Pusan National University scientists designed a new model to predict metal wear for safer, lighter cars and planes

This hybrid model uses machine learning and physics to improve fatigue life prediction for lightweight magnesium alloys

Pusan National University

 

image: 

The new hybrid model uses machine learning combined with physical principles to accurately predict the fatigue life of magnesium alloys under varying stress conditions, eliminating the need for manual parameter adjustments and improving predictive accuracy.

view more 

Credit: Taekyung Lee from Pusan National University, South Korea

Magnesium alloys are increasingly popular in vehicle and aircraft design due to their strength, light weight, and ease of machining. Reducing weight is crucial because lighter vehicles need less power to move, saving energy and reducing emissions. However, since magnesium alloys behave differently under stress, predicting their ‘fatigue life’ has been challenging. Over time, parts made from these alloys can develop tiny cracks from the repeated stress during their use.

Until now, predicting exactly how and when these cracks will form has been difficult, as traditional methods involve empirical models that demand frequent adjustments for different loading conditions.  This limitation makes them difficult to implement for industrial applications, where changing loads and directions are common.

A team of researchers led by Professor Taekyung Lee from Pusan National University, South Korea along with Mr. Jinyeong Yu, a Ph. D candidate set out to tackle this challenge. In their study published in Journal of Magnesium Alloys, the group integrated machine learning with energy-based physical modeling to improve prediction accuracy. The model works by using a combination of a neural network that analyzes complex patterns in stress and strain cycles, along with an energy-based physical model that provides a more holistic understanding of material behavior under cyclic loading.

The model was built using a large dataset of hysteresis loops—the stress-strain behaviors observed during repeated loading and unloading of the material—collected from low-cycle fatigue tests of the AZ31 magnesium alloy. “The neural network learns from these stress cycles which reveal how the metal stretches, bends, and returns to shape under load. We then use a physics-based model to ground the neural network in the physical laws of material science and to forecast when cracks may form,” explains Prof. Lee.

Instead of predicting fatigue life directly, the neural network estimates the hysteresis loops for the material under different conditions. By reconstructing these loops, it can more accurately assess how the material's energy is dissipated during each cycle of loading and unloading, which is directly related to how quickly fatigue will accumulate. Then the physics-based model converts these stress cycle predictions into a reliable estimate of the number of cycles to failure, or the fatigue life of the alloy. “Because the machine learning component can continually adapt as it learns from the loop data, this method is more flexible across multiple loading directions and conditions, removing the need for manual parameter adjustments,” adds Prof. Lee.

With the advent of this new approach, manufacturers may soon benefit from greater predictive reliability when working with magnesium alloys, enabling safer, lighter, and more cost-effective designs in high-stakes environments. The model offers a more streamlined and accurate approach to the fatigue life prediction of magnesium alloys that could lead to enhanced safety and longevity of critical components in real-world applications.

 

***

Reference                                    

Title of original paper: Alternative predictive approach for low-cycle fatigue life based on machine learning and energy-based modeling

Journal: Journal of Magnesium Alloys

DOI: https://doi.org/10.1016/j.jma.2024.10.014

                                 

About the institute Pusan National University, Korea

Pusan National University, located in Busan, South Korea, was founded in 1946 and is now the No. 1 national university of South Korea in research and educational competency. The multi-campus university also has other smaller campuses in Yangsan, Miryang, and Ami. The university prides itself on the principles of truth, freedom, and service, and has approximately 30,000 students, 1200 professors, and 750 faculty members. The university is composed of 14 colleges (schools) and one independent division, with 103 departments in all.

Website: https://www.pusan.ac.kr/eng/Main.do

 

About Professor Taekyung Lee

Dr. Taekyung Lee is an Associate Professor at the School of Mechanical Engineering at Pusan National University, Korea. His group, Metal Design & Manufacturing (MEDEM) Lab, studies advanced metal-forming processes, such as the electropulsing treatment, additive manufacturing, and severe plastic deformation process. MEDEM is also interested in the optimization of processing parameters based on physics, machine learning, and microstructure-mechanical analysis. Prof. Lee earned his Ph.D. at POSTECH, Korea in 2014 and completed the postdoctoral training at Northwestern University, USA. Before coming to Pusan National University, he worked at Kumamoto University, Japan, for two years as an assistant professor.

