How Google’s DeepMind tool is ‘more quickly’ forecasting hurricane behavior
When then Tropical Storm Melissa was churning south of Haiti, Philippe Papin, a National Hurricane Center (NHC) meteorologist, had confidence it was about to grow into a monster hurricane.As the lead forecaster on duty, he predicted that in just 24 hours the storm would become a category 4 hurricane and begin a turn towards the coast of Jamaica.No NHC forecaster had ever issued such a bold forecast for rapid strengthening.But Papin had an ace up his sleeve: artificial intelligence in the form of Google’s new DeepMind hurricane model – released for the first time in June.And, as predicted, Melissa did become a storm of astonishing strength that tore through Jamaica.
Forecasters at the NHC are increasingly leaning hard on Google DeepMind.On the morning of 25 October, Papin explained in his public discussion and on social media that Google’s model was a primary reason he was so confident: “Roughly 40/50 Google DeepMind ensemble members show Melissa becoming a Category 5.While I am not ready to forecast that intensity yet given the track uncertainty, that remains a possibility.“It appears likely that a period of rapid intensification will occur as the storm moves slowly over very warm ocean waters which is the highest oceanic heat content in the entire Atlantic basin.”Google DeepMind is the first AI model dedicated to hurricanes, and now the first to beat traditional weather forecasters at their own game.
Through all 13 Atlantic storms so far this year, Google’s model is the best – even beating human forecasters on track predictions.Melissa eventually made landfall in Jamaica at category 5 strength, one of the strongest landfalls ever documented in nearly two centuries of record-keeping across the Atlantic basin.Papin’s bold forecast likely gave people in Jamaica extra time to prepare for the disaster, possibly saving lives and property.Google DeepMind has been making weather forecasts for a few years now, and the parent forecast system from which the new hurricane model is derived also performed spectacularly well in diagnosing large-scale weather patterns last year.Google’s model works by spotting patterns that traditional time-intensive physics-based weather models may miss.
“They do it much more quickly than their physics-based cousins, and the computing power is less expensive and time consuming,” Michael Lowry, a former NHC forecaster, said,“What this hurricane season has proven in short order is that the newcomer AI weather models are competitive with and, in some cases, more accurate than the slower physics-based weather models we’ve traditionally leaned on,” Lowry said,To be sure, Google DeepMind is an example of machine learning – a technique that has been used in data-heavy sciences like meteorology for years – and is not generative AI like ChatGPT,Machine learning takes mounds of data and pulls out patterns from them in a such a way that its model only takes a few minutes to come up with an answer, and can do so on a desktop computer – in strong contrast to the flagship models that governments have used for decades that can take hours to run and require some of the biggest supercomputers in the world,Still, the fact that Google’s model could outperform previous gold-standard legacy models so quickly is nothing short of amazing to meteorologists who have spent their careers trying to forecast the world’s strongest storms.
Sign up to First ThingOur US morning briefing breaks down the key stories of the day, telling you what’s happening and why it mattersafter newsletter promotion“I’m impressed,” said James Franklin, a retired NHC forecaster,“The sample is now large enough that it’s pretty clear this is not a case of beginner’s luck,”Franklin said that although Google DeepMind is beating all other models on forecasting the future path of hurricanes worldwide this year, like many AI models it occasionally gets high-end intensity forecasts wrong,It struggled with Hurricane Erin earlier this year, as it was also undergoing rapid intensification to category 5 north of the Caribbean,It also struggled with Typhoon Kalmaegi – which made landfall in the Philippines on Monday.
In the coming offseason, Franklin said he plans to talk with Google about how it can make the DeepMind output even more helpful for forecasters by providing additional under-the-hood data they can use to assess exactly why it is coming up with the its answers.“The one thing that nags at me is that while these forecasts seem to be really, really good, the output of the model is kind of a black box,” said Franklin.There has never been a private, for-profit company that has produced a top-level weather model which allows researchers a peek into its methods – unlike nearly all other models which are provided free to the public in their entirety by the governments that designed and maintain them.While Google has made top-level output of DeepMind publicly available in real time on a dedicated website, its methods have still largely been hidden.Google is not alone in starting to use AI to solve difficult weather forecasting problems.
The US and European governments also have their own AI weather models in the works – which have also shown improved skill over previous non-AI versions.The next steps in AI weather forecasts seem to be startup companies taking swings at previously tough-to-solve problems such as sub-seasonal outlooks and better advance warnings of tornado outbreaks and flash flooding – and they are receiving US government funding to do so.One company, WindBorne Systems, is even launching its own weather balloons to fill the gaps in the US weather-observing network, which has recently been downsized by the Trump administration.
