Explore open access research and scholarly works from NERC Open Research Archive

Advanced Search

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

Parthipan, Raghul ORCID: https://orcid.org/0000-0002-1949-0367; Christensen, Hannah M.; Hosking, J. Scott ORCID: https://orcid.org/0000-0002-3646-3504; Wischik, Damon J.. 2023 Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: a case study with the Lorenz 96 model. Geoscientific Model Development, 16 (15). 4501-4519. 10.5194/gmd-16-4501-2023

Abstract
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. Red noise is essential to many operational parameterization schemes, helping model temporal correlations. We show how to build on the successes of red noise by combining the known benefits of stochasticity with machine learning. This is done using a physically-informed recurrent neural network within a probabilistic framework. Our model is competitive and often superior to both a bespoke baseline and an existing probabilistic machine learning approach (GAN) when applied to the Lorenz 96 atmospheric simulation. This is due to its superior ability to model temporal patterns compared to standard first-order autoregressive schemes. It also generalises to unseen scenarios. We evaluate across a number of metrics from the literature, and also discuss the benefits of using the probabilistic metric of hold-out likelihood.
Documents
533330:203363
[thumbnail of Open Access]
Preview
Open Access
gmd-16-4501-2023.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (5MB) | Preview
Information
Programmes:
BAS Programmes 2015 > AI Lab (2022-)
Library
Statistics

Downloads per month over past year

More statistics for this item...

Metrics

Altmetric Badge

Dimensions Badge

Share
Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email
View Item