
-
Youthful Matildas provide spark in friendly win over South Korea
-
Stocks, oil extend rout as China retaliates over Trump tariffs
-
De Bruyne says he will leave Man City at end of season
-
UK spy agency MI5 reveals fruity secrets in new show
-
Leverkusen's Wirtz to return 'next week', says Alonso
-
England bowler Stone to miss most of India Test series
-
Taiwan earmarks $2.7 bn to help industries hit by US tariffs
-
Rat earns world record for sniffing landmines in Cambodia
-
Elton John says new album 'freshest' since 1970s
-
EU announces 'new era' in relations with Central Asia
-
Greece nixes Acropolis shoot for 'Poor Things' director
-
'Historic moment': South Koreans react to Yoon's dismissal
-
Israel kills Hamas commander in Lebanon strike
-
Trump unveils first $5 million 'gold card' visa
-
Crashes, fires as Piastri fastest in chaotic second Japan GP practice
-
India and Bangladesh leaders meet for first time since revolution
-
Israel expands ground offensive in Gaza
-
Families of Duterte drug war victims demand probe into online threats
-
Stocks extend global rout after Trump's shock tariff blitz
-
Kolkata's Iyer more bothered about impact than price tag
-
BP chairman to step down after energy strategy reset
-
Indian patriotic movie 'icon' Manoj Kumar dies aged 87
-
China floats battle barges in Taiwan invasion plans
-
McLaren's Piastri fastest in chaotic second Japanese GP practice
-
South Korea seize two tons of cocaine in largest-ever drug bust
-
Pacific nations perplexed, worried by Trump tariffs
-
The race to save the Amazon's bushy-bearded monkeys
-
TikTok must find non-Chinese owner by Saturday to avert US ban
-
Trump tariffs to test resiliency of US consumers
-
Clamping down on 'forever chemicals'
-
Prominent US academic facing royal insult charge in Thailand
-
Yana, a 130,000-year-old baby mammoth, goes under the scalpel
-
'Don't want to die': Lesotho HIV patients look to traditional medicine
-
Curry scores 37 as Warriors outgun LeBron's Lakers
-
Crops under threat as surprise March heatwave hits Central Asia: study
-
Japan PM says Trump tariffs a 'national crisis'
-
Security 'breakdown' allows armed men into Melbourne's MCG
-
Norris fastest in Japan GP first practice, Tsunoda sixth on Red Bull debut
-
Albon says Thailand taking bid for F1 race 'very seriously'
-
'It's gone': conservation science in Thailand's burning forest
-
Protest as quake-hit Myanmar junta chief joins Bangkok summit
-
EU leaders push for influence at Central Asia summit
-
Asian stocks extend global rout after Trump's shock tariff blitz
-
Lewandowski, Mbappe duel fuelling tight La Liga title race
-
South Korea court upholds President Yoon's impeachment, strips him of office
-
Liverpool march towards title as Man City face Man Utd
-
Finland's colossal bomb shelters a model for jittery Europe
-
Athletes frustrated as France mulls Muslim headscarf ban in sport
-
Korda downs Kupcho to stay alive at LPGA Match Play
-
German industry grapples with AI at trade fair

Google says AI weather model masters 15-day forecast
A new artificial intelligence-based weather model can deliver 15-day forecasts with unrivaled accuracy and speed, a Google lab said, with potentially life-saving applications as climate change ramps up.
GenCast, invented by London-based AI research laboratory Google DeepMind, "showed better forecasting skill" than the current world-leading model, the company said Wednesday.
The European Centre for Medium-Range Weather Forecasts (ECMWF) produces predictions for 35 countries and is considered the global benchmark for meteorological accuracy.
But DeepMind said GenCast surpassed the precision of the center's forecasts in more than 97 percent of the 1,320 real-world scenarios from 2019 which they were both tested on.
Details of its findings were published in Nature, a leading science journal.
ECMWF chief Florence Rabier told AFP the project was a "first step" towards integrating AI in weather forecasting but that "it is indeed a leap forward."
At this stage it can be used to supplement their current models, she said.
"We are progressing year by year," she added. "Any new method that can enhance and accelerate this progress is extremely welcome in the context of the extreme societal pressures of climate change."
The model was trained on four decades of temperature, wind speed and air pressure data from 1979 to 2018 and can produce a 15-day forecast in just eight minutes -- compared to the hours it currently takes.
"GenCast provides better forecasts of both day-to-day weather and extreme events than the top operational system... up to 15 days in advance," a DeepMind statement said.
Scientists have warned extreme weather is becoming more common and more severe as a result of man made climate change.
Last August, a series of wildfires in Hawaii killed around 100 people. Authorities were criticized by locals who said they were given no warning of the impending blaze.
This summer, a sudden heatwave in Morocco killed at least 21 people over a 24-hour period. And in September, Hurricane Helene killed 237 people in Florida and other southeastern US states.
DeepMind said GenCast "consistently outperformed" the current leading forecast model when predicting extreme heat, extreme cold and high wind speeds.
"More accurate forecasts of risks of extreme weather can help officials safeguard more lives, avert damage, and save money," DeepMind said.
Th.Berger--AMWN