Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 15, issue 4
Articles | Volume 15, issue 4
https://doi.org/10.5194/gmd-15-1583-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-1583-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 15, issue 4
Development and technical paper
 | 
22 Feb 2022
Development and technical paper |  | 22 Feb 2022

Deep-learning spatial principles from deterministic chemical transport models for chemical reanalysis: an application in China for PM2.5

Baolei Lyu, Ran Huang, Xinlu Wang, Weiguo Wang, and Yongtao Hu

Supplement

https://doi.org/10.5194/gmd-15-1583-2022-supplement

Data sets

Global 30m land-cover products with fine classification system in 2015 L. Liu and X. Zhang https://doi.org/10.5281/zenodo.3986872

Model code and software

Chemical Reanalysis Model with Deep Learning from CTM simulations Baolei Lyu https://doi.org/10.5281/zenodo.5152567

Configurations for running 12 km resolution WRF-CMAQ simulations in China (v1.0) Yongtao Hu https://doi.org/10.5281/zenodo.5152621

Download
Short summary
Data fusion is used to estimate spatially completed and smooth reanalysis fields from multiple data sources of observations and model simulations. We developed a well-designed deep-learning model framework to embed spatial correlation principles of atmospheric physics and chemical models. The deep-learning model has very high accuracy to predict reanalysis data fields from isolated observation data points. It is also feasible for operational applications due to computational efficiency.
Read more