Climate change tipping points revealed using AI insights
Researchers are developing an artificial intelligence (AI) that could assess climate change tipping points. The deep-learning algorithm could act as an early warning system against runaway climate change.
Some tipping points that are often associated with runaway climate change include melting Arctic permafrost, which could release mass amounts of methane and spur further rapid heating; breakdown of oceanic current systems, which could lead to almost immediate changes in weather patterns; or ice sheet disintegration, which could lead to rapid sea-level change.
The innovative approach with the AI, according to the research team from the University of Waterloo, Canada, is that it was programmed to learn about not just one type of tipping point but the characteristics of tipping points generally.
The researchers are looking at thresholds beyond which rapid or irreversible change happens in a system. Chris Bauch, a professor of applied mathematics at the University of Waterloo and co-author of the research paper reporting results on the new deep-learning algorithm, said: “We found that the new algorithm was able to not only predict the tipping points more accurately than existing approaches but also provide information about what type of state lies beyond the tipping point. Many of these tipping points are undesirable and we’d like to prevent them if we can.”
The team's approach gains its strength from hybridising AI and mathematical theories of tipping points, accomplishing more than either method could on its own. After training the AI on what they characterise as a “universe of possible tipping points” that included some 500,000 models, the researchers tested it on specific real-world tipping points in various systems, including historical climate core samples.
“Our improved method could raise red flags when we’re close to a dangerous tipping point,” said Timothy Lenton, director of the Global Systems Institute at the University of Exeter and one of the study’s co-authors. “Providing improved early warning of climate tipping points could help societies adapt and reduce their vulnerability to what is coming, even if they cannot avoid it.”
Deep learning is making huge strides in pattern recognition and classification, with the researchers having for the first time converted tipping-point detection into a pattern-recognition problem. This is done to try and detect the patterns that occur before a tipping point and get a machine-learning algorithm to say whether a tipping point is coming.
“People are familiar with tipping points in climate systems, but there are tipping 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 on the paper. “What we’ve learned is that AI is very good at detecting features of tipping points that are common to a wide variety of complex systems.”
The new deep-learning algorithm is a “game-changer for the ability to anticipate big shifts, including those associated with climate change”, said Madhur Anand, another of the researchers on the project and director of the Guelph Institute for Environmental Research.
Now that their AI has learned how tipping points function, the team is working on the next stage, which is to give it the data for contemporary trends in climate change.
However, Anand issued a word of caution of what may happen with such knowledge: “It definitely gives us a leg up, but of course it’s up to humanity in terms of what we do with this knowledge. I just hope that these new findings will lead to equitable, positive change.”
The paper 'Deep learning for early warning signals of tipping points' by Bauch, Lenton, Bury, Anand and co-authors R I Sujith, Induja Pavithran and Marten Scheffer, was published in the journal Proceedings of the National Academy of Sciences.
The phenomenon of climate change tipping points has been similarly observed in another research paper, 'Critical slowing down suggests that the western Greenland Ice Sheet is close to a tipping point', published in the same journal.
In this paper, researchers from the Freie Universität, Berlin, Potsdam Institute for Climate Impact Research, Germany, the University of Exeter, and UiT the Arctic University of Norway, warn that ice sheet melting rates across Greenland have accelerated nonlinearly in recent decades and that models predict a critical temperature threshold beyond which the current ice sheet state is not maintainable.
In response to the ongoing anthropogenic global warming, they wrote, the Greenland ice sheet may reach a tipping point beyond which its current configuration would become unstable. A crucial nonlinear mechanism for the existence of this tipping point is the positive melt-elevation feedback: melting reduces ice sheet height, exposing the ice sheet surface to warmer temperatures, which further accelerates melting.
The researchers also draw particular attention to significant early-warning signals indicating that the central-western Greenland ice sheet is close to a critical transition and that substantial further mass loss of ice is likely in the near future.
This 'tipping point' research news comes at the same time as the publication of another report, authored by over 120 scientific experts, detailing unprecedented climate change impact on the global oceans, with the Arctic registering record low ice levels.
According to the report, Arctic ice levels logged in the last two years have reached record lows, while per decade they have on average, since 1979 to 2020, dropped by nearly 13 per cent.
The annual ‘Copernicus Ocean State Report, Issue 5’, published in the peer-reviewed Journal of Operational Oceanography, draws upon expert analyses by more than 120 scientific experts from more than 30 European institutions.
Recognised as the reference point for the scientific community, national and international bodies, decision makers, blue economy actors, and the general public, this year’s crucial review (focused on results from 2019) shows unprecedented levels of impact of climate change.
The report shows that across the world, serious issues are arising. The warming of the Arctic Ocean is contributing to an estimated 4 per cent of the entire global ocean warming. An almost 90 per cent reduction of average sea ice thickness has been witnessed in the Barents Sea (a small part of the Arctic), which has led to a decrease in sea ice import from the polar basin.
In the North Sea, extreme variability from cold spells and marine heatwaves has been linked to reported changes in catches of sole, European lobster, sea bass, red mullet and edible crabs. In the Mediterranean Sea, there were four consecutive record flooding events in Venice (November 2019) and higher-than-average wave heights in the southern Mediterranean (in 2019).
Summarising the international situation of the ocean, report chair Dr Karina von Schuckmann, of Mercator Ocean international, stated a need for ongoing improved development and provision of state-of-the art ocean knowledge and products, in addition to regular monitoring through the EU-funded Copernicus.
“Climate change, pollution, and overexploitation have placed unprecedented pressures on the ocean requiring the urgent need for sustainable measures for governance, adaptation and management in order to secure the various life support roles the ocean offers for human well-being,” she said.
“Scientifically sound knowledge derived from high-quality ocean products and delivered by ocean services is critical to stimulate transformative change. Considering the ocean as a fundamental factor in the Earth system and embracing the multidimensional and interconnected nature of the ocean is the bedrock for a sustainable future.”
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.