This repo is prepared for the submission of the ACP paper.
The following software dependencies are required.
Package | Version |
---|---|
Python | 3.6.3 |
TensorFlow | 2.1.0 |
CUDA | 8.0.44 |
cuDNN | 7.0 |
TensorFlow | 2.1.0 |
Keras | 2.3.1 |
A detailed list of packages installed while while testing and validating the model is provided in Unet_package_list.txt
.
- Training stage 1 involves TCR-2 surface NO2 concentrations and NOx emissions. Both could be found from the JPL TCR-2 website. Last access to the link was 4 October 2022.
- Training stage 2 involves in situ measurements from the China Ministry of Ecology and Environment (MEE) observation network (MEE website, last access: 18 February 2022).
- Both stages require meteorological fields from ERA5 on single levels and on pressure levels.
Examples of usage of the code are provided in the notebook example_code.ipynb
.
He, T.-L.; Jones, D. B. A.; Miyazaki, K; Bowman, K. W.; Jiang, Z.; Chen, X; Li, R.; Zhang, Y; Li, K. Inverse modeling of Chinese NOx emissions using deep learning: Integrating in situ observations with a satellite-based chemical reanalysis. Atmospheric Chemistry and Physics, 2022.