Estimation method of atmospheric particulate matter mass concentration based on machine learning and multi-source data

YANG Huirong; HE Nanteng; BU Lingbing; MO Zusi; FAN Zengchang; ZHOU Xiaomeng; SU Xin

doi:10.3969/j.issn.1673-6141.2025.02.006

Journal of Atmospheric and Environmental Optics, Volume. 20, Issue 2, 176(2025)

Estimation method of atmospheric particulate matter mass concentration based on machine learning and multi-source data

YANG Huirong^1,2, HE Nanteng^1,2, BU Lingbing^1,2、*, MO Zusi^1,2, FAN Zengchang^1,2, ZHOU Xiaomeng^1,2, and SU Xin^1,2

¹Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological Administration, Nanjing University of Information Science and Technology, Nanjing 210044, China

²School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing 210044, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Flow chart of model building

Download full size

View in Article

Fig. 2. Rank of importance of input factors. (a) PM_2.5 under clean background; (b) PM_2.5 under polluted background;(c) PM₁₀ under clean background; (d) PM₁₀ under polluted background

Fig. 3. [in Chinese]

Fig. 4. Optimal factor verification results of ML models. (a) Clean environment (RF model: 8 and 9 input factors for PM_2.5 and PM₁₀ respectively); (b) polluted environment (GRNN model: 6 and 8 input factors for PM_2.5 and PM₁₀ respectively)

Download full size

View in Article

Fig. 5. Horizontal distribution of PM_2.5 (a) and PM₁₀ (b) mass concentration estimated by optimal ML model (19:00, December 21, 2021, Beijing time)

Download full size

View in Article

Fig. 6. Comparison between the data of the state Control site and the model inversion data for PM_2.5 (a) and PM₁₀ (b)

Download full size

View in Article

Table 1. Optimal model and number of input factors under different conditions
View table
View in Article
Table 1. Optimal model and number of input factors under different conditions
Particulate matter in different environments Optimization model Number of optimal input factors
PM₁₀ (clean) RF 9
PM_2.5 (clean) RF 8
PM₁₀ (polluted) GRNN 8
PM_2.5 (polluted) GRNN 6

Table 2. Models used in different backgrounds and their verification results

View table

View in Article

Table 2. Models used in different backgrounds and their verification results

Particulate matter in different environments	Optimization model	Number of optimal input factors	$R^{2}$	$E_{M A}$ /(μg·m^-3)	$E_{R M S}$ /(μg·m^-3)
PM₁₀ (clean)	RF	9	0.73	10.02	13.79
PM_2.5 (clean)	RF	8	0.84	7.43	10.98
PM₁₀ (polluted)	GRNN	8	0.76	13.18	17.76
PM_2.5 (polluted)	GRNN	6	0.88	8.87	13.80

Tools

Get Citation

Copy Citation Text

Huirong YANG, Nanteng HE, Lingbing BU, Zusi MO, Zengchang FAN, Xiaomeng ZHOU, Xin SU. Estimation method of atmospheric particulate matter mass concentration based on machine learning and multi-source data[J]. Journal of Atmospheric and Environmental Optics, 2025, 20(2): 176

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites