There is a newer version of the record available.

Published January 18, 2023 | Version v2
Dataset Open

Code and partial data for "Representing sub-grid processes in weather and climate models via sequence learning"

Authors/Creators

  • 1. Danish Meteorological Institute

Contributors

  • 1. European Centre for Medium Range Weather Forecasts

Description

This repository contains the RNN training and evaluation code used in the paper Representing sub-grid processes in weather and climate models via sequence learning. Three parameterization problems from earlier studies are included (we have modified the code from these papers to incorporate RNNs): 

  • non-orographic gravity wave drag (Chantry et al. 2021) 
    • Based on TensorFlow
    • This repository uses the CliMetLab plugin and downloads the data from the European Weather Cloud
  • non-local parameterization (Wang et al. 2022)
    • The new code is based on TensorFlow, so you'll need both PyTorch and TensorFlow to run everything
    • See original paper for data access
  • moist physics (Han et al. 2023, 2020) 
    • Based on TensorFlow. This one has the most additions, e.g. code to generate a TensorFlow TFRecord dataset from the raw netCDF data archived in the original paper
    • See original paper for data access

Each of the code repos (unpack the tars) have an updated README.

References:

Chantry, M., Hatfield, S., Dueben, P., Polichtchouk, I., & Palmer, T. (2021). Machine learning emulation of gravity wave drag in numerical weather forecasting. Journal of Advances in Modeling Earth Systems, 13(7), e2021MS002477
 
Han, Y., Zhang, G. J., Huang, X., & Wang, Y. (2020). A moist physics parameterization based on deep learning. Journal of Advances in Modeling Earth Systems, 12(9), e2020MS002076.
 
Han, Y., Zhang, G. J., & Wang, Y. (2023). An ensemble of neural networks for moist physics processes, its generalizability and stable integration. Journal of Advances in Modeling Earth Systems, 15(10), e2022MS003508
 
Wang, P., Yuval, J., & O’Gorman, P. A. (2022). Non‐local parameterization of atmospheric subgrid processes with neural networks. Journal of Advances in Modeling Earth Systems, 14(10), e2022MS002984.
 

Files

Files (211.1 MB)

Name Size Download all
md5:99605137e5851a7e75ee5de2f0fb9731
89.9 MB Download
md5:cd6b9f6bef6441ade2d8934ca3280ef0
58.8 MB Download
md5:811c9c46a52d5cc8d176b2154f306325
62.4 MB Download