Training and Testing Data, Associated Code, and SCAM Validations Code and Data for ResNet in moist physics (ResCu)

<p>Data and codes for a deep convolutional residual neural network moist physics parameterization (ResCu).</p> <p>In this new version, the&nbsp;randomly selected training data samples and part of testing data samples (June, July&nbsp;and August) are provided. They are processed&nbsp;into a new data structure, which can be directly utilized in training and testing.&nbsp;For the entire second&nbsp;year training samples and&nbsp;the entire third year testing samples, we provide them in a repository at&nbsp;Dryad&nbsp;(<a href="https://doi.org/10.6075/J0CZ35PP">https://doi.org/10.6075/J0CZ35PP</a> and https://doi.org/10.6075/J03J3BGF).</p> <p>Please download and decompress ResCu_Han_et_al_JAMES.tar.gz.</p> <p>Follow the instructions in README.txt and download the training and testing data (The Dryad depositary is provided in the description).&nbsp;</p> <p>Here we provide 3 parts of data and codes:</p> <p>1, Training and testing data from SPCAM;</p> <p>2, Training and testing codes for ResCu and many other NN architectures;</p> <p>3, SCAM validations.</p> <p>&nbsp;</p>