Training and Testing Data, Associated Code, and WRF Code for ML-based nonhydrostatic alternative scheme in dynamical core of atmosphere

Data and codes for a nonhydrostatic alternative scheme (NAS) in dynamical core of atmosphere based on machine learning.

In this new version, the randomly sampled training data samples testing data samples from nonhydrostatic simulations in WRF baraclinic wave test are provided. They are processed into a new data structure, which can be directly utilized in training and testing. 

Follow the instructions in README.txt and download the training and testing data, and the associated codes.

Here we provide 3 parts of data and codes:

1, Training and testing data from WRF;

2, Training and testing codes for two machine learning emulators: machine learning and neural network

3, WRF application.