Computer models that use artificial intelligence (AI) cannot forecast record-breaking weather as well as traditional climate models, according to a new study.
It is well established that AI climate models have surpassed traditional, physics-based climate models for some aspects of weather forecasting.
However, new research published in Science Advances finds that AI models still “underperform” in forecasting record-breaking extreme weather events.
The authors tested how well both AI and traditional weather models could simulate thousands of record-breaking hot, cold and windy events that were recorded in 2018 and 2020.
They find that AI models underestimate both the frequency and intensity of record-breaking events.
A study author tells Carbon Brief that the analysis is a “warning shot” against replacing traditional models with AI models for weather forecasting “too quickly”.
AI weather forecasts
Extreme weather events, such as floods, heatwaves and storms, drive hundreds of billions of dollars in damages every year through the destruction of cropland, impacts on infrastructure and the loss of human life.
Many governments have developed early warning systems to prepare the general public and mobilise disaster response teams for imminent extreme weather events. These systems have been shown to minimise damages and save lives.
For decades, scientists have used numerical weather prediction models to simulate the weather days, or weeks, in advance.
These models rely on a series of complex equations that reproduce processes in the atmosphere and ocean. The equations are rooted in fundamental laws of physics, based on decades of research by climate scientists. As a result, these models are referred to as “physics-based” models.
However, AI-based climate models are gaining popularity as an alternative for weather forecasting.
Instead of using physics, these models use a statistical approach. Scientists present AI models with a large batch of historical weather data, known as training data, which teaches the model to recognise patterns and make predictions.
To produce a new forecast, the AI model draws on this bank of knowledge and follows the patterns that it knows.
There are many advantages to AI weather forecasts. For example, they use less computing power than physics-based models, because they do not have to run thousands of mathematical equations.
Furthermore, many AI models have been found to perform better than traditional physics-based models at weather forecasts.
However, these models also have drawbacks.
Study author Prof Sebastian Engelke, a professor at the research institute for statistics and information science at the University of Geneva, tells Carbon Brief that AI models “depend strongly on the training data” and are “relatively constrained to the range of this dataset”.
In other words, AI models struggle to simulate brand new weather patterns, instead tending forecast events of a similar strength to those seen before. As a result, it is unclear whether AI models can simulate unprecedented, record-breaking extreme events that, by definition, have never been seen before.
Record-breaking extremes
Extreme weather events are becoming more intense and frequent as the climate warms. Record-shattering extremes – those that break existing records by large margins – are also becoming more regular.
For example, during a 2021 heatwave in north-western US and Canada, local temperature records were broken by up to 5C. According to one study, the heatwave would have been “impossible” without human-caused climate change.
The new study explores how accurately AI and physics-based models can forecast such record-breaking extremes.
First, the authors identified every heat, cold and wind event in 2018 and 2020 that broke a record previously set between 1979 and 2017. (They chose these years due to data availability.) The authors use ERA5 reanalysis data to identify these records.
This produced a large sample size of record-breaking events. For the year 2020, the authors identified around 160,000 heat, 33,000 cold and 53,000 wind records, spread across different seasons and world regions.
For their traditional, physics-based model, the authors selected the High RESolution forecast model from the Integrated Forecasting System of the European Centre for Medium-Range Weather Forecasts. This is “widely considered as the leading physics-based numerical weather prediction model”, according to the paper.
They also selected three “leading” AI weather models – the GraphCast model from Google Deepmind, Pangu-Weather developed by Huawei Cloud and the Fuxi model, developed by a team from Shanghai.
The authors then assessed how accurately each model could forecast the extremes observed in the year 2020.
Dr Zhongwei Zhang is the lead author on the study and a researcher at Karlsruhe Institute of Technology. He tells Carbon Brief that many AI weather forecast models were built for “general weather conditions”, as they use all historical weather data to train the models. Meanwhile, forecasting extremes is considered a “secondary task” by the models.
