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 to traditional problems.
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 techniques. Examples include ML emulation of computationally intensive processes, data-driven parameterisations for sub-grid processes, ML assisted calibration and uncertainty quantification of parameters, amongst other applications.
Doing this brings a number of unique challenges, however, including but not limited to:
- enforcing physical compatibility and conservation laws, and incorporating physical intuition,
- 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.
- quantifying uncertainties and their sources
- tuning of physical or ML parameters after coupling to numerical models (derivative-free optimisation, Bayesian optimisation, ensemble Kalman methods, etc.)
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.
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 techniques. Examples include ML emulation of computationally intensive processes, data-driven parameterisations for sub-grid processes, ML assisted calibration and uncertainty quantification of parameters, amongst other applications.
Doing this brings a number of unique challenges, however, including but not limited to:
- enforcing physical compatibility and conservation laws, and incorporating physical intuition,
- 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.
- quantifying uncertainties and their sources
- tuning of physical or ML parameters after coupling to numerical models (derivative-free optimisation, Bayesian optimisation, ensemble Kalman methods, etc.)
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.