Published February 14, 2020
| Version For JAMES reviews
Dataset
Restricted
Training and Testing Data, Associated Code, and SCAM Validations Code and Data for ResNet in moist physics
- 1. 1 Department of Earth System Science, Tsinghua University, Beijing, China
- 2. 2 Scripps Institution of Oceanography, La Jolla, CA USA
Description
Data and code for a deep convolutional residual neural network moist physics parameterization (ResNet-MP).
Here we provide 3 parts of data and code:
1, SPCAM setups and simulations;
2, ResNet-MP training and testing;
3, SCAM validations.
Please generate the training and testing data according to the instruction in README. We can't directly provide the 800 GB one-year independent testing data and 50 GB training data.
Files
Restricted
The record is publicly accessible, but files are restricted to users with access.