FTorch Case Studies

  • Jack Atkinson
  • Last Updated: November 2026

FTorch has been deployed in a number of scientific projects. This page collates the examples we are aware of. If you have a case study you'd like to see listed here, please get in touch or open a pull request to add it!

If you make use of FTorch in your work please cite our publication:

Atkinson et al., (2025). FTorch: a library for coupling PyTorch models to Fortran.
Journal of Open Source Software, 10(107), 7602, https://doi.org/10.21105/joss.07602


Papers and Projects using FTorch

2026

  • Recurrent neural network constitutive model for human rib cortical bone, deployed in the LS-DYNA explicit FEM solver through user-defined material subroutines - DOI: 10.1016/j.cma.2026.119532
  • GRIST-MPS - ML physics parameterisation suite trained on storm-resolving simulations, coupled to the GRIST GCM for stable six-year AMIP runs - DOI: 10.5194/gmd-19-5553-2026
  • NLML neural network emulator of the exact nonlinear interactions, coupled online into the WAVEWATCH III wave model - DOI: 10.1029/2025JH000699
  • From stable online coupling to decade-long climate simulations with an ML cloud microphysics parameterisation in ICON - DOI: 10.1088/3049-4753/ae9e2e
  • Collaborative neural networks for global aerosol retrievals from multi-angle polarimeters, interfaced with the Fortran-based RemoTAP retrieval core - DOI: 10.1109/TGRS.2026.3685881
  • Testing winning parameterisation entries from the offline ClimSim Kaggle competition for online performance in a multi-scale model, coupled with an FTorch binding - DOI: 10.1029/2025MS005643
  • Beyond the training data: confidence-guided mixing of parameterisations in a hybrid AI-climate model (ICON) - DOI: 10.1029/2025MS005544
  • Finetuning AI foundation models for subgrid-scale parameterisations (atmospheric gravity waves case study) - DOI: 10.1029/2025MS005075
  • Review paper of hybrid modelling approaches for cloud microphysics - DOI: 10.1029/2025MS005341

2025

2024

  • Convection parameterisations in ICON - Implementing machine-learnt convection parameterisations in the ICON atmospheric model showing that best online performance occurs when causal relations are eliminated from the net. See Heuer et al (2024) - DOI: 10.1029/2024MS004398
  • DataWave CAM-GW - Using FTorch to couple neural net parameterisations of gravity waves to the CAM atmospheric model.
  • MiMA Machine Learning - Implementing a neural net parameterisation of gravity waves in the MiMA atmospheric model. Demonstrates that nets trained near-identically offline can display greatly varied behaviours when coupled online. See Mansfield and Sheshadri (2024) - DOI: 10.1029/2024MS004292