue, Yongchun Liu, Federico Bianchi, Kaspar R. Daellenbach, Douglas R. Worsnop, Veli-Matti Kerminen, Tuukka Petäjä, Aijun Ding, Jingkun Jiang, and Markku Kulmala
Atmos. Chem. Phys., 22, 12207–12220, https://doi.org/10.5194/acp-22-12207-2022, https://doi.org/10.5194/acp-22-12207-2022, 2022
Short summary
Short summary
Atmospheric new particle formation (NPF) is a dominant source of atmospheric ultrafine particles. In urban environments, traffic emissions are a major source of primary pollutants, but their contribution to NPF remains under debate. During the COVID-19 lockdown, traffic emissions were significantly reduced, providing a unique chance to examine their relevance to NPF. Based on our comprehensive measurements, we demonstrate that traffic emissions alone are not able to explain the NPF in Beijing.
Benjamin Foreback, Lubna Dada, Kaspar R. Daellenbach, Chao Yan, Lili Wang, Biwu Chu, Ying Zhou, Tom V. Kokkonen, Mona Kurppa, Rosaria E. Pileci, Yonghong Wang, Tommy Chan, Juha Kangasluoma, Lin Zhuohui, Yishou Guo, Chang Li, Rima Baalbaki, Joni Kujansuu, Xiaolong Fan, Zemin Feng, Pekka Rantala, Shahzad Gani, Federico Bianchi, Veli-Matti Kerminen, Tuukka Petäjä, Markku Kulmala, Yongchun Liu, and Pauli Paasonen
Atmos. Chem. Phys., 22, 11089–11104, https://doi.org/10.5194/acp-22-11089-2022, https://doi.org/10.5194/acp-22-11089-2022, 2022
Short summary
Short summary
This study analyzed air quality in Beijing during the Chinese New Year over 7 years, including data from a new in-depth measurement station. This is one of few studies to look at long-term impacts, including the outcome of firework restrictions starting in 2018. Results show that firework pollution has gone down since 2016, indicating a positive result from the restrictions. Results of this study may be useful in making future decisions about the use of fireworks to improve air quality.
Minttu Havu, Liisa Kulmala, Pasi Kolari, Timo Vesala, Anu Riikonen, and Leena Järvi
Biogeosciences, 19, 2121–2143, https://doi.org/10.5194/bg-19-2121-2022, https://doi.org/10.5194/bg-19-2121-2022, 2022
Short summary
Short summary
The carbon sequestration potential of two street tree species and the soil beneath them was quantified with the urban land surface model SUEWS and the soil carbon model Yasso. The street tree plantings turned into a modest sink of carbon from the atmosphere after 14 years. Overall, the results indicate the importance of soil in urban carbon sequestration estimations, as soil respiration exceeded the carbon uptake in the early phase, due to the high initial carbon loss from the soil.
Sasu Karttunen, Ewan O'Connor, Olli Peltola, and Leena Järvi
Atmos. Meas. Tech., 15, 2417–2432, https://doi.org/10.5194/amt-15-2417-2022, https://doi.org/10.5194/amt-15-2417-2022, 2022
Short summary
Short summary
To study the complex structure of the lowest tens of metres of atmosphere in urban areas, measurement methods with great spatial and temporal coverage are needed. In our study, we analyse measurements with a promising and relatively new method, distributed temperature sensing, capable of providing detailed information on the near-surface atmosphere. We present multiple ways to utilise these kinds of measurements, as well as important considerations for planning new studies using the method.
Jarmo Mäkelä, Laila Melkas, Ivan Mammarella, Tuomo Nieminen, Suyog Chandramouli, Rafael Savvides, and Kai Puolamäki
Biogeosciences, 19, 2095–2099, https://doi.org/10.5194/bg-19-2095-2022, https://doi.org/10.5194/bg-19-2095-2022, 2022
Short summary
Short summary
Causal structure discovery algorithms have been making headway into Earth system sciences, and they can be used to increase our understanding on biosphere–atmosphere interactions. In this paper we present a procedure on how to utilize prior knowledge of the domain experts together with these algorithms in order to find more robust causal structure models. We also demonstrate how to avoid pitfalls such as over-fitting and concept drift during this process.
