Machine Learning for Stochastic Parametrisation

no code implementations • 12 Feb 2024 • Hannah M. Christensen, Salah Kouhen, Greta Miller, Raghul Parthipan

Atmospheric models used for weather and climate prediction are traditionally formulated in a deterministic manner.

Taylorformer: Probabilistic Predictions for Time Series and other Processes

no code implementations • 30 May 2023 • Omer Nivron, Raghul Parthipan, Damon J. Wischik

We propose the Taylorformer for time series and other random processes.

Gaussian Processes Meta-Learning +1

Don't Waste Data: Transfer Learning to Leverage All Data for Machine-Learnt Climate Model Emulation

1 code implementation • 8 Oct 2022 • Raghul Parthipan, Damon J. Wischik

How can we learn from all available data when training machine-learnt climate models, without incurring any extra cost at simulation time?

Transfer Learning

Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: a case study with the Lorenz 96 model

1 code implementation • 28 Mar 2022 • Raghul Parthipan, Hannah M. Christensen, J. Scott Hosking, Damon J. Wischik

The modelling of small-scale processes is a major source of error in climate models, hindering the accuracy of low-cost models which must approximate such processes through parameterization.

BIG-bench Machine Learning