An artificial intelligence algorithm has predicted that the critical global warming threshold will be overcome faster than previously thought. This is stated in a study by Colorado State University and Stanford University, writes Gizmodo.
The scientists used neural networks trained on the output of a climate model to predict when critical global warming thresholds would be reached. AI has figured out that the Earth will be 1.5°C warmer in about ten years. By the end of the century, the planet will warm by 2°C.
According to the Paris Agreementthe average temperature on Earth should not rise by more than 1.5°C before 2050.
“We started with a particular interest in this global warming threshold. Because of the UN Paris Agreement, there has been a lot of discussion and research about how many years we will reach 1.5°C,” the researchers said.
The team trained the neural network on the same climate modeling database that other organizations use. The algorithm analyzed historical temperature observations from around the world and considered low, medium and high greenhouse gas emission scenarios.
The AI concluded that in any case, the planet will reach 1.5°C of warming between 2033 and 2035.
The algorithm also found that even under a low-emissions scenario, the average annual temperature would rise by 2°C by 2054.
According to researchers, AI worsened the forecast of the Intergovernmental Panel on Climate Change (IPCC). The organization had previously predicted an unlikely 2°C increase in mean temperature with zero CO emissions.2.
“AI in the same scenario predicts a higher probability […]. We do not claim that the algorithm is right and the IPCC is wrong, but this is the largest area of inconsistency between the predictions of the neural network and the group, ”the researchers say.
Although the calculations for a faster warming scenario are alarming, governments and agencies are still striving to avoid reaching the tipping point, study co-author Noah Diffenbaugh said. He credited the Paris Agreement for pushing policymakers to cut emissions faster.
“If you look at the 2014 IPCC report, […] the future of the 21st century ended up with a 4°C rise compared to 2°C for political action,” the scientist said.
Diffenboe added that the current vector of development is much “less warm” than before the Paris Agreement.
Recall that in October 2022, AI helped the victims of hurricanes Ian and Fiona receive monetary compensation.
In July, Ohio State University scientists taught a neural network to predict the extent of damage to buildings after a disaster.
Subscribe to CryptoNewsHerald news in Telegram: CryptoNewsHerald AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER
CryptoNewsHerald Newsletters: Keep your finger on the pulse of the bitcoin industry!