Lab Website: https://sites.google.com/site/medemlab/

ORCID id: 0000-0002-1589-3900

---

Journal

Journal of Magnesium and Alloys

DOI

10.1016/j.jma.2024.10.014 

Method of Research

Computational simulation/modeling

Subject of Research

Not applicable

Article Title

Alternative predictive approach for low-cycle fatigue life based on machine learning and energy-based modeling

The inequity of wildfire rescue resources in California

A new study finds that the most vulnerable communities are lacking state resources to reduce damages – and save lives – in a wildfire

Society for Risk Analysis

AUSTIN, TX, December 10, 2024 – Wildfires in California are intensifying due to warmer temperatures and dry vegetation – putting more residents at risk of experiencing costly damages or losing their homes. Marginalized populations (lower income, elderly, and the disabled) often suffer the most and, according to a new study, may receive less economic and emergency assistance compared to wealthy residents. 

A detailed analysis of more than 500 California wildfire incidents from 2015 to 2022 by University at Buffalo scientists shows that disaster recovery resources in California favor people living in wealthy communities over disadvantaged residents who lack the resources to plan for and recover from a wildfire. “We discovered that racial and economic inequity plays a pivotal role in resource allocation for wildfire recovery and mitigation,” says lead author Poulomee Roy, Ph.D. candidate in Industrial and Systems Engineering. She will present the results in December at the annual meeting of the Society for Risk Analysis in Austin, Texas. 

To examine the underlying relationships between resource allocation and socio-demographic factors, the researchers conducted an in-depth analysis of data (at the county level) related to 504 California wildfire incidents leveraging cutting-edge AI-driven approaches. Factors included in the analysis were: 

• wildfire impact (the spread, burnt area, structural damage, fatalities, etc.), 

• sociodemographic factors (population, race, ethnicity, poverty, educational level, populations of elderly and disabled, sex ratio, crowded households, etc.), and 

• resource allocation data (estimated cost incurred for the wildfire mitigation, personnel deployed in the rescue operation, and whether any equipment like aircraft, gulf strikes, water tenders, dozers, etc., are deployed or not).  

“Our study highlighted a pronounced trend in which counties with higher percentages of lower-income and black populations receive less personnel and funding, compared to those counties with higher proportions of high-income and white people,” says principal investigator Dr. Sayanti Mukherjee, Assistant Professor of Industrial and Systems Engineering. 

When measuring “personnel for rescue operations,” the analysis showed that racial distribution within a county plays an instrumental role in resource allocation. For example, counties with a higher number of Hispanic or Latino residents had fewer wildfire rescue personnel available to them despite facing a higher risk of wildfire. The results also showed a declining trend of recovery efforts and resources allocated in counties with higher Black or African American populations. 

By contrast, counties with a greater concentration of wealthier, single-parent households (such as Los Angeles County), received adequate personnel to mitigate a wildfire. (Wildfire mitigation is defined by FEMA as “any actions undertaken to decrease the risk of damage or loss of life from wildfires.”)  

Elderly and disabled populations likely need more assistance during an evacuation and rescue operation, yet the study revealed that the number of rescue personnel lowered as the population of elderly and disabled in a county increased. The same trend was seen when the number of “crowded households” rose -- despite the likelihood of more injuries and fatalities in crowded households during a fire.   

The results were similar when resources were measured as “cost for recovery” from a wildfire. The economically disadvantaged populations did not receive adequate resources to recover from a wildfire, compared to wealthier neighborhoods with a higher proportion of single-family households.  

“Our findings underscore the significant role of ethnicity, economic status, and proportion of the elderly population in determining wildfire resource allocation for these counties,” says Mukherjee. “The results of this study can equip policymakers to adopt an informed decision about the distribution and allocation of resources.” 

The authors argue that their findings demand action from policymakers to ensure equitable recovery efforts and support for marginalized communities.  

# 

Poulomee Roy is presenting this research Tuesday, December 10, from 3:30 pm, at the JW Marriot Austin, Texas. 

Assessing inequities and disparities in the post-wildfire recovery of socially vulnerable WUI (Wildfire Urban Interface) communities – Tuesday, December 10, 3:30 p.m. 

