The climate prediction models have faced many challenges while accurately representing the clouds, moistening and heating of atmospheres. It is indeed necessary for the policymakers to accurately monitor predictions about global warming in addition to the rising concentrations of the greenhouse gases. The most prominent example of this is the Paris Climate Agreement.

The research paper regarding this study is published online in Geophysical Research Letters. Pierre Gentine leads the team of researchers. Pierre is an associate professor of Earth and Environmental Engineering at the Columbia Engineering. The research team demonstrated that the shortcomings of the climate prediction models could be tackled with the assistance of machine learning techniques. Such machine learning techniques possess the calibre to represent the clouds with coarse resolution climate models. The coarse resolution is approximated at hundred kilometres. Coarse Resolution Climate Models are potent enough to narrow down the prediction range.

Gentine says, “This could be a real game-changer for climate prediction. We have large uncertainties in our prediction of the response of the Earth’s climate to rising concentrations of the greenhouse gases. The primary reason is the representation of clouds and how they respond to a change in those gases. 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.” Gentine is the member of Earth Institute and Data Science Institute. He is also the lead author of the current research study.

The researchers make the use of an idealised setup as a proof for their novel approach. The idealised configuration is inclusive of an aqua planet, or a planet accompanied with continents.
Gentine concludes, “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.”