Online training of large-scale Fortran-based hybrid computational science models, with applications in climate science ====================================================================================================================== [Co-PI with `Jack Atkinson `__.] `FTorch `__ is a library for coupling PyTorch models to Fortran. This is done by interfacing Fortran with the `libtorch` C++ backend underlying PyTorch, via the `iso_c_binding` module, which has been intrinsic to Fortran since the 2003 standard. It's an interesting project to work on, as it involves working with code in Python, C, C++, and Fortran, amongst other languages, software frameworks, and tools used for testing, linting, scripting, and documentation. Development tasks """"""""""""""""" * Set up online training in FTorch. * Expose PyTorch's Autograd functionality in FTorch, meaning gradient values can be tracked across mathematical operations acting on Torch Tensors. Community tasks """"""""""""""" * Organise and run a `workshop `__ on best practices for integrating machine learning into large-scale scientific modelling frameworks. * Research visits to assist collaborators with integrating online training into their ML workflows. * Integrate FTorch into the `Community Earth System Model (CESM) `__ build system on the high-performance computing system at the `National Center for Atmospheric Research (NCAR) `__. * Give FTorch tutorials on several occasions, including at `Durham HPC Days 2025 `_. Project information """"""""""""""""""" This work is currently underway as an RSE at the `Institute of Computing for Climate Science (ICCS) `__. It was supported by both ICCS and by a `joint grant `__ from the `Cambridge Centre for Data-Driven Discovery (C2D3) `__ and `ai@cam `__'s `Accelerate Programme `__. Outputs """"""" * FTorch software description paper: :cite:`AE25`.