FTorch

Brief description

It is desirable to be able to run machine learning (ML) models directly in Fortran. ML models are often trained in some other language (say, Python) using a popular frameworks (say, PyTorch) and saved. We want to run inference on this model without having to call a Python executable. To achieve this we use the existing Torch C++ interface, libtorch.

FTorch provides a library enabling a user to directly couple their PyTorch models to Fortran code. There are also installation instructions for the library and examples of performing coupling.

We support running on both CPU and GPU, and have tested the library on UNIX and Windows based operating systems

Presentations

The following presentations contain information about FTorch:

• Reducing the overheads for coupling PyTorch machine learning models to Fortran
  ML & DL Seminars, LSCE, IPSL, Paris - November 2023
  Slides - Recording
• Reducing the Overhead of Coupled Machine Learning Models between Python and Fortran
  RSECon23, Swansea - September 2023
  Slides - Recording

License

The FTorch source code, related files and documentation are distributed under an MIT License which can be viewed here.

Projects using FTorch

The following projects make use of FTorch.
If you use our library in your work please let us know.

• M2LInES CAM-ML - Using FTorch to couple a neural net parameterisation of convection to the CAM atmospheric model in CESM.
• DataWave CAM-GW - Using FTorch to couple neural net parameterisations of gravity waves to the CAM atmospheric model.
• MiMA Machine Learning - Using FTorch to couple a neural net parameterisation of gravity waves to the MiMA atmospheric model. See Mansfield and Sheshadri (2024) - DOI: 10.1029/2024MS004292
• Convection parameterisations in ICON - Implementing machine learnt convection parameterisations in the ICON atmospheric model. See Heuer et al (2023) - DOI: 10.48550/arXiv.2311.03251