The authors explored a range of different “lead times” – in other words, how far into the future the model is forecasting. For example, a lead time of two days could mean the model uses the weather conditions at midnight on 1 January to simulate weather conditions at midnight on 3 January.
The plot below shows how accurately the models forecasted all extreme events (left) and heat extremes (right) under different lead times. This is measured using “root mean square error” – a metric of how accurate a model is, where a lower value indicates lower error and higher accuracy.
The chart on the left shows how two of the AI models (blue and green) performed better than the physics-based model (black) when forecasting all weather across the year 2020.
However, the chart on the right illustrates how the physics-based model (black) performed better than all three AI models (blue, red and green) when it came to forecasting heat extremes.
The authors note that the performance gap between AI and physics-based models is widest for lower lead times, indicating that AI models have greater difficulty making predictions in the near future.
They find similar results for cold and wind records.
In addition, the authors find that AI models generally “underpredict” temperature during heat records and “overpredict” during cold records.
The study finds that the larger the margin that the record is broken by, the less well the AI model predicts the intensity of the event.
‘Warning shot’
Study author Prof Erich Fischer is a climate scientist at ETH Zurich and a Carbon Brief contributing editor. He tells Carbon Brief that the result is “not unexpected”.
He adds that the analysis is a “warning shot” against replacing traditional models with AI models for weather forecasting “too quickly”.
The analysis, he continues, is a “warning shot” against replacing traditional models with AI models for weather forecasting “too quickly”.
AI models are likely to continue to improve, but scientists should “not yet” fully replace traditional forecasting models with AI ones, according to Fischer.
He explains that accurate forecasts are “most needed” in the runup to potential record-breaking extremes, because they are the trigger for early warning systems that help minimise damages caused by extreme weather.
Leonardo Olivetti is a PhD student at Uppsala University, who has published work on AI weather forecasting and was not involved in the study.
He tells Carbon Brief that “many other studies” have identified issues with using AI models for “extremes”, but this paper is novel for its specific focus on extremes.
Olivetti notes that AI models are already used alongside physics-based models at “some of the major weather forecasting centres around the world”. However, the study results suggest “caution against relying too heavily on these [AI] models”, he says.
Prof Martin Schultz, a professor in computational earth system science at the University of Cologne who was not involved in the study, tells Carbon Brief that the results of the analysis are “very interesting, but not too surprising”.
He adds that the study “justifies the continued use of classical numerical weather models in operational forecasts, in spite of their tremendous computational costs”.
Advances in forecasting
The field of AI weather forecasting is evolving rapidly.
Olivetti notes that the three AI models tested in the study are an “older generation” of AI models. In the last two years, newer “probabilistic” forecast models have emerged that “claim to better capture extremes”, he explains.
The three AI models used in the analysis are “deterministic”, meaning that they only simulate one possible future outcome.
In contrast, study author Engelke tells Carbon Brief that probabilistic models “create several possible future states of the weather” and are therefore more likely to capture record-breaking extremes.
Engelke says it is “important” to evaluate the newer generation of models for their ability to forecast weather extremes.
He adds that this paper has set out a “protocol” for testing the ability of AI models to predict unprecedented extreme events, which he hopes other researchers will go on to use.
The study says that another “promising direction” for future research is to develop models that combine aspects of traditional, physics-based weather forecasts with AI models.
Engelke says this approach would be “best of both worlds”, as it would combine the ability of physics-based models to simulate record-breaking weather with the computational efficiency of AI models.
Dr Kyle Hilburn, a research scientist at Colorado State University, notes that the study does not address extreme rainfall, which he says “presents challenges for both modelling and observing”. This, he says, is an “important” area for future research.
The post Traditional models still ‘outperform AI’ for extreme weather forecasts appeared first on Carbon Brief.
