AI predicts that most of the world will see temperatures rise to 3C much faster than previously expected
Introduction
Three established climate scientists have utilised insights from 10 global climate models, along with the aid of artificial intelligence (AI), to conclude that regional warming thresholds will possibly reach sooner than previously estimated.
Their study, published in Environmental Research Letters by IOP Publishing, forecasts that most land regions, as defined by the Intergovernmental Panel on Climate Change (IPCC) will surpass the critical 1.5°C threshold by 2040 or earlier. Moreover, several regions are expected to exceed the 3.0°C threshold by 2060—sooner than anticipated in earlier projections.
Regions such as South Asia, the Mediterranean, Central Europe, and parts of sub-Saharan Africa are anticipated to reach these thresholds quicker, increasing risks for vulnerable ecosystems and communities.
The research was led by three professors, Elizabeth Barnes (Colorado State University), Noah Diffenbaugh (Stanford University), and Sonia Seneviratne (ETH-Zurich). They employed an enhanced AI transfer-learning approach. This method integrates knowledge from multiple climate models and observation data, refining previous estimates and providing more precise regional predictions.
Key Findings
Leveraging AI-based transfer learning, the researchers analysed data from 10 distinct climate models to predict temperature increases and found that:
- 34 regions are likely to exceed 1.5°C of warming by 2040.
- Of these 34 regions,
- 31 regions are expected to reach 2°C of warming by 2040.
- 26 regions are projected to surpass 3°C of warming by 2060.
Elizabeth Barnes stated:
“Our research underscores the importance of incorporating innovative AI techniques like transfer learning into climate modelling to potentially improve and constrain regional forecasts and provide actionable insights for policymakers, scientists, and communities worldwide.”
Noah Diffenbaugh, co-author and professor at Stanford University, continued:
“It is important to focus not only on global temperature increases but also on specific changes happening in local and regional areas. By constraining when regional warming thresholds will be reached, we can more clearly anticipate the timing of specific impacts on society and ecosystems. The challenge is that regional climate change can be more uncertain, both because the climate system is inherently noisier at smaller spatial scales and because processes in the atmosphere, ocean and land surface create uncertainty about precisely how a given region will respond to global-scale warming.”
Copyright 2025 IOP Publishing. All Rights Reserved.
Contact us via email for more information.