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.

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

Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model

no code implementations • 10 Sep 2019 • David John Gagne II, Hannah M. Christensen, Aneesh C. Subramanian, Adam H. Monahan

Some of the GAN configurations perform better than a baseline bespoke parameterization at both timescales, and the networks closely reproduce the spatio-temporal correlations and regimes of the Lorenz '96 system.

BIG-bench Machine Learning Generative Adversarial Network