Latest news with #weatherforecast
BBC News
12 hours ago
- Climate
- BBC News
Weather forecasts: The tech giants use AI but is it any good?
A wave of machine-learning weather models have been unleashed by some of the very biggest businesses on the challenge the orthodoxy of traditional physics-based computer forecasts that have been incrementally developed and improved over many decades. But are the machine learning models any good? The weather is a national obsession for us Brits, and it is no wonder given the huge changes that are seen and felt from one day to the next. Accurate weather forecasts are not just vital for planning our daily lives but knowing about upcoming severe weather can help us to change our behaviour, save lives and mitigate damage to is impossible to assess the full economic value of weather forecasts globally, but the numbers are huge. According to NOAA (National Oceanic and Atmospheric Administration), in the US alone - and just taking into account the biggest weather disasters that caused over $1bn (£740m) in damage - the fallout from severe weather in 2024 amounted to $182bn, with 568 1980, this damage figure stands at nearly $3tn! Meanwhile, in the UK, there were 1,311 excess deaths caused by heatwaves in 2024.A study from consultants, external, London Economics, concluded that the Met Office would bring £56bn of benefits to the UK economy over the course of a decade through providing meteorological services. Multiply these kinds of numbers across the whole world, with a growing population exposed to increasingly extreme weather fuelled by climate change, and weather is big business. The biggest computers on the planet Traditional weather forecasts are produced on some of the biggest supercomputers on the planet; the Met Office super computing contract is worth £1.2bn. That huge sum of money buys you a machine that can perform 60 quadrillion (60,000,000,000,000,000) calculations per second, running a model containing the understood physics, with over a million lines of code and using 215 billion weather observations. Global weather models work by crunching the numbers in a grid of boxes right around the planet. The size or resolution of these boxes varies across different meteorological models, but range between about 10sq km to 28sq km (3.86sq miles to 10.81sq miles).At this kind of resolution they cannot accurately predict showers, while mountain ranges are lower and smoother than in the real world. The highest resolution model from the Met Office, the UKV (the model that runs BBC TV graphics for the first 48 hours) can predict showers with its incredible 1.5km (0.9 mile) resolution - but it takes so much computing time and power that this model is not able to forecast for the entire world; instead it concentrates on the UK and Europe. Machine-learning weather models: are they any good? Machine-learning weather models have only been around for a few years, showing promise as they develop rapidly. Traditional models take hours to run on hugely expensive supercomputers, however this new breed of models can take less than a minute to run on a standard laptop. They don't need to know all the 'burdensome' laws of physics, but are instead trained on 40 years of past data to make their do they perform? Well let's look at forecast verification data from ECMWF (European Centre for Medium Range weather Forecasting) for atmospheric pressure patterns in winter 2024/2025, (Google), AIFS (ECMWF) and Aurora (Microsoft) were more accurate than the traditional IFS (ECMWF) benchmark forecast, whereas FourCastNet (Nvidia) and Pangu-Weather (Huawei) trailed some of the machine-learning models performed better, and some worse, but it depends on which variable you look at, and all of this could change quickly as the rate of progress accelerates. Just like traditional models, AI models are less accurate the further ahead in the future they're trying to predict - a consequence of the chaotic nature of the atmosphere. Looking 10 days ahead, none of the AI models (or traditional models) were able to offer forecasts considered to be of much use in terms of accuracy. So is it time to walk away from physics-based weather models? Not yet! Machine-learning weather models are not only trained using data produced by traditional weather models, but they also use the start position of the atmosphere from traditional models as their input point. In other words, without those traditional models running, the machine-learning models wouldn't work as machine-learning models can forecast large scale features like high and low pressure six days ahead very well, but they can underperform compared to traditional models at smaller-scales of 1000km or means that important features like troughs and ridges could be missed, which would make the difference between a dry day, or a day with heavy rain. The majority of machine learning models have a resolution of 28sq km, which is the same scale as the data that they've trained on. This means small features like showers would most likely be missed, so they wouldn't be able to forecast a Boscastle flood event many days headlines have claimed that these new models are better than traditional models at predicting hurricanes. It may be true that some have been a little better at predicting the landfall of hurricanes ahead of traditional models, but at the same time they have been very poor at predicting the wind strength and therefore the likely damage the storm would bring. This may be the result of the smoothing, or averaging effect of looking at lots of hurricanes in the 40 years of training data. AI models may struggle to forecast effects from rare events that have not been seen often in the 40 years of training data. An example of this is the 1991 eruption of Mount Pinatubo that cooled the planet down by up to 0.5C for two are also questions about how well AI models will forecast in a warmer world as our planet continues to heat up as a result of climate change. The past climate that they've trained on will look quite different to our future climate, as greenhouse gases continue to accumulate in the where will we be in five years time?"I think we'll have traditional models running alongside AI models so that we are drawing on their combined strengths to enable hyper-localised accurate forecasts, delivered fast, when you need them," says Professor Kirstine Dale, chief AI officer at the Met Office. Machine-learning models haven't been around for very long, but with their speed, computer efficiency and rapid rate of development, they show great potential.
