Articles | Volume 15, issue 20
https://doi.org/10.5194/gmd-15-7791-2022
https://doi.org/10.5194/gmd-15-7791-2022
Development and technical paper
 | 
24 Oct 2022
Development and technical paper |  | 24 Oct 2022

Development of a regional feature selection-based machine learning system (RFSML v1.0) for air pollution forecasting over China

Li Fang, Jianbing Jin, Arjo Segers, Hai Xiang Lin, Mijie Pang, Cong Xiao, Tuo Deng, and Hong Liao

Related authors

A gridded air quality forecast through fusing site-available machine learning predictions from RFSML v1.0 and chemical transport model results from GEOS-Chem v13.1.0 using the ensemble Kalman filter
Li Fang, Jianbing Jin, Arjo Segers, Hong Liao, Ke Li, Bufan Xu, Wei Han, Mijie Pang, and Hai Xiang Lin
Geosci. Model Dev., 16, 4867–4882, https://doi.org/10.5194/gmd-16-4867-2023,https://doi.org/10.5194/gmd-16-4867-2023, 2023
Short summary
Inverse modeling of the 2021 spring super dust storms in East Asia
Jianbing Jin, Mijie Pang, Arjo Segers, Wei Han, Li Fang, Baojie Li, Haochuan Feng, Hai Xiang Lin, and Hong Liao
Atmos. Chem. Phys., 22, 6393–6410, https://doi.org/10.5194/acp-22-6393-2022,https://doi.org/10.5194/acp-22-6393-2022, 2022
Short summary

Related subject area

Atmospheric sciences
An optimisation method to improve modelling of wet deposition in atmospheric transport models: applied to FLEXPART v10.4
Stijn Van Leuven, Pieter De Meutter, Johan Camps, Piet Termonia, and Andy Delcloo
Geosci. Model Dev., 16, 5323–5338, https://doi.org/10.5194/gmd-16-5323-2023,https://doi.org/10.5194/gmd-16-5323-2023, 2023
Short summary
Modelling concentration heterogeneities in streets using the street-network model MUNICH
Thibaud Sarica, Alice Maison, Yelva Roustan, Matthias Ketzel, Steen Solvang Jensen, Youngseob Kim, Christophe Chaillou, and Karine Sartelet
Geosci. Model Dev., 16, 5281–5303, https://doi.org/10.5194/gmd-16-5281-2023,https://doi.org/10.5194/gmd-16-5281-2023, 2023
Short summary
Simulation model of Reactive Nitrogen Species in an Urban Atmosphere using a Deep Neural Network: RNDv1.0
Junsu Gil, Meehye Lee, Jeonghwan Kim, Gangwoong Lee, Joonyoung Ahn, and Cheol-Hee Kim
Geosci. Model Dev., 16, 5251–5263, https://doi.org/10.5194/gmd-16-5251-2023,https://doi.org/10.5194/gmd-16-5251-2023, 2023
Short summary
J-GAIN v1.1: a flexible tool to incorporate aerosol formation rates obtained by molecular models into large-scale models
Daniel Yazgi and Tinja Olenius
Geosci. Model Dev., 16, 5237–5249, https://doi.org/10.5194/gmd-16-5237-2023,https://doi.org/10.5194/gmd-16-5237-2023, 2023
Short summary
Metrics for evaluating the quality in linear atmospheric inverse problems: a case study of a trace gas inversion
Vineet Yadav, Subhomoy Ghosh, and Charles E. Miller
Geosci. Model Dev., 16, 5219–5236, https://doi.org/10.5194/gmd-16-5219-2023,https://doi.org/10.5194/gmd-16-5219-2023, 2023
Short summary

Cited articles

Abu Awad, Y., Koutrakis, P., Coull, B. A., and Schwartz, J.: A spatio-temporal prediction model based on support vector machine regression: Ambient Black Carbon in three New England States, Environ. Res., 159, 427–434, https://doi.org/10.1016/j.envres.2017.08.039, 2017. a
Altmann, A., Toloşi, L., Sander, O., and Lengauer, T.: Permutation importance: a corrected feature importance measure, Bioinformatics, 26, 1340–1347, https://doi.org/10.1093/bioinformatics/btq134, 2010. a
Bai, Y., Li, Y., Zeng, B., Li, C., and Zhang, J.: Hourly PM2.5 concentration forecast using stacked autoencoder model with emphasis on seasonality, J. Clean. Prod., 224, 739–750, 2019. a
Bartier, P. M. and Keller, C.: Multivariate interpolation to incorporate thematic surface data using inverse distance weighting (IDW), Comput. Geosci., 22, 795–799, https://doi.org/10.1016/0098-3004(96)00021-0, 1996. a
Bey, I., Jacob, D. J., Yantosca, R. M., Logan, J. A., Field, B. D., Fiore, A. M., Li, Q., Liu, H. Y., Mickley, L. J., and Schultz, M. G.: Global modeling of tropospheric chemistry with assimilated meteorology: Model description and evaluation, J. Geophys. Res.-Atmos., 106, 23073–23095, https://doi.org/10.1029/2001JD000807, 2001. a
Short summary
This study proposes a regional feature selection-based machine learning system to predict short-term air quality in China. The system has a tool that can figure out the importance of input data for better prediction. It provides large-scale air quality prediction that exhibits improved interpretability, fewer training costs, and higher accuracy compared with a standard machine learning system. It can act as an early warning for citizens and reduce exposure to PM2.5 and other air pollutants.