Wednesday , October 27 2021

Artificial intelligence can be set up to reveal turning points about climate change


climate change

Credit: Unsplash / CC0 Public Domain

Researchers are developing artificial intelligence that could assess the critical points of climate change. The deep learning algorithm could act as an early warning system against fugitive climate change.

Chris Bauch, a professor of applied mathematics at the University of Waterloo, is the co-author of a recent research paper reporting on the results of the new deep learning algorithm. The research looks at the thresholds beyond which rapid or irreversible change in a system occurs, Bauch said. “We found that the new algorithm was able to not only predict turning points more accurately than existing approaches, but also provide information about what kind of state there is beyond the turning point,” Bauch said. . “Many of these turning points are not desirable and we would like to prevent them if we can.”

Some turning points that are often associated with leakage climate change include melting Arctic permafrost, which could release massive amounts of methane and stimulate rapid warming; the decomposition of current ocean systems, which could lead to almost immediate changes in weather patterns; or the disintegration of the ice sheet, which could cause a rapid change in sea level.

According to the researchers, the innovative approach with this AI is that it was programmed to learn not only about a type of turning point, but also the characteristics of turning points in general.

The approach gains its strength from the hybridization of AI and mathematical theories of turning points, achieving more than any method could do on its own. After training AI on what they characterize as a “universe of possible turning points” that included about 500,000 models, the researchers tested it at specific real-world turning points in various systems, including historical samples. of climatic core.

“Our improved method could raise red flags when we are near a dangerous turning point,” said Timothy Lenton, director of the Global Systems Institute at the University of Exeter and one of the study’s co-authors. “Providing an enhanced early warning of climate turning points could help societies adapt and reduce their vulnerability to what is to come, even if they can’t avoid it.”

Deep learning is making great strides in pattern recognition and classification, and researchers have, for the first time, made point-of-investment detection a pattern recognition problem. This is done by trying to detect patterns that occur before a turning point and get a machine learning algorithm that tells if a turning point is coming.

“People are familiar with the turning points of climate systems, but there are turning points in ecology and epidemiology and even in the stock markets,” said Thomas Bury, a postdoctoral researcher at McGill University and another of the co-authors of the paper. “What we’ve learned is that AI is very good at detecting turning point characteristics that are common to a wide variety of complex systems.”

The new deep learning algorithm is a “game changer for the ability to anticipate major changes, including those associated with climate change,” said Madhur Anand, another of the project’s researchers and director of the Research Institute. Environmental of Guelph.

Now that your AI has learned how turning points work, the team is working on the next stage, which is to provide you with data on contemporary climate change trends. But Anand issued a word of caution about what can happen with this knowledge.

“It definitely gives us a leg up,” he said. “But of course it depends on humanity what we do with this knowledge. I just hope these new findings lead to equitable and positive changes.”

The paper “Deep Learning for Early Warning Signs of Turning Points,” by Bauch, Lenton, Bury, Anand, and co-authors RI Sujith, Induja Pavithran, and Marten Scheffer, was published in the journal Proceedings of the National Academy of Sciences (PNAS).

Breaking the turning points would increase the economic costs of the impacts of climate change

More information:
Thomas M. Bury et al, Deep learning of early warning points of deviation points, Proceedings of the National Academy of Sciences (2021). DOI: 10.1073 / pnas.2106140118

Provided by the University of Waterloo

Citation: Artificial Intelligence Can Be Set Up to Reveal Turning Points on Climate Change (2021, September 23) Retrieved September 23, 2021 at intelligence-reveal-climate-change.html

This document is subject to copyright. Apart from any fair treatment for the purposes of private study or investigation, no part may be reproduced without written permission. Content is provided for informational purposes only.

Source link