ITS1.3/CL0.1.18 | Interfacing machine learning and numerical modelling - challenges, successes, and lessons learned.
EDI
Interfacing machine learning and numerical modelling - challenges, successes, and lessons learned.
Convener: Jack AtkinsonECSECS | Co-conveners: Julien Le Sommer, Alessandro Rigazzi, Filippo GattiECSECS, Will ChapmanECSECS, Nishtha SrivastavaECSECS, Emily Shuckburgh

Machine learning (ML) is being used throughout the geophysical sciences with a wide variety of applications.
Advances in big data, deep learning, and other areas of artificial intelligence (AI) have opened up a number of new approaches.

Many fields (climate, ocean, NWP, space weather etc.) make use of large numerical models and are now seeking to enhance these by combining them with scientific ML/AI.
Examples include ML emulation of computationally intensive processes, training on high resolution models or data-driven parameterisations for sub-grid processes, and Bayesian optimisation of model parameters and ensembles amongst several others.

Doing this brings a number of unique challenges, however, including but not limited to:
- enforcing physical compatibility and conservation laws, and incorporating physical intuition into ML models,
- ensuring numerical stability,
- coupling of numerical models to ML frameworks and language interoperation,
- handling computer architectures and data transfer,
- adaptation/generalisation to different models/resolutions/climatologies,
- explaining, understanding, and evaluating model performance and biases.

Addressing these requires knowledge of several areas and builds on advances already made in domain science, numerical simulation, machine learning, high performance computing, data assimilation etc.

We solicit talks that address any topics relating to the above.
Anyone working to combine machine learning techniques with numerical modelling is encouraged to participate in this session.