Terrible predictions: Scientists used artificial intelligence to find a planet that could cross a critical global warming threshold sooner than expected

By Christian Edwards, CNN

A new study using machine learning reveals that the planet could pass critical warming thresholds sooner than previous models predicted, even with coordinated global climate action.

The study estimates that the planet could reach 1.5°C of warming above pre-industrial levels in a decade, and finds a “significant potential” for global warming to exceed the 2° threshold by mid-century, even with significant global efforts to reduce pollution from warming. thermal.

The data shows that the global average temperature has already risen by about 1.1 to 1.2 degrees since industrialization.

“Our results provide additional evidence of high-impact climate change over the next three decades,” noted the report, published Monday in the Proceedings of the National Academy of Sciences.

Under the 2015 Paris Climate Agreement, countries pledged to limit global warming to below 2 degrees – preferably 1.5 degrees – compared to pre-industrial levels.

Scientists have identified 1.5 degrees of warming as the major tipping point after which the chances of severe floods, droughts, wildfires and food shortages will increase dramatically.

A rise in temperatures of more than 2 degrees could have catastrophic and potentially irreversible effects, including pushing three billion people into “chronic water scarcity.”

The study used artificial neural networks — a type of machine learning or artificial intelligence — that scientists trained on climate models and then used historical observations of temperature around the world “as independent inputs that the AI ​​makes predictions about,” said Noah Divenbaugh, one of the university professors. Professor at Stanford University and co-author of the study.

Divenbaugh and co-author Elizabeth Barnes, a professor at Colorado State University, evaluated three different scenarios: low, medium and high climate trajectories, which indicate the intensity of heat caused by greenhouse gases in the atmosphere.

In all three scenarios, scientists estimate that the world will reach 1.5 degrees of warming between 2033 and 2035, even if pollution from a warming planet drops significantly.

Diffenbaugh said that while “individual years are likely to reach 1.5 degrees sooner,” their predictions “focus on the duration until the global average temperature warms by 1.5 degrees.”

The study’s prediction is consistent with previous models. In a major report published in 2022, the Intergovernmental Panel on Climate Change (IPCC) estimated that the world could pass the 1.5°C threshold “in the early 2030s”.

Where the study deviates from many of the current predictions is in its estimates of when the world crosses the 2-degree threshold.

While the Intergovernmental Panel on Climate Change projects that, in a low-emissions scenario, a 2-degree rise in global temperatures is unlikely by the end of the century, the study provided more troubling findings.

AI has predicted a probability of about 80% of a 2°C warming before 2065, even if, over the next half-century, the world reaches net zero – removing at least as much global warming pollution from the atmosphere as it emits from him.

If emissions remain high, Diffenbaugh said, the AI ​​predicts a 50% probability that 2 degrees will be reached before 2050.

There is “clear evidence that half a degree of warming poses significant risks to people and ecosystems. Hence, the greater the global warming, the greater the adaptation challenges.”

While many net decarbonization pledges and targets are framed around keeping global warming at 1.5 degrees, he added: “The AI ​​predictions in our study suggest that those may be necessary to avoid 2 degrees.”

The use of machine learning to make predictions is increasing in climate science, Divenbaugh said.

“Artificial intelligence is able to learn the most reliable indicators of how long it will take until a certain level of global warming is reached in a large number of sometimes contradictory climate model predictions.”

CNN Wire
™ & © 2023 Cable News Network, Inc. , a Warner Bros. discovery company. All rights reserved.

Leave a Comment