Part of a symposium on “Confronting the Wildfire Crisis Leveraging Risk-informed Wildfire Preparedness and Recovery Strategies” 

About SRA   

The Society for Risk Analysis is a multidisciplinary, interdisciplinary, scholarly, international society that provides an open forum for all those interested in risk analysis. SRA was established in 1980. Since 1982, it has continuously published Risk Analysis: An International Journal, the leading scholarly journal in the field. For more information, visit www.sra.org.   

 

Aerosol pollutants from cooking may last longer in the atmosphere – new study

University of Birmingham

New insights into the behaviour of aerosols from cooking emissions and sea spray reveal that particles may take up more water than previously thought, potentially changing how long the particles remain in the atmosphere. 

Research led by the University of Birmingham found pollutants that form nanostructures could absorb substantially more water than simple models have previously suggested. Taking on water means the droplets become heavier and will eventually be removed from the atmosphere when they fall as rain. 

The team, also involving researchers from the University of Bath, used facilities at Diamond Light Source, to study the water uptake of oleic acid, a molecule commonly found in emissions from cooking and in spray from the ocean’s surface.  They used a technique called Small-Angle X-ray Scattering (SAXS) to chart the relationship between the structure inside the particle and both its ability to absorb water and its reactivity.  

Working at Diamond’s I22 beamline with the I22 team and experts from the Central Laser Facility operated by the Science and Technology Facilities Council at the Rutherford Appleton Laboratory, the team also studied changes in the structures of polluting particles, caused by changes in humidity. They showed that as molecules react with ozone in the atmosphere and break down, they can also reform into different 3-D structures with varying abilities to absorb water and to react with other chemicals. 

The findings, published in Atmospheric Chemistry and Physics, suggest these combined effects work to keep oleic acid particles circulating in the atmosphere for longer. 

“As we develop our understanding of how these particles behave in the atmosphere, we will be able to design more sophisticated strategies for the control of air pollution,” said lead researcher  

Professor Christian Pfrang. “For example, protecting harmful emissions from degrading in the atmosphere could allow them to travel and disperse further through the atmosphere, thus substantially increasing the pollutant’s reach.”  

He added: “Our results show that aerosols exist in a really dynamic state, with complex structures being formed as well as being destroyed. Each of these states allows polluting molecules to linger in the atmosphere for longer. To reduce exposure to pollutants from cooking, people should consider making more use of extractor fans and ensuring that kitchens are well ventilated to allow aerosol particles to escape rapidly.” 

ENDS 

---

Journal

Atmospheric Chemistry and Physics

DOI

10.1155/2024/6355613 

Method of Research

Experimental study

Subject of Research

Not applicable

Article Title

Experimental observation of the impact of nanostructure on hygroscopicity and reactivity of fatty acid atmospheric aerosol proxies

Article Publication Date

10-Dec-2024

Air pollution linked to rising depression rates, study finds

Eurasia Academic Publishing Group

A groundbreaking study published in Environmental Science and Ecotechnology has revealed a strong connection between long-term air pollution exposure and an increased risk of depression. The research, led by Harbin Medical University and Cranfield University, analyzed data from over 12,000 participants in the China Health and Retirement Longitudinal Study (CHARLS).

 

The study identifies sulfur dioxide (SO₂) as the most significant contributor to depression risk, with fine particulate matter (PM2.5) and carbon monoxide (CO) also linked to depressive symptoms. These pollutants were found to have a compounded impact when combined, highlighting the dangers of multi-pollutant exposure.

 

The research also explored potential mechanisms, finding that cognitive and physical impairments partially mediate the link between pollution and depression. The findings emphasize the mental health risks posed by environmental pollutants and call for urgent action to reduce their levels.

 

“Our findings underscore the critical need for integrated air quality management to improve both physical and mental health,” the authors noted. Targeting SO₂ and other key pollutants could significantly alleviate the public health burden of depression, particularly among vulnerable populations like middle-aged and older adults.

 

With millions exposed to unsafe air quality levels worldwide, this study highlights the intersection of environmental and mental health challenges, calling for stricter pollution controls and targeted interventions.

---

Journal

Environmental Science and Ecotechnology

DOI

10.1016/j.ese.2024.100515 

Method of Research

Observational study

Subject of Research

People

Article Title

Synergistic air pollution exposure elevates depression risk: A cohort study

Woodburning creates major PM2.5 air pollution issue in UK West Midlands 

University of Birmingham

Woodburning has a major impact on air quality in Birmingham and the wider West Midlands region of the UK – accounting for a substantial proportion of all fine pollution particles and representing a significant risk to public health, a new study reveals. 