CTV News
13 hours ago
- Climate
- CTV News
Rain in the northeast for the foreseeable future
Rain in the northeast for the foreseeable future With heavy rain on the way to the northeast, Rick Wyman has all the weather forecast details you need for the next seven days.
Yahoo
14 hours ago
- Climate
- Yahoo
It's going to be a hot weekend in the Appleton area. Here's how hot
After a chance of rain and thunderstorms the night of Thursday, June 19 and throughout the day Friday, June 20, it's going to be a hot weekend in the Appleton area. High temperatures are expected in the mid-90s Saturday, June 21 and Sunday, June 22, and in the low-90s Monday, June 23, according to the National Weather Service in Green Bay. The heat index — what the temperature feels like to the human body when relative humidity is combined with the air temperature — will be between 95 and 105 degrees June 21 and June 22, the NWS said. "Further complicating things are the overnight temperatures, which are unlikely to drop out of the 70s overnight Saturday or Sunday," the NWS said, "which makes for no relief from the heat overnight and may pose a concern for those planning to sleep outdoors such as in tents." The heat will stick around through June 23, along with a 50% chance of rain, before cooling off into the upper 70s June 24. There's a chance of an isolated severe storm through 10 p.m. June 19 and thunderstorms will be possible at times June 20 through the next morning. There's a 50 percent chance of rain, mainly before 1 p.m., with a high temperature near 80. "The greatest risk of strong or severe storms will be overnight Friday night into Saturday morning as a thunderstorm complex is expected move across the area," the NWS said. This article originally appeared on Appleton Post-Crescent: Appleton area weather forecast calls for a scorching hot weekend
CTV News
15 hours ago
- Climate
- CTV News
Colleen Bready's forecast: Tornadoes possible as thunderstorms brew
Colleen Bready has your current conditions and updated weather forecast for June 19, 2025. Colleen Bready has your current conditions and updated weather forecast for June 19, 2025. After severe thunderstorms moved through southwestern Manitoba Wednesday, more are expected to develop in the region Thursday that could produce tornadoes. Environment and Climate Change Canada (ECCC) has issued tornado watch Thursday for all areas within the Virden, Minnedosa and Dauphin regions. ECCC said a low pressure system will trigger severe thunderstorms in southeastern Saskatchewan Thursday afternoon that will move into southwestern Manitoba by early evening. The weather agency said conditions are favourable for these severe thunderstorms to produce tornadoes. Hail up to six centimetres in size, wind gusts up to 100 km/h and heavy rain are also likely. Expand Autoplay 1 of 49 Sunset Sunset over Northshore Bunnville, Sagkeeng First Nation (Photo by Brittany Bunn) Baby loon Baby loon. A couple hrs old! (Photo by Bruce Janzen) Dandelion Dandelion (Photo by Sheryl Twardoski) Mom and dad stand guard Mom and dad stand guard (Photo by Debbie Wowchuk) Garson, Manitoba Garson, Manitoba (Photo by Tom Kostyk) Rainbow over Steinbach Rainbow over Steinbach (Photo by Christopher Bleasdale) Fathers' Day sunset Fathers' Day sunset on East of Elm Creek (Photo by Marion Stangl) Can you see the face? Can you see the face? (Photo by Audrey Seip) Beauty of a rainbow Beauty of a rainbow (Photo by Christine Pedersen) Fort Garry Bad hair day out in our yard in Fort Garry (Photo by Brent Prusak) Oak Lake, MB Western Grebe couple (Photo by Vladimir McRae) Whyte Ridge Park Barely enjoying the weather in Whyte Ridge Park. (Photo by Martha Heinrichs) The Pas, MB Two swans and a duck swimming under a rainbow. (Photo by Halle Olson) Snowy Owl Snowy