A major challenge in current climate prediction models is how to accurately represent clouds and their atmospheric heating and moistening. This challenge is behind the wide spread in climate prediction. Yet accurate predictions of global warming in response to increased greenhouse gas concentrations are essential for policy-makers (e.g. the Paris climate agreement).
In a paper recently published online in American Geophysical Union (May 23), researchers led by Pierre Gentine, associate professor of earth and environmental engineering at Columbia Engineering, demonstrate that machine learning techniques can be used to tackle this issue and better represent clouds in coarse resolution (~100km) climate models, with the potential to narrowing the range of prediction.
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 an idealized setup (an aquaplanet, or a planet with continents) as a proof of concept for their novel approach to convective parameterization based on machine learning. They trained a deep neural network to learn from a simulation that explicitly represents clouds. The machine-learning representation of clouds, which they named the Cloud Brain (CBRAIN), could skillfully predict many of the cloud heating, moistening, and radiative features that are essential to climate simulation.
Gentine notes, “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.”
The researchers also note that, because global temperature sensitivity to CO2 is strongly linked to cloud representation, CBRAIN may also improve estimates of future temperature. They 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.
The Latest on: Climate prediction
via Google News
The Latest on: Climate prediction
Sri Lankan farmers’ traditional knowledge and climate change predictions
on July 16, 2018 at 11:30 am
“If eagles and grey hornbills are flying above their normal height in the sky, it signals that rain is expected soon; if seagulls are flying close to the ground, it suggests that there will be heavy r... […]
Evaluating the Accuracy of Seasonal Climate Predictions
on July 12, 2018 at 5:11 am
An analysis of historical modeling outputs is improving our understanding of the relationships between different types of seasonal forecasting skills. Source: Journal of Geophysical Research: Atmosphe... […]
Jet stream discovery may lead to better weather predictions
on July 11, 2018 at 4:03 pm
New research reveals a physical link between the speed and location of the jet stream and the strength of the polar vortex, a swirl of air that usually hovers over the Arctic. If you can predict the p... […]
What’s the Zululand weather prediction?
on July 5, 2018 at 6:25 am
ZULULANDERS throughout the region have been pulling their warmest winter pj’s from storage, and loading up on extra blankets at night – and the cold snap may continue for a few more days. Our beautifu... […]
Climate predictions should include impacts of CO2 on life
on June 29, 2018 at 10:26 am
Climate change predictions are not taking account of the full range of possible effects of rising carbon dioxide levels, researchers say. Scientists currently use models in which warming of 1.5°C coin... […]
30 years later, deniers are still lying about Hansen’s amazing global warming prediction
on June 25, 2018 at 3:12 am
Hansen’s 1988 global climate model was almost spot-on. The incredible accuracy of Hansen’s climate model predictions debunks a number of climate denier myths. It shows that climate models are accurate ... […]
Machine learning may be a game-changer for climate prediction
on June 20, 2018 at 5:00 am
A major challenge in current climate prediction models is how to accurately represent clouds and their atmospheric heating and moistening. This challenge is behind the wide spread in climate predictio... […]
TempoQuest Weather Prediction Software Achieves HPC Performance Breakthrough
on June 1, 2018 at 2:37 am
TempoQuest Weather Prediction Software Achieves HPC Performance Breakthrough Weather start-up leverages cutting-edge NVIDIA GPU technology to achieve revolutionary speed for the most widely used weath... […]
via Bing News