EUVIMEDEUVIMED entdecken
Crossref

Machine learning-based prediction of ambient CO2 and CH4 concentrations with high temporal resolution in Seoul metropolitan area

Seongjun Park, Kwang-Joo Moon, Hyo-Jin Eom, Seung-Muk Yi, Youngkwon Kim, Moonkyung Kim, Donghyun Rim, Young Su Lee

Environmental Pollution · 2025-07 · 376 · 126362

DOI: 10.1016/j.envpol.2025.126362 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Pollution, 2025-07. Verfasst von Seongjun Park und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA, USA. Electronic address: seongjunpark@hsph.harvard.edu. Hauptthemen laut MEDLINE: Machine Learning, Air Pollutants, Environmental Monitoring, Carbon Dioxide. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Institute of Environmental Research, National Research Foundation of Korea, Korea Environmental Industry and Technology Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning has the potential to support the growing need for high-resolution greenhouse gas monitoring in urban and industrial environments, where deploying extensive sensor networks is often limited by cost and operational challenges. This study presents a novel approach for estimating greenhouse gas (GHG) concentrations using routinely collected air quality and meteorological data from existing monitoring stations. Focusing on the Seoul metropolitan area in the Republic of Korea, we developed and evaluated three machine learning models - Random Forest, Long Short-Term Memory (LSTM), and an ensemble learning approach - to predict CO2 and CH4 concentrations without relying on additional GHG monitoring equipment. Among these, the ensemble learning model outperformed the individual models, consistently achieving lower error metrics, even in data-limited scenarios. Feature importance analysis identifies NO2, CO, O3, and temperature as key predictors of CO2 and CH4 level variations, highlighting the influence of combustion-related pollutants and photochemical processes. Cross-validation results confirm the model's out-of-sample capabilities; however, local factors, such as traffic density, industrial activities, and meteorology, can affect performance. Consequently, model retraining or transfer learning may be required when applying the model to new locations with comparable emission profiles or atmospheric conditions. These findings emphasize the importance of localized context in model application while also demonstrating the broader applicability of the approach. By utilizing data already available through urban monitoring networks, this study offers a scalable and cost-effective strategy to support high-resolution GHG monitoring and inform targeted climate policies in complex urban-industrial regions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAir PollutantsEnvironmental MonitoringCarbon DioxideMethaneAir PollutionSeoulGreenhouse GasesRepublic of Korea

Stichwörter der Autor:innen

Air quality monitoringCarbon dioxideGlobal warmingGreenhouse gasMachine learning modelsMethane

Substanzen

Air PollutantsCarbon DioxideMethaneGreenhouse Gases

Autor:innen und Institutionen

  • Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA, USA. Electronic address: seongjunpark@hsph.harvard.edu.
  • Climate Change Research Division, Climate Change and Carbon Research Department, National Institute of Environmental Research, Incheon, Republic of Korea. Electronic address: iamiyan@korea.kr.
  • Climate Change Research Division, Climate Change and Carbon Research Department, National Institute of Environmental Research, Incheon, Republic of Korea. Electronic address: hjeom2017@korea.kr.
  • Department of Environmental Health Sciences, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea. Electronic address: yiseung@snu.ac.kr.
  • Department of Environmental Health Sciences, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea. Electronic address: 98youngkwon@gmail.com.
  • Department of Environmental Health Sciences, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea. Electronic address: strikingirl@snu.ac.kr.

Förderung

  • National Institute of Environmental Research
  • National Research Foundation of Korea
  • Korea Environmental Industry and Technology Institute
  • Ministry of Environment

Zitieren

APA

Park, S., Moon, K. J., Eom, H. J., Yi, S. M., Kim, Y., Kim, M., Rim, D., & Lee, Y. S. (2025). Machine learning-based prediction of ambient CO2 and CH4 concentrations with high temporal resolution in Seoul metropolitan area. Environmental Pollution, 376, 126362. https://doi.org/10.1016/j.envpol.2025.126362

Vancouver

Park S, Moon KJ, Eom HJ, Yi SM, Kim Y, Kim M, et al. Machine learning-based prediction of ambient CO2 and CH4 concentrations with high temporal resolution in Seoul metropolitan area. Environmental Pollution. 2025;376:126362. doi:10.1016/j.envpol.2025.126362

BibTeX
@article{Park2025,
  author = {Park, Seongjun and Moon, Kwang-Joo and Eom, Hyo-Jin and Yi, Seung-Muk and Kim, Youngkwon and Kim, Moonkyung and Rim, Donghyun and Lee, Young Su},
  title = {Machine learning-based prediction of ambient CO2 and CH4 concentrations with high temporal resolution in Seoul metropolitan area},
  journal = {Environmental Pollution},
  year = {2025},
  volume = {376},
  pages = {126362},
  doi = {10.1016/j.envpol.2025.126362}
}
Kostenlos starten →