(ORDO NEWS) — The planet could pass critical global warming thresholds sooner than previous models predicted, according to a new study that used machine learning. This will happen even with coordinated global climate action by countries.
The study estimates that global warming could exceed pre-industrial levels by 1.5 degrees Celsius in a decade, and found a “substantial likelihood” of a global temperature rise above the 2-degree threshold by mid-century, even with significant global efforts to reduce planetary pollution as a result of warming.
The data show that the average global temperature has already risen by about 1.1 degrees to 1.2 degrees since industrialization.
“Our results provide additional evidence that climate change will have major impacts over the next three decades,” says the report.
Under the 2015 Paris Climate Agreement, nations committed to limiting global warming to well below 2 degrees and preferably to 1.5 degrees below pre-industrial levels.
Scientists have identified 1.5 degrees of warming as a key tipping point, after which the likelihood of extreme floods, droughts, wildfires and food shortages will increase dramatically.
A rise in temperature of more than 2 degrees could lead to catastrophic and potentially irreversible consequences, including “chronic water scarcity” for three billion people.
The study used an artificial neural network that scientists trained on climate models and then used historical observations of temperatures around the world “as an independent input from which AI makes predictions,” said study co-author Professor Noah Diffenbaugh of Stanford University.
Diffenbaugh and colleague Professor Elizabeth Barnes of Colorado State University evaluated three different scenarios: low, medium and high “forcing” climate pathways, which refer to the intensity of heating caused by greenhouse gases in the atmosphere.
Under all three scenarios, scientists have calculated that between 2033 and 2035 the world will reach 1.5 degrees of warming, even if the pollution of the planet caused by warming is significantly reduced.
Diffenboe said that while “individual years are likely to hit 1.5 degrees earlier,” their projections “focus on how long the global average temperature won’t warm by 1.5 degrees.”
The prediction of the study 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 degree threshold “by the early 2030s.”
The study differs from many current projections in its estimates of when the world will cross the 2-degree threshold.
While the IPCC predicts that under a low-emissions scenario, global temperature rise is unlikely to reach 2 degrees by the end of the century, a new study is more troubling.
AI has predicted about an 80 percent chance that 2-degree warming will be achieved before 2065, even if the world reaches net zero over the next half century, when it removes at least as much pollutants from the atmosphere as it emits.
If emissions remain high, AI has predicted a 50 percent chance that 2 degrees will be reached before 2050, Diffenbo said.
There is “clear evidence that half global warming poses significant risks to people and ecosystems. Therefore, the more global warming, the more problems with adaptation,” said Diffenboe.
The use of machine learning for forecasting in climate science is on the rise, Diffenbo said.
“AI is able to learn the most reliable indicators of how much time is left until a given level of global warming is reached in a large number of sometimes conflicting climate model predictions,” he said.
—
Online:
Contact us: [email protected]
Our Standards, Terms of Use: Standard Terms And Conditions.