UK watchdogs need to step in on rip-off bills, which are bad for consumers and the economy | Heather Stewart
Ever felt swizzed by the small print in your mobile contract, bamboozled by a plethora of insurance products or locked into a subscription you signed up for by mistake?Then you are far from alone: a paper on the UK’s productivity predicament suggests the way the markets for some key services work is not only a monumental pain for consumers but bad for the economy, too.Rachel Reeves has promised to tackle the cost of living in her 26 November budget – alongside bringing in tax rises.Briefing in advance has suggested she and her colleagues are focused on cost-cutting levers they can easily pull from Whitehall: removing VAT on energy bills, for example.However, in their paper “getting Britain out of the hole”, the economists Andrew Sissons and John Springford suggest a much more muscular approach to making markets for key services work better.They argue that lack of proper competition for services is an important explanation for the UK’s frustratingly “sticky” inflation
‘I think the city is falling apart’: Leicester braces for a make-or-break budget
Anika* has a full-time job, but says she never eats in local cafes or restaurants and takes her lunch to work. The cost of living is too high for her to buy more than the basics of life.“Everything is so expensive. I cry, and ask myself what more can I do to make things better,” she says.The charity worker lives in Leicester, the local authority where people have the least spare cash after paying taxes, property ownership costs and pensions contributions
Personal details of Tate galleries job applicants leaked online
Personal details submitted by applicants for a job at Tate art galleries have been leaked online, exposing their addresses, salaries and the phone numbers of their referees, the Guardian has learned.The records, running to hundreds of pages, appeared on a website unrelated to the government-sponsored organisation, which operates the Tate Modern and Tate Britain galleries in London, Tate St Ives in Cornwall and Tate Liverpool.The data includes details of applicants’ current employers and education, and relates to the Tate’s hunt for a website developer in October 2023. Information about 111 individuals is included. They are not named but their referees are, sometimes with mobile numbers and personal email addresses
AI firm claims it stopped Chinese state-sponsored cyber-attack campaign
A leading artificial intelligence company claims to have stopped a China-backed “cyber espionage” campaign that was able to infiltrate financial firms and government agencies with almost no human oversight.The US-based Anthropic said its coding tool, Claude Code, was “manipulated” by a Chinese state-sponsored group to attack 30 entities around the world in September, achieving a “handful of successful intrusions”.This was a “significant escalation” from previous AI-enabled attacks it monitored, it wrote in a blogpost on Thursday, because Claude acted largely independently: 80 to 90% of the operations involved in the attack were performed without a human in the loop.“The actor achieved what we believe is the first documented case of a cyber-attack largely executed without human intervention at scale,” it wrote.Anthropic did not clarify which financial institutions and government agencies had been targeted, or what exactly the hackers had achieved – although it did say they were able to access their targets’ internal data
Santi Carreras orchestrates stunning Argentina comeback against Scotland
Nothing short of a disaster for Scotland, but a magnificent comeback by Argentina. The hosts were 21-0 up and cruising in the second half when a loose Finn Russell pass was seized on by opponents who had been poor until that point.Blair Kinghorn was soon in the sin‑bin and a sensational flurry of five Argentina tries in the final 24 minutes sealed Scotland’s fate. It was all orchestrated in stunning fashion by Santi Carreras of Bath, one of six replacements who appeared together after half-time.Disappointment generated by inaccuracy and uncertainty is a familiar refrain for home fans but this, a record comeback for Argentina in Test rugby, was far more painful than most
Ford urges England to ensure win over New Zealand is no ‘flash in the pan’
George Ford has called on England to make sure their statement victory against the All Blacks is not a false dawn after Steve Borthwick’s side extended their winning run to 10 matches.England have moved up to third in the world rankings after their impressive 33-19 win against New Zealand on Saturday and could go second next weekend should they defeat Argentina and Wales spring a surprise against the All Blacks.In Borthwick’s tenure as head coach, England have managed narrow victories against Ireland and France but the commanding win against the All Blacks – a first at Twickenham since 2012 – goes down as their finest achievement under the head coach.Under Jones, England defeated New Zealand in the 2019 World Cup semi-final in stunning style but a week later South Africa were comfortable 32-12 winners in the final. The 2012 victory gave rise to optimism at the end of Stuart Lancaster’s first year in charge but the bubble burst when England were thrashed 30-3 by Wales in Cardiff in the following Six Nations
Benjamina Ebuehi’s recipe for apple, brown butter and oat loaf | The sweet spot
Kids have a wobble in the face of rabbit jelly | Brief letters
Think autumn, think Piedmont – wine from ‘the foot of the mountain’
‘I’m now a one-issue voter’: US shoppers fear Italian pasta tariff will cause shortage
Jimi Famurewa’s recipe for puff-puff pancakes
Polpa position: budget tinned tomatoes score well in Choice taste test