Planet may cross critical global warming thresholds sooner than expected

Planet Earth could cross critical global warming thresholds sooner than previous models predicted, even with coordinated global climate action, according to a new study using machine learning.

The study estimates that the planet could reach 1.5^TheC of warming above pre-industrial levels within a decade and found a “substantial possibility” of global temperature increases crossing the 2^TheC by mid-century, even with significant global efforts to reduce planet-warming pollution.

The data show that the global average temperature has already risen by about 1.1 to 1.2^TheC since industrialization.

“Our results provide further evidence for 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 well below 2^TheC – and preferably at 1.5 ^TheC – compared to pre-industrial levels.

Scientists have identified 1.5^Thewarming as a key tipping point, beyond which the chances of extreme floods, droughts, wildfires and food shortages will increase dramatically.

Temperature rises above 2^TheC can have catastrophic and potentially irreversible impacts, including pushing three billion people into “chronic water scarcity”.

The study used artificial neural networks – a type of machine learning or artificial intelligence – that the scientists trained on climate models and then used historical temperature observations around the world “as an independent input from which the AI ​​makes a prediction”, said Noah Diffenbaugh, a professor at Stanford University and co-author of the study.

Diffenbaugh and his co-author Elizabeth Barnes, a professor at Colorado State University, evaluated three different scenarios: low, medium and high “forcing” climate paths, which refer to the amount of warming caused by greenhouse gases in the atmosphere.

In all three scenarios, scientists estimated that the world would reach 1.5^TheC of warming between 2033 and 2035, even if the pollution that warms the planet were substantially reduced.

Diffenbaugh said that while “individual years are likely to add up to 1.5^TheC sooner”, its predictions “are focused on how long until the global average temperature rises by 1.5^TheÇ”.

The prediction of the study is in line with previous models. In a major report published in 2022, the Intergovernmental Panel on Climate Change (IPCC) estimated that the world could cross the threshold of 1.5^TheC “in the early 2030s”.

Where the study departs from many current projections is in its estimates of when the world will cross the 2^TheÇ.

Although the IPCC projects that, under a low emissions scenario, global temperature rise is unlikely to reach 2^TheC by the end of the century, the study returned more worrying results.

The AI ​​predicted a probability of about 80% that 2^TheC of warming will be achieved before 2065, even if, over the next half century, the world reaches net zero – where it removes at least as much planet-warming pollution from the atmosphere as it emits.

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

There is “clear evidence that half a degree of global warming poses substantial risks to people and ecosystems.

Therefore, the greater the global warming, the greater the adaptation challenges,” said Diffenbaugh.

While many net zero decarbonization pledges and targets have been framed to keep global warming at 1.5^TheC, he added: “The AI ​​predictions in our study suggest they may be needed to prevent 2^TheÇ”.

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

“AI is able to learn the most reliable indicators of how much time remains until a given level of global warming is reached from a large number of sometimes contradictory climate model predictions.”