Owl finding breakfast at the zoo (Photo by Neil Longmuir) Northern lights Northern lights put on a show over Riverton, Manitoba (Photo by Vince Pahkala) Bee in the garden Bee in the garden (Photo by Debbie Wowchuk) Great Crested Flycatcher Great Crested Flycatcher belting out his mating call in St. Vital. (Photo by Wade Munro) June Strawberry Moon June Strawberry Moon (Photo by Hans Epp) Lady Slippers Beautiful yellow Lady Slippers (Photo by Lorette Dheilly) Big Bug's Bunny Big Bug's bunny (Photo by Beverly McLean) Elm Creek sky Elm Creek sky (Photo by Natalie Stangl) Mom and her ducklings Mom and her ducklings (Photo by Debbie Wowchuk) Lester beach Cold and incredibly windy in Lester beach (Photo by Andrew Ashett) Transcona trail Transcona trail (Photo by Jennifer Zacharias) Hatchlings Dove hatchlings. (Photo by Emmin Hosein) Sperling MB Approaching storm in Sperling MB (Photo by Ken Russell) Big Saturday Storm Big Saturday storm energizing seconds before huge downpour over Clearwater Bay. (Photo by Geoff Hicks) Manitoba Karting Track Manitoba Karting track (Photo by Monica Brooks) Gladstone Gladstone, Manitoba (Photo by Ray Baloun) Riding Mountain National Park Smoky the bear (Photo by Vladimir McRae) Brandon MB Smokey sunset at Errol Black Park (Photo by Giselle Fillion) Steinbach MB This kit was very curious but cautious (Photo by Kevin Friesen) Betula Lake Turtle off to lay her eggs at Betula Lake (Photo by Chris Jonsson) Red River Dragon boat racing along the Red River (Photo by Patricia McGhie) Blue Heron Blue heron at Hillside Beach, MB/ (Photo by Seth Franklin) Wildfire haze Wildfire haze at Snowlake area (Photo by Kevin Shpak) Pelicans and Smoke Pelicans and smoke (Photo by Doug Lauvstad) Old Pinawa Dam Old Pinawa Dam (Photo by Jennifer Field) Sunset Sunset over Mitchell (Photo by Martha Loeppky) After the light rain After the light rain in Beausejour (Photo by Ed Pauls) Over looking the Red River Henderson Highway over looking the Red River (Photo by Betty Clark) Trumpeter Swans Flocks of swans have been spotted on the Winnipeg River. Unusual and most likely fleeing the fires. (Photo by Jen Smithson) Very Curious Very curious but cautious (Photo by Kevin Friesen) Beautiful Heron Beautiful heron at Winnipeg Beach (Photo by Annette Courcelles) The Saskatchewan river The Saskatchewan river (Photo by Mary Ann Bradley) Unique cloud formation Unique cloud formation over South of McCreary (Photo by Gail James) Mallards & Geese The pair of Mallards seem to be impressed with the parenting skills of the geese. (Photo by Don McLeod) Northern Lights Northern lights at Durban, Mb. (Photo by Ryan McCullough) Newborn Fawn Newborn fawn (Photo by Roland Huemmer) The likelihood of showers or thunderstorms is lower in the southeast, but still certainly possible, particularly late Thursday evening and overnight, including in Winnipeg. Dry conditions continue in the north Thursday, including in wildfire-affected areas. Sunshine or a mix of sun and clouds, light winds, and highs in the upper-teens or low-twenties are all forecast for the afternoon. Air quality has improved enough Thursday that ECCC has issued no related alerts in Manitoba or northwestern Ontario, but that could change. The weather agency said smoke plumes from wildfires near Island Lake on the Ontario side, coupled with smoke from renewed Nopiming Provincial Park fires will spread south-southwest back into Manitoba before moving north Thursday. That could diminish air quality in the Interlake and east of Lake Winnipeg.
CTV News
18 hours ago
- Climate
- CTV News
Portions of southern Alberta could see up to 200 millimetres of rain this weekend
Weather statement issued because of intense rain. Jodi Hughes has a look at the five-day forecast from the Sky Watch Weather Centre.
