Top-down estimates of anthropogenic NO x emissions over China through a new zone-stratified RF machine learning model

Yin Huang; Yi Wang; Jun Wang; Minghui Tao; Meng Zhou; Jhoon Kim; Lunche Wang

doi:10.1016/j.envpol.2026.128202

Back

Top-down estimates of anthropogenic NO x emissions over China through a new zone-stratified RF machine learning model

Journal article

Peer reviewed

Top-down estimates of anthropogenic NO x emissions over China through a new zone-stratified RF machine learning model

Yin Huang, Yi Wang, Jun Wang, Minghui Tao, Meng Zhou, Jhoon Kim and Lunche Wang

Environmental pollution (1987), Vol.400, 128202

07/01/2026

DOI: 10.1016/j.envpol.2026.128202

PMID: 42055207

View Online

Abstract

This study designs a new zone-stratified Random Forest (RF) machine learning model to estimate monthly anthropogenic NOx emissions over China at the spatial resolution of 0.25° × 0.25°. Zone-stratified RF divides China into different emission zones to estimate anthropogenic NOx emissions separately, thereby showing the improvement over the unstratified RF that is applied for the whole study domain and resulted in apparent overestimation at high emission regions and underestimation at low emission regions. In the training, Multi-resolution Emission Inventory for China (MEIC) anthropogenic NOx emission inventory is used as a target, while features include Tropospheric Monitoring Instrument (TROPOMI) tropospheric NO2 Vertical Column Density (VCD), fifth generation ECMWF reanalysis meteorological data, Infrared Imaging Radiometer Suite nighttime light data, and WorldPop Global Project Population data. Once trained for 2019, the zone-stratified RF model is further applied in other years for independent evaluation. Total anthropogenic NOx emission estimates over China in 2020 from zone-stratified RF is 20.6 Tg, comparable to 19.7 Tg from MEIC, and the difference between them is less than 0.1 Tg for 27 provinces. Additionally, the nationwide mean difference is 0.04 Tg, corresponding to an average error of 8.6%. The pronounced urban-rural emission gradient in MEIC is accurately reproduced by zone-stratified RF, but not by unstratified RF. Furthermore, over Taiwan province where MEIC data is not available for the training, the trained zone-stratified RF model estimate of anthropogenic NOx emissions exhibit good agreement of spatial pattern with Emissions Database for Global Atmospheric Research (EDGAR). Temporally, zone-stratified RF also identifies emission reduction during COVID-19 lockdown in Taiwan. Overall, zone-stratified RF is effective for rapid update and projection of NOx emissions.

Machine Learning

anthropogenic NO(x) emissions

zone-stratified

random forest

top-down

Details

Title: Subtitle: Top-down estimates of anthropogenic NO x emissions over China through a new zone-stratified RF machine learning model
Creators: Yin Huang - China University of Geosciences
Yi Wang - China University of Geosciences
Jun Wang - University of Iowa
Minghui Tao - China University of Geosciences
Meng Zhou - Goddard Space Flight Center
Jhoon Kim - Yonsei University
Lunche Wang - China University of Geosciences
Resource Type: Journal article
Publication Details: Environmental pollution (1987), Vol.400, 128202
DOI: 10.1016/j.envpol.2026.128202
PMID: 42055207
NLM abbreviation: Environ Pollut
ISSN: 0269-7491
eISSN: 1873-6424
Publisher: Elsevier
Grant note: National Natural Science Founda-tion of China: 42201409
This research was funded by the National Natural Science Founda-tion of China (Grant No. 42201409) .
Language: English
Electronic publication date: 04/27/2026
Date published: 07/01/2026
Academic Unit: Electrical and Computer Engineering; Civil and Environmental Engineering; Iowa Technology Institute; Physics and Astronomy; Chemical and Biochemical Engineering
Record Identifier: 9985157587102771

Metrics

3 Record Views