Shang Gao, Mona Kurppa, Chak K. Chan, and Keith Ngan
Atmos. Chem. Phys., 22, 2703–2726, https://doi.org/10.5194/acp-22-2703-2022, https://doi.org/10.5194/acp-22-2703-2022, 2022
Short summary
Short summary
The contribution of cooking emissions to organic aerosols may exceed that of motor vehicles. However, little is known about how cooking-generated aerosols evolve in the outdoor environment. In this paper, we present a numerical study of the dispersion of cooking emissions. For plausible choices of the emission strength, cooking can yield much higher concentrations than traffic. This has important implications for public health and city planning.
Michal Belda, Jaroslav Resler, Jan Geletič, Pavel Krč, Björn Maronga, Matthias Sühring, Mona Kurppa, Farah Kanani-Sühring, Vladimír Fuka, Kryštof Eben, Nina Benešová, and Mikko Auvinen
Geosci. Model Dev., 14, 4443–4464, https://doi.org/10.5194/gmd-14-4443-2021, https://doi.org/10.5194/gmd-14-4443-2021, 2021
Short summary
Short summary
The analysis summarizes how sensitive the modelling of urban environment is to changes in physical parameters describing the city (e.g. reflectivity of surfaces) and to several heat island mitigation scenarios in a city quarter in Prague, Czech Republic. We used the large-eddy simulation modelling system PALM 6.0. Surface parameters connected to radiation show the highest sensitivity in this configuration. For heat island mitigation, urban vegetation is shown to be the most effective measure.
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
Cristianini, N. and Shawe-Taylor, J.: An Introduction to Support Vector
Machines and Other Kernel-based Learning Methods, Cambridge University Press, Cambridge, United Kingdom,
https://doi.org/10.1017/CBO9780511801389, 2000. a
Feng, R., Zheng, H.-J., Gao, H., Zhang, A.-R., Huang, C., Zhang, J.-X., Luo,
K., and Fan, J.-R.: Recurrent Neural Network and random forest for analysis
and accurate forecast of atmospheric pollutants: A case study in Hangzhou,
China, J. Cleaner Product., 231, 1005–1015,
https://doi.org/10.1016/j.jclepro.2019.05.319, 2019. a
Fernández-Delgado, M., Cernadas, E., Barro, S., and Amorim, D.: Do We Need
Hundreds of Classifiers to Solve Real World Classification Problems?, J.
Mach. Learn. Res., 15, 3133–3181, 2014. a
Gama, J. A., Žliobaitundefined, I., Bifet, A., Pechenizkiy, M., and
Bouchachia, A.: A Survey on Concept Drift Adaptation, ACM Comput. Surv., 46, 44,
https://doi.org/10.1145/2523813, 2014. a
Gómez-Dans, J. L., Lewis, P. E., and Disney, M.: Efficient Emulation of
Radiative Transfer Codes Using Gaussian Processes and Application to Land
Surface Parameter Inferences, Remote Sensing, 8, https://doi.org/10.3390/rs8020119,
2016. a
Heus, T., van Heerwaarden, C. C., Jonker, H. J. J., Pier Siebesma, A., Axelsen,
S., van den Dries, K., Geoffroy, O., Moene, A. F., Pino, D., de Roode, S. R.,
and Vilà-Guerau de Arellano, J.: Formulation of the Dutch Atmospheric
Large-Eddy Simulation (DALES) and overview of its applications, Geosci. Model
Dev., 3, 415–444, https://doi.org/10.5194/gmd-3-415-2010, 2010. a
Hu, K., Rahman, A., Bhrugubanda, H., and Sivaraman, V.: HazeEst:
Machine Learning Based Metropolitan Air Pollution Estimation From Fixed and
Mobile Sensors, IEEE Sensors J., 17, 3517–3525,
https://doi.org/10.1109/JSEN.2017.2690975, 2017. a, b, c
Karttunen, S., Kurppa, M., Auvinen, M., Hellsten, A., and Järvi, L.:
Large-eddy simulation of the optimal street-tree layout for pedestrian-level
aerosol particle concentrations – A case study from a city-boulevard, Atmos.
Environ., 6, 100073, https://doi.org/10.1016/j.aeaoa.2020.100073, 2020. a, b, c, d
Karttunen, S. and Kurppa, M.: Input data for article “Large eddy simulation of the optimal street-tree layout for pedestrian-level aerosol particle concentrations”, Zenodo [data set], https://doi.org/10.5281/zenodo.3556287, 2021a. a
Karttunen, S. and Kurppa, M.: Input and output files and datasets for a LES case study of city-boulevard ventilation, Fairdata [data set], available at: http://urn.fi/urn:nbn:fi:att:ee275362-3f56-477c-bbbc-6fcacd9c7f95, last access: 22 November 2021. a
King, R. N., Adcock, C., Annoni, J., and Dykes, K.: Data-Driven Machine
Learning for Wind Plant Flow Modeling, J. Phys. Conf. Ser.,
1037, 072004, https://doi.org/10.1088/1742-6596/1037/7/072004, 2018. a
Krecl, P., Cipoli, Y. A., Targino, A. C., de Oliveira Toloto, M., Segersson,
D., Ãlvaro Parra, Polezer, G., Godoi, R. H. M., and Gidhagen, L.: Modelling
urban cyclists' exposure to black carbon particles using high spatiotemporal
data: A statistical approach, Sci. Total Environ., 679,
115–125, https://doi.org/10.1016/j.scitotenv.2019.05.043, 2019. a, b, c
Kumar, P., Ketzel, M., Vardoulakis, S., Pirjola, L., and Britter, R.: Dynamics
and dispersion modelling of nanoparticles from road traffic in the urban
atmospheric environment – A review, J. Aerosol Sci., 42, 580–603,
https://doi.org/10.1016/j.jaerosci.2011.06.001, 2011. a
Kurppa, M., Hellsten, A., Roldin, P., Kokkola, H., Tonttila, J., Auvinen, M.,
Kent, C., Kumar, P., Maronga, B., and Järvi, L.: Implementation of the
sectional aerosol module SALSA2.0 into the PALM model system 6.0: model
development and first evaluation, Geosci. Model Dev., 12,
1403–1422, https://doi.org/10.5194/gmd-12-1403-2019, 2019. a
Kurppa, M., Helssten, A., Auvinen, M., and Järvi, L.: Assessing pollutant ventilation in a city-boulevard using large-eddy simulation, Fairdata [data set], available at: http://urn.fi/urn:nbn:fi:att:cfe1bd77-6697-44b5-bdd7-ee74f36c7dcd, last access: 22 November 2021. a
Lambert, D.: Zero-Inflated Poisson Regression, With an Application to Defects
in Manufacturing, Technometrics, 34, 1–14, 1992. a
Lange, M., Suominen, H., Kurppa, M., Järvi, L., Oikarinen, E., Savvides, R., and Puolamäki, K.: Datasets of Air Pollutants on Boulevard Type Streets and Software to Replicate Large-Eddy Simulations of Air Pollutant Concentrations Along Boulevard-Type Streets (1.0.0), Zenodo [data set and code], https://doi.org/10.5281/zenodo.3999302, 2021. a
Lelieveld, J., Evans, J. S., Fnais, M., Giannadaki, D., and Pozzer, A.: The
contribution of outdoor air pollution sources to premature mortality on a
global scale, Nature, 525, 367–371, https://doi.org/10.1038/nature15371, 2015. a
Lelieveld, J., Klingmüller, K., Pozzer, A., Pöschl, U., Fnais, M.,
Daiber, A., and Münzel, T.: Cardiovascular disease burden from ambient
air pollution in Europe reassessed using novel hazard ratio functions, Eur.