University of Birmingham researchers found that biomass burning, primarily from woodburning activities, such as heating homes using woodburning stoves or logs on open fires, contributes significantly to fine particulate matter (PM2.5) levels in the region – accounting for some 25% of the total PM2.5 mass. 

Publishing their findings today (10 Dec) in Atmospheric Environment, the researchers call for targeted measures to mitigate health risks associated with PM2.5 emissions from woodburning activities. 

The experts found woodburning-related PM2.5 concentrations seven times higher than those observed in 2008-2010. They also discovered that the impact of woodburning is particularly pronounced during winter months, contributing up to around half of PM2.5 concentrations - a seasonal spike attributed to people heating their homes. 

Exposure to elevated PM2.5 levels poses severe health risks, including respiratory and cardiovascular diseases, low birthweight, and increased mortality rates. The study estimates that reducing woodburning emissions could significantly decrease mortality and life-years lost due to air pollution in the West Midlands.  

Lead author Dr Deepchandra Srivastava commented: "Our study highlights the significant increase in woodburning activity in the past 10 years, making it one of the most important sources of air pollution in the West Midlands.” 

Lead investigator of the study, Professor Zongbo Shi commented: “We need to see immediate and coordinated actions at local and national levels to reduce wood burning, improve air quality - including enhancement and enforcement of smoke control areas to curb emissions from woodburning stoves and open fires. This has great potential to reduce PM2.5-related health risks and decrease mortality in the region.”  

The experts also recommend raising public awareness about the health impacts of woodburning and promoting best practices, such as burning only dry, seasoned wood and maintaining stoves properly, as crucial steps in reducing pollution. 

Researchers are also calling for local regulations to be strengthened to promote the use of cleaner alternatives, such as electric heating or heat pumps. They say that, to further improve air quality in the West Midlands, wider national and international policy interventions are also needed to address regional and transboundary PM2.5-related exposure. 

Larissa Lockwood, Director of Clean Air at Global Action Plan said: “Lighting fires in our homes is now the largest source of toxic fine particle air pollution in the UK, presenting a range of serious health risks including heart and lung disease, diabetes, and dementia.  

“Despite growing evidence of the UK’s burning problem - like this new research from the University of Birmingham - many people are still unaware that wood burning is harming our health and the planet.  

“While many work to communicate these harms through moments such as Clean Air Night, we need urgent action from central government to share these harms with people across the UK and empower local authorities to tackle this growing source of air pollution in ways that are appropriate for their local communities. Join people across the country in learning the facts about wood burning this Clean Air Night (22 January 2025).” 

This research was conducted as part of the Natural Environment Research Council (NERC)-funded West Midlands Air Quality Improvement Programme (WM-Air), led by Professor William Bloss. Researchers analysed PM2.5 samples collected in 2021 and 2022 at two urban background sites in Birmingham, utilizing advanced receptor modelling techniques to identify and quantify pollution sources. 

PM2.5 refers to tiny airborne particles or droplets that are 2.5 microns or less in diameter and represents a serious health concern because it can be inhaled into our lungs and cause a range of health issues. It can come from a variety of sources, including woodburning, vehicle and industrial emissions, power plants, cooking, cigarettes and smoking. 

ENDS 

For more information, please contact Tony Moran, International Communications Manager, tel: +44 (0)7827 832312: email: t.moran@bham.ac.uk   

Notes to editor: 

• The University of Birmingham is ranked amongst the world’s top 100 institutions. Its work brings people from across the world to Birmingham, including researchers, teachers and more than 8,000 international students from over 150 countries. 

• ‘Comparative Receptor Modelling for the Sources of Fine Particulate Matter (PM2.5) at Urban Sites in the UK’ - Deepchandra Srivastava, Supattarachai Saksakulkrai, W. Joe F. Acton, Daniel J. Rooney, James Hall, Siqi Hou, Mark Wolstencroft, Suzanne Bartington, Roy M. Harrison, Zongbo Shi, and William J. Bloss is published in Atmospheric Environment. 

• WM-Air – the West Midlands Air Quality Improvement Programme - is an initiative to support the improvement of air quality, and associated health, environmental and economic benefits, in the West Midlands. Project partners include the West Midlands Combined Authority, Transport for West Midlands, local authorities across the region including Birmingham and Coventry City Councils, HS2, and the Birmingham & Solihull NHS Sustainability & Transformation Partnership, plus a number of private sector organisations and local businesses. 