Traditional models still ‘outperform AI’ for extreme weather forecasts
Climate Change
WA EPA warned Woodside of ‘serious, significant and irreversible’ harms to Scott Reef from gas plans, new documents reveal
SYDNEY/PERTH, Tuesday 27 October 2026 — In response to Western Australian Environmental Protection Authority (WA EPA) documents about Woodside’s plans to drill for gas at Scott Reef, as reported today, the following comments can be attributed to Glenn Walker, Head of Nature at Greenpeace Australia Pacific:
“These WA EPA documents show the depth of concern echoed by multiple regulators about Woodside’s plans to drill for oil and gas at Scott Reef, a proposal that flouts legislated nature protection principles.
“The WA EPA appears to have informed Woodside that the Browse project was bound for rejection based on an extensive review process and the opinion of multiple state government departments and independent experts.
“Greenpeace analyses have confirmed this year that Woodside’s gas drilling plans at Scott Reef still risk destroying vulnerable green turtle homes, further endangering pygmy blue whales with atomic bomb-level seismic blasting noise, and unleashing the worst oil spill in Australian history.
“The federal environment department raised similar red flags about oil spill risk from Woodside’s Scott Reef drilling plans in 2025 and 2026 before handing the project’s assessment over to the National Environmental Protection Authority.
“Woodside’s suggested ‘fixes’ in response to grave concerns for the wellbeing of Scott Reef and threatened species have been unilaterally criticised by independent experts for lacking in scientific basis and adequate detail.
“It would be a major backflip for both the WA EPA and the National EPA to now recommend approving this project. It is now critical that these regulators maintain their independence from corporate and political influence and reject this destructive project once and for all.”
-ENDS-
Notes to editor
Greenpeace Technical assessments of Woodside’s Browse Pygmy Blue Whale Management Plan, the Turtle Management Plan, and an analysis of Woodside’s Browse Oil Spill Modelling and Risk Mitigation Plan
High res images and footage of Scott Reef can be found here
Media contact:
Emma Sangalli at emma.sangalli@greenpeace.org or 0431 513 465
The surprise re-election of Brazil’s President Luiz Inácio Lula da Silva on Sunday, in a tight race against right-wing candidate Flávio Bolsonaro, has raised hopes the country can meet a flagship target to end deforestation in all its biomes by 2030 and advance international fundraising to protect rainforests.
Defying expectations to win an unprecedented fourth term in office, Lula – who turns 81 this week – said in his acceptance speech that “we will show the world how climate policy is handled in this country”, and highlighted that, during his last four years as leader, the country has reduced deforestation every year.
Earlier this month, new data from Brazil’s space agency showed that forest-clearing in the Amazon fell to its lowest on record, after the introduction of a deforestation action plan that constrained illegal cattle ranching from expanding into the world’s largest rainforest.
Brazil leads “encouraging” decline in global rainforest destruction in 2025
At an international level, the country has long championed forest conservation, spearheading the creation of the newly established Tropical Forest Forever Facility (TFFF). As president of last year’s COP30 climate summit, the country is also developing a global roadmap to halt forest loss by the end of the decade, in line with a global goal, which will be presented at the upcoming UN climate summit in Antalya.
‘Much more needs to be done’
In 2023, Lula’s previous administration introduced a deforestation action plan that set a target of zero deforestation by 2030, achieving swift results. His re-election paves the way for this downward trend to continue.
Carlos Nobre, a veteran Brazilian climate scientist and co-chair of the Science Panel for the Amazon, said Brazil now has a “historic opportunity” to prevent a tipping point where large parts of the Amazon rainforest could turn into savanna, with dangerous impacts for the planet’s climate.
“The reduction in deforestation over recent years has been crucial, but much more needs to be done. Ending deforestation by 2030, tackling forest degradation and accelerating large-scale forest restoration are urgent priorities,” he said.
Anders Haug Larsen, advocacy director at the Norway Rainforest Foundation, described the election result as a “relief”, adding it makes it more attractive for donors to support rainforest protection in the country.
