The world will exceed the global warming threshold of 1.5 degrees Celsius within 10 to 15 years, even if emissions fall, according to a study that used artificial intelligence (AI) to predict the results. If emissions remain high over the next few decades, the study predicts a one-in-two chance that Earth will warm by an average of 2 degrees Celsius compared to pre-industrial times and more than four inches by the middle of this century. – five chances to reach this limit by 2060.
Research published in the journal Proceedings of the National Academy of Sciences used AI to predict climate change using recent temperature observations from around the world.
New approach that relies on the current state of the climate system
lead study author Noah Diffenbaugh, a climatologist at Stanford University in the US says “Using a completely new approach that relies on the current state of the climate system to predict the future, we confirm that the world is on the verge of exceeding the 1.5 C threshold”.
Diffenbaugh, who co-authored the research with an Elizabeth State University atmospheric scientist in Colorado State University Barnes says “Our AI model is quite confident that there has already been enough warming that 2°C is likely to be exceeded if it takes half a century to reach zero emissions”.
The finding may be controversial, Diffenbaugh said, because other authoritative assessments, including the most recent Intergovernmental Panel on Climate Change (IPCC) report, have concluded that the 2-degree limit is unlikely to be reached if emissions drop to net zero sooner. 2080.
Exceeding the 1.5C and 2C thresholds would mean failing to meet the goals of the 2015 Paris Agreement, in which countries committed to keeping global warming to “well below” 2C above pre-industrial levels, while pursuing the more ambitious goal of limiting warming to 1 .5C.
Previous assessments used global climate models to simulate future warming trajectories; statistical techniques for extrapolating recent warming rates; and carbon budgets to calculate how fast emissions will have to fall to stay below Paris Agreement targets.
For the new estimates, the researchers used a type of AI known as a neural network, which they trained on a large archive of output from widely used global climate model simulations.
Written by : Vaishali Verma
