Could machine learning break the convection parametrization deadlock?

This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint.


Download Preprint

Supplementary Files

Pierre Gentine, Mike Pritchard, Stephan Rasp, Gael Reinaudi, Galen Yacalis


Modeling and representing moist convection in coarse-scale climate models remains one of the main bottlenecks of current climate simulations. Many of the biases present with parameterized convection are strongly reduced when convection is explicitly resolved (in cloud resolving models at high spatial resolution ~ a kilometer or so). We here present a novel approach to convective parameterization based on machine learning over an aquaplanet with prescribed sea surface temperatures. The machine learning is trained over a superparameterized version of a climate model in which convection is resolved by an embedded 2D cloud resolving models. The machine learning representation of convection, called Cloud Brain (CBRAIN) replicates many of the convective features of the superparameterized climate model, yet reduces its inherent stochasticity. The approach presented here opens up a new possibility and a first step towards better representing convection in climate models and reducing uncertainties in climate predictions.



Atmospheric Sciences, Oceanography and Atmospheric Sciences and Meteorology, Physical Sciences and Mathematics, Physics, Planetary Sciences


machine learning, Precipitation, convection, Clouds


Published: 2018-03-16 12:26

Last Updated: 2018-04-09 13:17

Older Versions

Academic Free License (AFL) 3.0

Add a Comment

You must log in to post a comment.


There are no comments or no comments have been made public for this article.