“Hope is a scarce commodity these days,” he said. “The international community must grasp this opportunity to strengthen efforts towards zero deforestation in the Amazon.”
Rainforest fund boosted by election result
Brazil was the original proponent of the TFFF, one of the highest-profile initiatives aimed at channelling new finance to protect the world’s rainforests. The fund aims to raise public seed capital to invest in financial markets, and then pay rainforest countries from the returns on those investments.
Despite being a developing country, Brazil has pledged $1 billion to the fund and is expected to play a key role in helping reach its goal to raise $10 billion from governments by the end of this year.
“We need more countries to come on board to meet the mobilisation target of $10 billion this year, and this election should inject trust in the calls from rainforest countries for support to their forest protection efforts,” Larsen said.
Brazil confident new rainforest fund will reach $10bn donor milestone
On Monday, the day after the election result, the Netherlands announced a €500-million contribution to the fund, which will be disbursed over ten years and is still subject to parliamentary approval. This brings the total pledged to the TFFF from a range of countries to $7.8 billion.
Norway’s climate minister Sigrun Aasland told a TFFF event on the sidelines of the UN biodiversity summit in Yerevan that she was hopeful the $10bn goal could be achieved by the end of this year.
Brazilian officials have led the TFFF’s fundraising efforts and said they are in conversations with more potential donors including China, Korea and Japan.
Congress shifts further to the right
Sonia Guajajara, former minister of Indigenous Peoples in Lula’s government, celebrated the president’s re-election but cautioned that the 20 indigenous territories created under his current administration must be consolidated, as they are “essential to tackling the climate crisis and preserving our biomes”.
Veteran Brazilian diplomat Bráulio Ferreira de Souza Dias, meanwhile, noted that Lula faces a difficult political scenario, as right-wing pro-Bolsonaro lawmakers have gained more seats in both legislative chambers. He added that the courts will become key battlegrounds to challenge anti-climate legislation.
Observatório do Clima, a network of Brazilian green groups, said seven out of every ten representatives and senators who will make up the next legislature are likely to vote against the climate and environmental agenda, urging Lula’s administration to strengthen its action in parliament and expand alliances.
Still, Ferreira de Souza Dias echoed the widespread view among climate policy-makers that a Bolsonaro win would have been “terrible” for the rainforest and Indigenous peoples, and said the country had avoided a scenario where deforestation threatened to increase again.
The post Lula’s election win in Brazil raises hopes for zero deforestation drive appeared first on Climate Home News.
Lula’s election win in Brazil raises hopes for zero deforestation drive
African governments are developing policies to manage waste from solar panels, batteries and other clean tech equipment as installations surge, with officials warning the energy transition could create a new environmental problem unless it is accompanied by investment in recycling and reuse.
Many African households and businesses are increasingly turning away from unreliable grid power or deciding not to wait for access, and are installing more solar panels and battery storage. Data from energy think-tank Ember, published in August, projects that the continent will install a record 17 gigawatts (GW) of solar capacity in 2026 – equal to around 100,000 solar panels every day. This would mark the third consecutive year of record growth, following increases of 51% in 2025 and 25% in 2024.
While generally a welcome sign of progress towards a cleaner energy mix, this trend could also create a headache for African officials. Anselm Marungu, Namibia’s deputy minister of environment, forestry and tourism, believes rules should be put in place to ensure that valuable materials can be recovered from discarded solar panels, batteries and inverters at the end of their useful life.
-
Made in Nigeria: The race to build an African solar industry from scratch
A solar power revolution is gathering pace in Africa and Nigeria wants a slice of the fast-growing industry, but competing with Chinese imports won’t be easy -
Indian start-ups mine e-waste for battery minerals but growing industry has a dark side
Recycling e-waste can unlock a vast and sustainable supply of transition minerals but in India the sector relies on a neglected informal economy
