Latest news with #cyclones
The Independent
22-05-2025
- Science
- The Independent
AI is already beating traditional forecasters when it comes to predicting weather
A new AI model is outperforming the world's top forecasting systems for weather, pollution and cyclones, according to a new study, boosting hopes of weather forecasting becoming cheaper and more accurate. The model, called Aurora, accurately predicted cyclone paths and produced weather forecasts in a matter of seconds instead of hours. It was trained on a vast collection of atmospheric data, like weather observations, climate simulations and satellite measurements, by researchers at Microsoft and the University of Pennsylvania. When evaluated against global forecasting benchmarks, the AI system consistently produced faster forecasts than traditional models and, in many cases, offered greater accuracy, according to the new research published in Nature. Aurora was able to predict the path of Doksuri, the costliest Pacific typhoon of 2023, four days before landfall. While official weather agencies forecast landfall in Taiwan, Aurora correctly placed it in the northern Philippines. It also tracked the path and wind speeds of the storm Ciarán, which struck northwestern Europe last autumn, outperforming traditional models as well as newer systems based on AI like GraphCast and FourCastNet. According to the study, Aurora was the only model to correctly estimate peak winds from the storm. The results mark a major advance in modelling complex Earth systems with speed and accuracy. 'Earth's climate is perhaps the most complex system we study, with interactions spanning from quantum scales to planetary dynamics,' noted Dr Paris Perdikaris, associate professor at the University of Pennsylvania. 'With Aurora, we addressed a fundamental challenge in Earth system prediction: how to create forecasting tools that are both more accurate and dramatically more computationally efficient." The system is not limited to weather. Aurora has also been tested for forecasting air quality and ocean waves. In one case study, it accurately predicted a large sandstorm in Iraq, which closed airports and led to over 5,000 hospitalisations, a day before it occurred. The model managed to do this despite being trained without explicit knowledge of atmospheric chemistry. Aurora 'did not have any prior knowledge about atmospheric chemistry or how nitrogen dioxide, for instance, interacts with sunlight," said study co-first author Dr Megan Stanley of Microsoft Research, 'that wasn't part of the original training.' "And yet,' she said, 'in fine-tuning, Aurora was able to adapt to that because it had already learned enough about all of the other processes'. The model was also able to simulate complex ocean wave patterns generated by typhoons such as Nanmadol, which struck Japan in 2022. Aurora captured wave heights and direction with more detail and higher accuracy than the standard ocean forecasting systems in use today. 'When we compared Aurora to official forecasts from agencies like the National Hurricane Centre, China Meteorological Administration and others, Aurora outperformed all of them across different basins worldwide," said Dr Perdikaris. The model works by identifying patterns in large environmental datasets instead of solving physical equations. This allows it to generate 10-day weather forecasts and 5-day air quality predictions in under a minute, compared to the hours needed by traditional models running on supercomputers. Unlike traditional systems that need supercomputers, a key advantage of Aurora is that it can run on simpler machines. This could make accurate local forecasts possible even in countries with limited resources. 'The most transformative aspect is democratising access to high-quality forecasts,' Dr Perdikaris said. 'Traditional systems require supercomputers and specialised teams, putting them out of reach for many communities worldwide. Aurora can run on modest hardware while matching or exceeding traditional model performance.' The new AI model's foundation architecture allows it to be fine-tuned for various forecasting tasks, from local rain patterns to seasonal trends. "Knowledge gained from one area, such as atmospheric dynamics used in weather forecasting, enhances its predictive performance in other domains, including air quality modelling or predicting tropical cyclone formation," noted Dr Perdikaris. 'This cross-domain learning is central to the foundation model philosophy that guides my broader research programme.' Each new application requires only a small amount of additional data. According to Microsoft, some fine-tuning experiments took only a few weeks compared to the years typically needed to build numerical models. Although Aurora still needs existing data sources to generate forecasts, researchers say its speed and flexibility could make it useful for real-time applications in the future. Microsoft says the source code and model weights are publicly available and Aurora is already being used to improve weather services on its MSN platform. The researchers are interested in extending the model to generate predictions on a wider range of Earth system behaviours, including local and seasonal weather, extreme rainfall and urban flooding. "What excites me most about this technology is its broader applicability," Dr Perdikaris. "At Penn, we are exploring how similar foundation model approaches can address other prediction challenges beyond weather – from urban flooding to renewable energy forecasting to air quality management – making powerful predictive tools accessible to communities that need them most." Its developers believe that similar systems could eventually be adapted for other forecasting challenges, including floods, heatwaves and agriculture.
