Sophisticated artificial intelligence (AI) algorithms have predicted that the world will be 1.5 °C hotter than it was before the Industrial Revolution by the early 2030s – another climate change alarm bell to add to the cacophony that’s already being sounded.
And that’s baked in, the AI says: it doesn’t matter whether greenhouse gases rise or fall over the next decade, the 1.5 °C rise now can’t be avoided. Bear in mind that limiting temperature increases to 1.5 °C was the ambitious goal of the 2015 Paris Agreement.
The drastic measures originally proposed to cut emissions and stay under 1.5 °C of warming will now most likely be required to avoid a 2 °C increase, according to the authors of the new study. The 2 °C is pegged as when global warming consequences get significantly worse for life on the planet.
But we are already seeing a litany of climate impacts in the form of heatwaves, bushfires, floods, and storms with just 1.1 °C of global heating. So, limiting temperature increases as much as possible matters, because every fraction of a degree counts.
There’s more: The AI model shows that even if greenhouse gas emissions rapidly decline to hit net zero by 2076, there’s a 1 in 2 chance of hitting 2 °C of warming by 2054, and a 2 in 3 chance of hitting it between 2044 and 2065.
“Using an entirely new approach that relies on the current state of the climate system to make predictions about the future, we confirm that the world is on the cusp of crossing the 1.5 °C threshold,” says climate scientist Noah Diffenbaugh from Stanford University in California.
“Our AI model is quite convinced that there has already been enough warming that 2 °C is likely to be exceeded if reaching net-zero emissions takes another half century.”
To attain these estimates, rather than using predictive climate models and global carbon budgets to calculate future warming, the researchers fed an AI known as a neural network a database of temperature changes that have already happened.
These neural networks use a vast number of weighted nodes to spot patterns in existing data, patterns which can then be extrapolated out into the future. In particular, the AI looked at recent temperature rises in specific locations compared with reference data from between 1951 and 1980.
To first test the accuracy of the future estimations, the AI was asked to predict the current rise of 1.1 °C above pre-industrial levels. Sure enough, it returned the correct year of 2022, with a most likely range of 2017 to 2027.
“This was really the acid test to see if the AI could predict the timing [of warming] that we know has occurred,” says Diffenbaugh. “We were pretty skeptical that this method would work until we saw that result.
“The fact that the AI has such high accuracy increases my confidence in its predictions of future warming.”
The AI’s prediction that the world will be a degree and a half hotter by the early 2030s matches conclusions in the Intergovernmental Panel on Climate Change (IPCC) Sixth Assessment Report, which state, “the central estimate of crossing the 1.5 °C threshold lies in the early 2030s”, adding further confidence in the AI’s accuracy.
There’s still some uncertainty about when we might reach that 2 °C rise, which is understandable when you’re trying to simulate an entire planet many years into the future. What we do know is that increased temperatures will trigger additional ‘tipping points’, creating a feedback loop of even more warming.
That’s why the 2 °C level is considered so important by scientists. Its effects will be felt in crop failures, sea level rises, the collapse of ecosystems on land and in the seas, economic downturns and severe impacts on human health.
Zero-emission goals covering carbon dioxide, methane, and other heat-trapping gases would have to be hit by the middle of this century, the team suggests, to avoid going over 2 °C of warming. Right now, most countries are aiming at somewhere between 2050 and 2070 to bring their emission levels down to zero.
“Those net-zero pledges are often framed around achieving the Paris Agreement 1.5 °C goal,” says Diffenbaugh.
“Our results suggest that those ambitious pledges might be needed to avoid 2 °C [warming].”
The research has been published in PNAS.