04 Oct 2022
 | 04 Oct 2022

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

Raghul Parthipan, Hannah M. Christensen, J. Scott Hosking, and Damon J. Wischik

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.

Raghul Parthipan et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Raghul Parthipan et al.

Model code and software

Model code Raghul Parthipan

Raghul Parthipan et al.


Total article views: 738 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
581 144 13 738 2 4
  • HTML: 581
  • PDF: 144
  • XML: 13
  • Total: 738
  • BibTeX: 2
  • EndNote: 4
Views and downloads (calculated since 04 Oct 2022)
Cumulative views and downloads (calculated since 04 Oct 2022)

Viewed (geographical distribution)

Total article views: 735 (including HTML, PDF, and XML) Thereof 735 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 07 Jun 2023
Short summary
How can we create better climate models? We tackle this by proposing a data-driven successor to the existing approach for capturing key temporal trends in climate models. We combine probability, allowing us to represent uncertainty, with machine learning, a technique to learn relationships from data which are undiscoverable to humans. Our model is often superior to existing baselines when tested in a simple atmospheric simulation.