Yahoo
17-05-2025
- Science
- Yahoo
Seismic Waves From Intense Storms Can Ripple Through Earth's Core
Researchers have now 'heard' the echo of cyclones whirling ocean waters from all the way on the other side of our planet. Microseismic waves generated by interactions between the ocean and Earth's crust might be able to help us peer into otherwise hidden parts of Earth's geological structure, such as regions left shrouded by a scarcity of high-energy earthquakes in the North Atlantic. "Our research uses these microseismic phenomena as an alternative data source to study the Earth's structure beneath Australia," says seismologist Hrvoje Tkalčić from Australian National University. Intense storm activity like cyclones over the ocean produces acoustic energy strong enough to ring through the planet. By the time these vibrations pass through Earth's core though, they're incredibly subtle. So Tkalčić and fellow seismologist Abhay Pandey went searching for these seismic waves using sensitive spiral arrays of sensors located in extremely quiet, remote parts of Australia. "We combined data from multiple days to identify the regions where the signals were strongest, providing insights into the source and transmission of the seismic waves," explains Pandey. "The signals are tiny in amplitude and often below the observational threshold of a single sensor, requiring specific instrument designs to record them." The researchers were able to trace these signals back to the waters near Greenland and Newfoundland, stirred up by winter storms. "The Newfoundland basin is a significant and persistent source of microseisms observed on most days during the study period, which is likely linked to the movement of frequent cyclones during the winter months," Pandey and Tkalčić write in their paper. This new method of detecting signals through the Earth may also prove useful for exploration of alien worlds. "We live in the times of interplanetary voyages, and perhaps it is not far-fetched to say that in the not-so-distant future, we might be able to harness the energy of storms to complement the investigations of the interiors of planets and several moons upholding atmospheres," the researchers conclude. This research was published in Seismological Research Letters. New Theory Suggests Dark Matter Is Frozen Relics of Light-Speed Particles The End of The Universe Could Come 'Much Sooner' Than We Thought We Finally Know Why Ancient Roman Concrete Lasts Thousands of Years
Times
06-05-2025
- Business
- Times
Shell's LNG production hit by cyclones in Australia
Shell produced less liquefied natural gas (LNG) than expected in the first quarter after bad weather and unplanned maintenance in Australia. Europe's biggest oil and gas group lowered its guidance for LNG output yesterday ahead of publishing its first quarter results on May 2. Shell now expects to report production of between 6.4 million and 6.8 million tons of LNG in the three months to the end of March, down from a previous forecast of 6.6 million to 7.2 million tons. That would also be a reduction from the 7.1 million tons it produced in the fourth quarter of last year. • Can Shell investors really be sure of Wael Sawan? Shell blamed the cut on a combination of cyclones and unplanned maintenance. It said
Reuters
03-04-2025
- Business
- Reuters
Steep US tariffs on Africa signal end of trade deal meant to boost development
JOHANNESBURG/ANTANANARIVO, April 3 (Reuters) - The U.S. government's imposition of steep tariffs on African nations signals the end of the AGOA trade deal that was supposed to help African economies develop through preferential access to U.S. markets, trade experts said on Thursday. Several African countries were hit by some of the highest tariffs announced by U.S. President Donald Trump on Wednesday, including levies of 50% on goods from Lesotho, 47% for Madagascar, 40% for Mauritius, 37% for Botswana and 30% for South Africa, the continent's biggest exporter to the U.S. Many of the hardest-hit countries are already struggling with very high levels of poverty and debt as well as, in some cases, other severe challenges such as food shortages or cyclones in Madagascar, and one of the world's highest rates of HIV/AIDS infections in Lesotho. The tariffs also compound the pain for Africa after Trump's administration dismantled USAID, the government agency that was a major supplier of aid to the continent, and specifically cut bilateral aid to South Africa. The AGOA trade accord is due to expire in September, and the raft of tariffs suggests that a renewal of the deal, a major part of U.S. policy towards the continent since the 1990s era of President Bill Clinton, is extremely unlikely. "The reciprocal trade announcement policy will pull the AGOA rug from under our feet. That will be gone. It will replace AGOA, you don't have to wait for September. It'll be gone before then," said economist Adrian Saville, a professor at South Africa's Gordon Institute of Business Science. It was unclear whether AGOA tariff exemptions on certain goods would continue to be applied between now and September in the wake of Trump's tariff barrage. "There is no indication that imports under AGOA are exempt from the 10% tariffs, so it appears that effectively immediately AGOA imports that previously were duty-free are now subject to a 10% duty," the Washington-based African Coalition for Trade said in a memo to members on Thursday. "This is obviously not a positive sign for the outlook for renewal of AGOA." However, the permanent secretary at Kenya's foreign ministry, Korir Sing'Oei, said his understanding was that tariff exemptions under AGOA would remain valid until the act's expiry. In South Africa, whose second largest trading partner is the U.S., after China, the government struck a hopeful note despite the blow. "The tariffs affirm the urgency to negotiate a new bilateral and mutually beneficial trade agreement with the U.S., as an essential step to secure long-term trade certainty," the presidency said in a statement. But a new trade deal with Washington looks like a mountain to climb for Pretoria. Trump has repeatedly lambasted South Africa, the country that overcame apartheid, over what he described as discriminatory policies against white people. U.S.-South African relations have soured since Trump cut U.S. financial aid to the country, citing disapproval of its land policy and its genocide case at the International Court of Justice against Washington's ally Israel. Trump's latest tariffs are in addition to the 25% imposed on all vehicles and car parts imported into the U.S., which will kick in from Thursday. South Africa's exports of vehicles and parts into the U.S. are estimated at over $2 billion and could be hit hard by the levies. Speaking at an investment conference in Johannesburg, South African Trade Minister Parks Tau said the current global economic uncertainty was affecting demand for South Africa's products and its ability to create jobs. "If there is one message that we must convey today, it is that diversifying trade relationships is absolutely critical." In 2024, U.S. imports from South Africa totalled $14.7 billion, up 4.9% from 2023, according to the Office of the United States Trade Representative. Major South African exports to the U.S. include precious stones and metals, motor vehicle parts and accessories, iron and steel, machinery and aluminium products. Lesotho, a tiny landlocked country surrounded by South Africa, is the second largest exporter of textiles and garments to the U.S. under AGOA. In 2024 it exported goods worth $237 million into the U.S., a 4.7% increase over 2023.
