predict extreme events more frequently in new ways

NEW YORK, NY — May 23, 2023 — With a warming climate making extreme weather more frequent, accurate forecasting has become more important for all of us, from farmers to city dwellers to businesses around the world. I’m here. . To date, climate models have not been able to accurately predict precipitation intensity, especially extreme precipitation intensity. In nature, precipitation is highly variable and there are many extremes of precipitation, but climate models are biased toward light precipitation and predict smaller variations in precipitation.

The Missing Piece of Current Algorithms: Cloud Organizations

Researchers have worked to develop algorithms to improve prediction accuracy, columbia engineering Climate scientists report that information is missing in traditional climate model parameterization, which is a way to describe cloud structure and organization, at such a fine scale that it is used It cannot be captured by computational grids. These tissue measurements influence predictions of both precipitation intensity and its stochasticity, that is, the variability of random fluctuations in precipitation intensity. Until now, there has been no effective and accurate way to measure cloud structure and quantify its impact.

new research from a team led by Pierre Jeantinedirector of Learning the Earth through Artificial Intelligence and Physics (LEAP) Centerused global storm resolution simulations and machine learning to create algorithms that can independently handle two different scales of cloud organizations: those that are resolved by climate models and those that are too small to be resolved. This new approach addresses missing information in traditional climate model parameterizations and provides a way to more accurately predict precipitation intensity and variability.

“Our findings are of particular interest because the scientific community has long debated whether cloud texture should be included in climate models,” said Maurice Ewing, Professor Genting of the Department of Geophysics, J. Professor Lamar Worzel said: Global Environmental Engineering and a member of the Global Environmental Sciences. Data Science Institute. “Our study answers the debate and provides a new solution for including organization, and shows that the inclusion of this information can significantly improve predictions of precipitation intensity and variability.”

Design neural network algorithms with AI

Sarah Shamekh, a PhD student working with Gentine, has developed a neural network algorithm that learns relevant information about the role of fine-scale cloud texture (unresolved scale) in precipitation. Since Shamekh did not define any metrics or formulas beforehand, she implicitly learns how to measure cloud clustering, an organizational metric, and uses this metric to improve precipitation forecasts. . Shamekh trained an algorithm on high-resolution water fields to encode the degree of small-scale organization.

“We find that our institutional measure accounts for precipitation variability almost completely and can replace stochastic parameterization in climate models,” said the study’s first author. said Shamek. PNAS. “The inclusion of this information has significantly improved precipitation projections at scales relevant to climate models, allowing them to accurately predict extreme precipitation and spatial variability.”

Machine learning algorithms improve future predictions

Researchers are now using machine learning approaches in climate models that implicitly learn subgrid cloud organization metrics. This will greatly improve predictions of precipitation intensity and variability, including extreme precipitation events, and enable scientists to better predict future changes in the hydrological cycle and extreme weather patterns in a warming climate.

How it will be done in the future

The study also opens up new avenues for investigation, such as exploring the possibility that precipitation can create memories, in which the atmosphere retains information about recent weather conditions and influences subsequent atmospheric conditions in the climate system. increase. This new approach has potential for a wide range of applications beyond precipitation modeling, such as better modeling of ice sheets and sea levels.

###

About research

The title of this study is “Implicit Learning of Convective Organizations Explains Precipitation Probability”.

Authors: Sarah Shamek, Kara Lam, Yu Fan, Pierre Jeantine

Department of Global Environmental Engineering, Columbia University, New York, NY, USA

This work was supported by: SS and PG acknowledged funding from the European Research Council grant USMILE, the Schmidt Future project M2LiNES, and the National Science Foundation Science and Technology Center (STC) Artificial Intelligence and Learning the Earth in Physics (LEAP), Award 2019625 -STC. KDL acknowledges support from LEAP and DOE grant DE-SC0022323 “Discovering Physically Meaningful Structures from Extreme Climate Data”.

The authors declare no financial or other conflicts of interest.

###

Link:

Paper: https://www.pnas.org/doi/10.1073/pnas.2216158120

DOI: 10.1073/pnas.2216158120