Articles | Volume 21, issue 22
Research article
24 Nov 2021
Research article |  | 24 Nov 2021

Estimation of the vertical distribution of particle matter (PM2.5) concentration and its transport flux from lidar measurements based on machine learning algorithms

Yingying Ma, Yang Zhu, Boming Liu, Hui Li, Shikuan Jin, Yiqun Zhang, Ruonan Fan, and Wei Gong

Related authors

Measurement report: Assessing the impacts of emission uncertainty on aerosol optical properties and radiative forcing from biomass burning in peninsular Southeast Asia
Yinbao Jin, Yiming Liu, Xiao Lu, Xiaoyang Chen, Ao Shen, Haofan Wang, Yinping Cui, Yifei Xu, Siting Li, Jian Liu, Ming Zhang, Yingying Ma, and Qi Fan
Atmos. Chem. Phys., 24, 367–395,,, 2024
Short summary
Extending wind profile beyond the surface layer by combining physical and machine learning approaches
Boming Liu, Xin Ma, Jianping Guo, Hui Li, Shikuan Jin, Yingying Ma, and Wei Gong
EGUsphere,,, 2023
Short summary
A comprehensive reappraisal of long-term aerosol characteristics, trends, and variability in Asia
Shikuan Jin, Yingying Ma, Zhongwei Huang, Jianping Huang, Wei Gong, Boming Liu, Weiyan Wang, Ruonan Fan, and Hui Li
Atmos. Chem. Phys., 23, 8187–8210,,, 2023
Short summary
Estimating hub-height wind speed based on a machine learning algorithm: implications for wind energy assessment
Boming Liu, Xin Ma, Jianping Guo, Hui Li, Shikuan Jin, Yingying Ma, and Wei Gong
Atmos. Chem. Phys., 23, 3181–3193,,, 2023
Short summary
Performance evaluation for retrieving aerosol optical depth from the Directional Polarimetric Camera (DPC) based on the GRASP algorithm
Shikuan Jin, Yingying Ma, Cheng Chen, Oleg Dubovik, Jin Hong, Boming Liu, and Wei Gong
Atmos. Meas. Tech., 15, 4323–4337,,, 2022
Short summary

Related subject area

Subject: Aerosols | Research Activity: Remote Sensing | Altitude Range: Troposphere | Science Focus: Physics (physical properties and processes)
Opinion: Aerosol remote sensing over the next 20 years
Lorraine A. Remer, Robert C. Levy, and J. Vanderlei Martins
Atmos. Chem. Phys., 24, 2113–2127,,, 2024
Short summary
Monitoring biomass burning aerosol transport using CALIOP observations and reanalysis models: a Canadian wildfire event in 2019
Xiaoxia Shang, Antti Lipponen, Maria Filioglou, Anu-Maija Sundström, Mark Parrington, Virginie Buchard, Anton S. Darmenov, Ellsworth J. Welton, Eleni Marinou, Vassilis Amiridis, Michael Sicard, Alejandro Rodríguez-Gómez, Mika Komppula, and Tero Mielonen
Atmos. Chem. Phys., 24, 1329–1344,,, 2024
Short summary
Thermal infrared observations of a western United States biomass burning aerosol plume
Blake T. Sorenson, Jeffrey S. Reid, Jianglong Zhang, Robert E. Holz, William L. Smith Sr., and Amanda Gumber
Atmos. Chem. Phys., 24, 1231–1248,,, 2024
Short summary
A new look into the impacts of dust radiative effects on the energetics of tropical easterly waves
Farnaz Hosseinpour and Eric M. Wilcox
Atmos. Chem. Phys., 24, 707–724,,, 2024
Short summary
Wind-driven emissions of coarse-mode particles in an urban environment
Markus D. Petters, Tyas Pujiastuti, Ajmal Rasheeda Satheesh, Sabin Kasparoglu, Bethany Sutherland, and Nicholas Meskhidze
Atmos. Chem. Phys., 24, 745–762,,, 2024
Short summary

Cited articles

Altman, N. S.: An introduction to kernel and nearest-neighbor nonparametric regression, Am. Stat., 46, 175–185, 1992. 
Belmonte Rivas, M. and Stoffelen, A.: Characterizing ERA-Interim and ERA5 surface wind biases using ASCAT, Ocean Sci., 15, 831–852,, 2019. 
Boyouk, N., Léon, J. F., Delbarre, H., Podvin, T., and Deroo, C.: Impact of the mixing boundary layer on the relationship between PM2.5 and aerosol optical thickness, Atmos. Environ., 44, 271–277, 2010. 
Breiman, L.: Random forests, in: Machine Learning, 45, 5–32, 2001. 
Cao, L.: Support vector machines experts for time series forecasting, Neurocomputing, 51, 321–339, 2003. 
Short summary
The vertical distribution of the aerosol extinction coefficient (EC) measured by lidar systems has been used to retrieve the profile of particle matter with a diameter of less than 2.5 μm (PM2.5). However, the traditional linear model cannot consider the influence of multiple meteorological variables sufficiently, which then causes low inversion accuracy. In this study, the machine learning algorithms which can input multiple features are used to solve this constraint.
Final-revised paper