• Air pollution in the West Midlands affects some 2.8 million people, reducing average life expectancy by up to 6 months, and is responsible for direct and indirect economic costs of several hundred million pounds per year. Air quality is therefore a key priority for local and regional government, and for the health and wellbeing of the region’s population.  

 

 

---

Journal

Atmospheric Environment

Method of Research

Experimental study

Subject of Research

People

Article Title

Comparative Receptor Modelling for the Sources of Fine Particulate Matter (PM2.5) at Urban Sites in the UK

Article Publication Date

10-Dec-2024

Dubai project produces 90 tonnes of green hydrogen



The Green Hydrogen project is the first of its kind in the Middle East and North Africa to produce green hydrogen using solar energy.

Dubai Electricity and Water Authority (DEWA) has announced that its Green Hydrogen project has produced around 90 tonnes of green hydrogen since it was launched in May 2021.

Most of this hydrogen was used to produce more than one-gigawatt hour (GWh) of green energy, reducing about 450 tonnes of CO2 emissions.

The Green Hydrogen project is the first of its kind in the Middle East and North Africa to produce green hydrogen using solar energy.

Implemented in collaboration with Expo 2020 Dubai and Siemens Energy, the project produces about 20 kilogrammes of hydrogen per hour, and its gas tank can store up to 12 hours of hydrogen produced using solar energy. It is used to produce electricity during the night through a hydrogen gas motor with a capacity of approximately 300 kilowatts of electrical energy.

The Green Hydrogen project has been designed and built to accommodate future applications and test platforms for various uses of hydrogen, including the air, land and sea transport sectors and other industries.

Saeed Mohammed Al Tayer, MD and CEO of DEWA, said, “We support the vision of His Highness Sheikh Mohammed Bin Rashid Al Maktoum, Vice President, Prime Minister and Ruler of Dubai, to enhance the UAE’s pioneering and competitive position worldwide in low-carbon hydrogen.

“The Green Hydrogen project promotes the UAE’s goal to acquire 25% of the low-carbon hydrogen market. The project aligns with our efforts to diversify energy resources and achieve the National Hydrogen Strategy, the Dubai Clean Energy Strategy 2050 and the Dubai Net Zero Carbon Emissions Strategy 2050 to provide 100% of the energy production capacity from clean energy sources by 2050.”

Implementing this project at the Mohammed Bin Rashid Al Maktoum Solar Park, the largest single-site solar park in the world, which will have a production capacity of over 5,000 MW by 2030, contributes to achieving competitive prices in green hydrogen production.

The green hydrogen is produced through electrolysis using renewable energy sources. DEWA has achieved world-class results for solar energy prices, making Dubai a global benchmark for solar energy prices.

According to a recent report, green hydrogen, often referred to as the fuel of the future, is emerging as one of the most prominent clean energy sources that will significantly contribute to transforming the global energy landscape.

Recognising its potential, the World Green Economy Summit (WGES) will explore the latest developments in the renewable and clean energy sector. The summit will also focus on enhancing the role of innovation and research and development in energy storage technologies, including green hydrogen, to devise mechanisms to address sustainability challenges and achieve carbon neutrality, thereby accelerating the transition to a green economy.

WGES is held annually under the patronage of His Highness Sheikh Mohammed Bin Rashid Al Maktoum, Vice President, Prime Minister and Ruler of Dubai. It is organised by the Dubai Supreme Council of Energy, Dubai Electricity and Water Authority (DEWA), and the World Green Economy Organisation (WGEO).

“Global interest in investing in clean and renewable energy sources, including green hydrogen, is rising, particularly as the cost of renewable energy production decreases. The UAE is at the forefront of this energy transition, leveraging innovation and research and development to expand the use of green energy. We look forward to advancing green energy at the 10th World Green Economy Summit, laying the groundwork for a just energy transition to achieve the UN Sustainable Development Goals 2030,” said Saeed Mohammed Al Tayer, Vice Chairman of the Dubai Supreme Council of Energy, MD&CEO of DEWA, and Chairman of WGEO.

