Machine learning techniques could help create accurate predictions of global warming by better representing clouds, a new study has found.
A major challenge in current climate prediction models is how to accurately represent clouds and their atmospheric heating and moistening.
By studying clouds, it is possible to predict global and regional climate’s response to rising greenhouse gas concentrations.
Now, a paper has shown machine learning techniques could be used to tackle this issue and better represent clouds in coarse resolution climate models, with the potential to narrow the range of prediction.
“This could be a real game-changer for climate prediction,” commented Pierre Gentine from Columbia Engineering in New York and lead author of the paper. “Our study shows that machine-learning techniques help us better represent clouds and thus better predict global and regional climate’s response to rising greenhouse gas concentrations.”
The researchers used the idealized setup of an aquaplanet, or a planet with continents, as a proof of concept for their novel approach to convective parameterization based on machine learning, explained a statement.
They trained a deep neural network to learn from a simulation that explicitly represents clouds. Dubbed Cloud Brain (CBRAIN), the machine-learning representation of clouds could skillfully predict many of the cloud heating, moistening and radiative features that are essential to climate simulation.
Because global temperature sensitivity to CO2 is strongly linked to cloud representation, CBRAIN may also improve estimates of future temperature. According to the statement, the researchers have tested this in fully coupled climate models and have demonstrated very promising results, showing that this could be used to predict greenhouse gas response.
Gentine added: “Our approach may open up a new possibility for a future of model representation in climate models, which are data driven and are built ‘top-down,’ that is, by learning the salient features of the processes we are trying to represent.”
Photo credit: Bryan Jones/ CC BY-NC-ND 2.0