Improving PM2.5 Forecasts in WRF-Chem-v3.6.1 over China through a Deep Learning-based Emission Source Inversion Method

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Xingxing Ma, Yi Zhang, Zhen Peng
DOI: 10.5281/zenodo.18185599
Cited by: 0

Abstract

emission_inversion.tar.gz repository provides code accopanying the paper.This project employs a MDS-3DUNet architecture to replace the EnKF methods in the emission source inversion. The model is used as a deep learning-based emission source inversion method for PM2.5 and other emission species. WRF-chem3.6.1 software was also uploaded.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
8 January 2026
Document type
Dataset