Waleed bin Salman, Executive Vice President of Business Development and Excellence at DEWA, noted that DEWA has implemented the Green Hydrogen project at the Mohammed Bin Rashid Al Maktoum Solar Park in Dubai, which is the first of its kind in the Middle East and North Africa to produce green hydrogen using solar power, store it, and convert it into electrical energy, in addition to other applications in the transport and industrial sectors. The project exemplifies DEWA’s dedication to pioneering initiatives that support the UAE’s vision for a green economy.

WAM

A socio-economic perspective on green hydrogen as a sustainable operations strategy

KeAi Communications Co., Ltd.

 

image: 

Hydrogen production from green and fossil sources distinguished by age and gender

view more 

Credit: Francesco Bonesso, Idiano D’Adamo, Marco Giannini, Massimo Gastaldi

Hydrogen serves as an energy carrier with the potential to enable sustainable and flexible energy systems. However, achieving true decarbonization requires the use of renewable energy sources and responsible water management.

In a study published in the KeAi journal Sustainable Operations and Computers, a team of researchers conducted a socio-economic analysis of hydrogen production from an integrated wind and electrolysis plant in southern Italy.

The study estimated a Levelized Cost of Hydrogen (LCOH) of €3.60/kg for a 30 MW wind and 18.5 MW electrolysis plant, capable of producing 1,776,000 kg of hydrogen in its first year. Sensitivity analyses indicated that LCOH could range from €2.81 to €4.48/kg, influenced significantly by inflation and capacity factors. For instance, a capacity reduction from 35% to 25% would increase the LCOH to €5.25/kg.

An online public survey revealed that 72.5% of Italians are unaware of the differences between green and grey hydrogen, with knowledge peaking among men over 35. Willingness to pay (WTP) for green hydrogen stood at approximately 10%, with the highest acceptance found among women aged 18-24. Public acceptance of wind power installations reflected a WTP of 8.7%. The study further highlighted that 68.6% of LCOH values cluster between 3.20 and 4.00 €/kg at a 35% capacity factor, emphasizing the need for public education and engagement to enhance acceptance.

While green hydrogen demonstrates substantial economic potential, addressing public knowledge gaps and societal resistance is crucial for large-scale adoption. The study calls for strategic spatial energy planning to facilitate successful implementation.

###

Contact the author: Idiano D'Adamo, Department of Computer, Control and Management Engineering, Sapienza University of Rome, Rome, Italy.

The publisher KeAi was established by Elsevier and China Science Publishing & Media Ltd to unfold quality research globally. In 2013, our focus shifted to open access publishing. We now proudly publish more than 190 world-class, open access, English language journals, spanning all scientific disciplines. Many of these are titles we publish in partnership with prestigious societies and academic institutions, such as the National Natural Science Foundation of China (NSFC).

---

Journal

Sustainable Operations and Computers

DOI

10.1016/j.susoc.2024.11.002 

Method of Research

Experimental study

Subject of Research

Not applicable

Article Title

Green hydrogen as a sustainable operations strategy: A socio-economic perspective

 

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

IOP Publishing

 

image: 

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

view more 

Credit: CCBY IOP Publishing

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. 

---

Journal

Environmental Research Letters

DOI

10.1088/1748-9326/ad91ca 

Method of Research

Content analysis

Article Title

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

Article Publication Date

10-Dec-2024

AI predicts Earth’s peak warming

Artificial intelligence provides new evidence that rapid decarbonization will not prevent warming beyond 1.5 degrees Celsius. The hottest years of this century are likely to shatter recent records

Stanford University

Researchers have found that the global goal of limiting warming to 1.5 degrees Celsius above pre-industrial levels is now almost certainly out of reach.

The results, published Dec. 10 in Geophysical Research Letters, suggest the hottest years ahead will very likely shatter existing heat records. There is a 50% chance, the authors reported, that global warming will breach 2 degrees Celsius even if humanity meets current goals of rapidly reducing greenhouse gas emissions to net-zero by the 2050s.

A number of previous studies, including the authoritative assessments by the Intergovernmental Panel on Climate Change, have concluded that decarbonization at this pace would likely keep global warming below 2 degrees.

“We’ve been seeing accelerating impacts around the world in recent years, from heatwaves and heavy rainfall and other extremes. This study suggests that, even in the best case scenario, we are very likely to experience conditions that are more severe than what we’ve been dealing with recently,” said Stanford Doerr School of Sustainability climate scientist Noah Diffenbaugh, who co-authored the study with Colorado State University climate scientist Elizabeth Barnes.