Heart J., 40, 1590–1596, https://doi.org/10.1093/eurheartj/ehz135, 2019. a
Maronga, B., Gryschka, M., Heinze, R., Hoffmann, F., Kanani-Sühring, F.,
Keck, M., Ketelsen, K., Letzel, M. O., Sühring, M., and Raasch, S.: The
Parallelized Large-Eddy Simulation Model (PALM) version 4.0 for atmospheric
and oceanic flows: model formulation, recent developments, and future
perspectives, Geosci. Model Dev., 8, 2515–2551,
https://doi.org/10.5194/gmd-8-2515-2015, 2015. a
Maronga, B., Banzhaf, S., Burmeister, C., Esch, T., Forkel, R., Fröhlich, D., Fuka, V., Gehrke, K. F., Geletič, J., Giersch, S., Gronemeier, T., Groß, G., Heldens, W., Hellsten, A., Hoffmann, F., Inagaki, A., Kadasch, E., Kanani-Sühring, F., Ketelsen, K., Khan, B. A., Knigge, C., Knoop, H., Krč, P., Kurppa, M., Maamari, H., Matzarakis, A., Mauder, M., Pallasch, M., Pavlik, D., Pfafferott, J., Resler, J., Rissmann, S., Russo, E., Salim, M., Schrempf, M., Schwenkel, J., Seckmeyer, G., Schubert, S., Sühring, M., von Tils, R., Vollmer, L., Ward, S., Witha, B., Wurps, H., Zeidler, J., and Raasch, S.: Overview of the PALM model system 6.0, Geosci. Model Dev., 13, 1335–1372, https://doi.org/10.5194/gmd-13-1335-2020, 2020. a
Nosek, Š., Kukačka, L., Kellnerová, R., Jurčáková,
K., and Jaňour, Z.: Ventilation Processes in a Three-Dimensional Street
Canyon, Bound.-Lay. Meteorol., 159, 259–284,
https://doi.org/10.1007/s10546-016-0132-2, 2016.
a
Oikarinen, E., Tiittanen, H., Henelius, A., and Puolamäki, K.: Detecting
virtual concept drift of regressors without ground truth values, Data Min. Knowl. Disc., 35, 726–747, https://doi.org/10.1007/s10618-021-00739-7,
2021. a, b, c
Peng, H., Lima, A. R., Teakles, A., Jin, J., Cannon, A. J., and Hsieh, W. W.:
Evaluating hourly air quality forecasting in Canada with nonlinear updatable
machine learning methods, Air Quality, Atmos. Health, 10, 195–211,
https://doi.org/10.1007/s11869-016-0414-3, 2017. a, b
R Core Team: R: A Language and Environment for Statistical Computing, R
Foundation for Statistical Computing, Vienna, Austria,
avilable at: https://www.R-project.org/ (last access: 22 November 2021), 2020. a
Rybarczyk, Y. and Zalakeviciute, R.: Machine Learning Approaches for Outdoor
Air Quality Modelling: A Systematic Review, Appl. Sci., 8, 2570,
https://doi.org/10.3390/app8122570, 2018. a, b
Salim, S. M., Buccolieri, R., Chan, A., and Sabatino, S. D.: Numerical
simulation of atmospheric pollutant dispersion in an urban street canyon:
Comparison between RANS and LES, J. Wind Eng. Ind. Aerod., 99, 103–113, https://doi.org/10.1016/j.jweia.2010.12.002, 2011. a
Tominaga, Y. and Stathopoulos, T.: CFD modeling of pollution dispersion in a
street canyon: Comparison between LES and RANS, J. Wind Eng. Ind. Aerod.,
99, 340–348, https://doi.org/10.1016/j.jweia.2010.12.005, 2011. a
Van den Bossche, J., Baets, B. D., Verwaeren, J., Botteldooren, D., and
Theunis, J.: Development and evaluation of land use regression models for
black carbon based on bicycle and pedestrian measurements in the urban
environment, Environ. Model. Softw., 99, 58–69,
https://doi.org/10.1016/j.envsoft.2017.09.019, 2018. a, b, c, d
WHO (World Health Organization): Ambient air pollution: A global assessment of exposure and burden of
disease, available at: https://apps.who.int/iris/handle/10665/250141 (last access: 22 November 2021), 2016. a
Yang, W., Deng, M., Xu, F., and Wang, H.: Prediction of hourly PM2.5 using a
space-time support vector regression model, Atmos. Environ., 181, 12–19, https://doi.org/10.1016/j.atmosenv.2018.03.015, 2018. a
Yuan, C., Ng, E., and Norford, L. K.: Improving air quality in high-density
cities by understanding the relationship between air pollutant dispersion and
urban morphologies, Build. Environ., 71, 245–258,
https://doi.org/10.1016/j.buildenv.2013.10.008, 2014. a
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.
This study aims to replicate computationally expensive high-resolution large-eddy simulations...
