Code

Codes

Our codes are hosted on our Github repository.

• Code for Pyqg Parameterization benchmarks:

  • Pyqg_parameterization_benchmarks (Ross et al. 2022)

• Code for subgrid ML parameterizations:

  • Atmospheric Momentum Parametrization (Yuval and O’Gorman 2021): Neural Network Parameterization of subgrid momentum using SAM data
  • Ocean Momentum Parameterization (Guillaumin and Zanna 2021): Convolutional Neural Network subgrid momentum using CM2.6 data

• Implementation of ML parameterizations & numerical solvers:

  • Stochastic Deep Learning Parameterization: Online implementation of Guillaumin & Zanna in an idealized barotropic model
  • TorchQG: Differentiable quasi-geostrophic spectral solver in PyTorch with ML parameterizations
  • Parameterizations in pyqg : e.g., implementation of Zanna & Bolton 2020
  • MOM6 Implementation of data-driven parameterization: e.g., Zanna & Bolton 2020.

• Software Package

  • GCM-filter : software package filtering ocean model data, including in the presence of topography.

Upcoming codes will be linked to this repository as they become available.

Datasets

All of the datasets used in M²LInES publications will be made openly available. When possible, they will be hosted on Pangeo