This year is set to beat 2023 as Earth’s hottest year on record, with global average temperatures expected to exceed 1.5 degrees Celsius or nearly 2.7 degrees Fahrenheit above the pre-industrial baseline, before people started burning fossil fuels widely to power industry. According to the new study, there is a nine-in-ten chance that the hottest year this century will be at least half a degree Celsius hotter even under rapid decarbonization. 

Using AI to refine climate projections

For the new study, Diffenbaugh and Barnes trained an AI system to predict how high global temperatures could climb, depending on the pace of decarbonization.

When training the AI, the researchers used temperature and greenhouse gas data from vast archives of climate model simulations. To predict future warming, however, they gave the AI the actual historical temperatures as input, along with several widely used scenarios for future greenhouse gas emissions. 

“AI is emerging as an incredibly powerful tool for reducing uncertainty in future projections. It learns from the many climate model simulations that already exist, but its predictions are then further refined by real-world observations,” said Barnes, who is a professor of atmospheric science at Colorado State. 

The study adds to a growing body of research indicating that the world has almost certainly missed its chance to achieve the more ambitious goal of the 2015 Paris Climate Agreement, in which nearly 200 nations pledged to keep long-term warming “well below” 2 degrees while pursuing efforts to avoid 1.5 degrees. 

A second new paper from Barnes and Diffenbaugh, published Dec. 10 in Environmental Research Letters with co-author Sonia Seneviratne of ETH-Zurich, suggests many regions including South Asia, the Mediterranean, Central Europe, and parts of sub-Saharan Africa will surpass 3 degrees Celsius of warming by 2060 in a scenario in which emissions continue to increase – sooner than anticipated in earlier studies.

Extremes matter

Both new studies build on 2023 research in which Diffenbaugh and Barnes predicted the years remaining until the 1.5 and 2 degrees Celsius goals are breached. But because these thresholds are based on average conditions over many years, they don’t tell the full story of how extreme the climate could become.

“As we watched these severe impacts year after year, we became more and more interested in predicting how extreme the climate could get even if the world is fully successful at rapidly reducing emissions,” said Diffenbaugh, the Kara J Foundation Professor and Kimmelman Family Senior Fellow at Stanford.

For a scenario in which emissions reach net-zero in the 2050s – the most optimistic scenario widely used in climate modeling – the researchers found a nine-in-ten chance that the hottest year this century will be at least 1.8 degrees Celsius hotter globally than the pre-industrial baseline, with a two-in-three chance for at least 2.1 degrees Celsius. 

For a scenario in which emissions decline too slowly to reach net-zero by 2100, Diffenbaugh and Barnes found a nine-in-ten chance that the hottest year will be 3 degrees Celsius hotter globally than the pre-industrial baseline. In this scenario, many regions could experience temperature anomalies at least triple what occurred in 2023.

Investing in adaptation

The new predictions underline the importance of investing not only in decarbonization but also in measures to make human and natural systems more resilient to severe heat, intensified drought, heavy precipitation, and other consequences of continued warming. Historically, those efforts have taken a back seat to reducing carbon emissions, with decarbonization investments outstripping adaptation spending in global climate finance and policies such as the 2022 Inflation Reduction Act. 

“Our results suggest that even if all the effort and investment in decarbonization is as successful as possible, there is a real risk that, without commensurate investments in adaptation, people and ecosystems will be exposed to climate conditions that are much more extreme than what they are currently prepared for,” Diffenbaugh said. 

 

---

 

Diffenbaugh is a professor of Earth system science in the Stanford Doerr School of Sustainability and a senior fellow in the Stanford Woods Institute for the Environment. 

The Geophysical Research Letters study was supported by Stanford University and the Regional and Global Model Analysis program area of the U.S. DOE Office of Biological and Environmental Research as part of the Program for Model Diagnosis and Intercomparison.

The Environmental Research Letters study was supported by Stanford University, the European Union’s Horizon 2020 and Horizon Europe programs, the Swiss State Secretariat for Education, Research and Innovation (SERI), and the Stanford Woods Institute for the Environment.

---

Journal

Geophysical Research Letters

DOI

10.1029/2024GL111832 

Article Title

Data-driven Predictions of Peak Warming Under Rapid Decarbonization

Article Publication Date

10-Dec-2024