AI predicts that most of the world will see temperatures rise to 3°C much faster than previously expected

Three leading climate scientists have combined insights from 10 global climate models and, with the help of artificial intelligence (AI), conclude that regional warming thresholds are likely to be reached faster than previously estimated.

The study, published in Environmental Research Letters by IOP Publishing, projects that most land regions as defined by the Intergovernmental Panel on Climate Change (IPCC) will likely surpass the critical 1.5°C threshold by 2040 or earlier. Similarly, several regions are on track to exceed the 3.0°C threshold by 2060—sooner than anticipated in earlier studies.

Regions including South Asia, the Mediterranean, Central Europe and parts of sub-Saharan Africa are expected to reach these thresholds faster, compounding risks for vulnerable ecosystems and communities.

The research, conducted by Elizabeth Barnes, professor at Colorado State University, Noah Diffenbaugh, professor at Stanford University, and Sonia Seneviratne, professor at the ETH-Zurich, used a cutting-edge AI transfer-learning approach, which integrates knowledge from multiple climate models and observations to refine previous estimates and deliver more accurate regional predictions.

Key Findings

Using AI-based transfer learning, the researchers analysed data from 10 different climate models to predict temperature increases and found:

• 34 regions are likely to exceed 1.5°C of warming by 2040.
• 31 of these 34 regions are expected to reach 2°C of warming by 2040.
• 26 of these 34 regions are projected to surpass 3°C of warming by 2060.

Elizabeth Barnes says:

“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, added:

“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 more noisy at smaller spatial scales and because processes in the atmosphere, ocean and land surface create uncertainty about exactly how a given region will respond to global-scale warming.”

ENDS

About Environmental Research Letters

Environmental Research Letters™ (ERL) is a high-impact, open-access journal published by IOP Publishing. The journal is intended to be the meeting place of the research and policy communities concerned with environmental change and management. ERL is dedicated to bringing together intellectual and professional scientists, economists, engineers, and social scientists, as well as the public sector, industry, and civil society, all of whom are engaged in efforts to understand the state of natural systems and, increasingly, the human footprint on the biosphere.

About IOP Publishing 

IOP Publishing is a society-owned scientific publisher, delivering impact, recognition and value to the scientific community. Its purpose is to expand the world of physics, offering a portfolio of journals, ebooks, conference proceedings and science news resources globally.    IOPP is a member of Purpose-Led Publishing, a coalition of society publishers who pledge to put purpose above profit.  

As a wholly owned subsidiary of the Institute of Physics, a not-for-profit society, IOP Publishing supports the Institute’s work to inspire people to develop their knowledge, understanding and enjoyment of physics. Visit ioppublishing.org to learn more.