Latest news with #NOAA
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.
Yahoo
14 hours ago
- Climate
- Yahoo
Strong storms with hail, heavy rain Thursday morning
MEMPHIS, Tenn. — Showers and thunderstorms will become likely late this evening and into the overnight hours. A few of those storms may become severe, with damaging winds the primary concern, followed by large hail and heavy rainfall. The majority of the Mid-South is under a Slight Risk (Level 2/5) for severe weather. By daybreak, storms will be moving southward and out of the Mid-South. Highs will climb to around 90 again Thursday afternoon, with a slight chance for a pop-up shower through the evening. STAY CONNECTED – We encourage you to always have multiple ways to receive weather information. Download the WREG weather app for the latest forecast details while you are on the go. Make sure your location is turned ON, so you can receive watch and warning information for your exact location at all times. A NOAA weather radio is a great investment as well. You can also download the new WREG+ app on your smart TV to stream live newscasts and weather coverage. Check the latest forecasts from WREG Weather Copyright 2025 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
India Today
15 hours ago
- Climate
- India Today
Aurora alert: Rare Borealis display predicted over US due to geomagnetic storm
The National Oceanic and Atmospheric Administration (NOAA) has predicted increased Northern Lights activity for Thursday night, forecasting a Kp index of 5 out of 9. This means the aurora borealis may intensify and become visible farther south than on NOAA's three-day space weather forecast, geomagnetic activity is expected to increase Thursday evening and continue into the early hours of Friday, with minor to moderate geomagnetic storms AURORA VISIBILITY LIKELY TO DECLINEWhile auroral activity peaks Thursday night, NOAA expects space weather to calm by Friday and Saturday. The Kp index will dip slightly, just above 3 on Friday then drop to 2 on Saturday, reducing the likelihood of widespread aurora sightings over the TO SEE THE LIGHTS? According to Forbes, a "view line" passes through several northern US states. Areas with a chance to see the aurora include parts of northern Washington, Idaho, Montana, North Dakota, Minnesota, Wisconsin, and Upper Michigan. Northern parts of New York, New Hampshire, Vermont, and Maine may also experience faint activity under perfect TO MAXIMISE YOUR VIEWING EXPERIENCE To boost your chances of seeing the aurora, NOAA recommends heading to high-altitude northern locations with minimal light best viewing window is between 10 p.m. and 2 a.m. local time, under clear for Capturing the Aurora on CameraPhotographers advise using a wide-angle lens with aperture f/4 or lower. The ISO and shutter speeds need to be adjusted according to the aurora's users should enable night mode, use a tripod, and turn off the flash to enhance image clarity.
Forbes
19 hours ago
- Climate
- Forbes
Northern Lights Alert: Some States Could See Aurora Borealis Thursday
The National Oceanic and Atmospheric Administration said Thursday some geomagnetic storms will likely disrupt Earth's magnetic field soon, which could make the northern lights visible in several states tonight. TK NOAA forecast a Kp index of five on a scale of nine for Thursday night, suggesting the northern lights will become brighter as they become more active while moving farther from the poles. Thursday's auroral forecast will likely increase through the night and into Friday morning, when some 'minor' or greater geomagnetic storms are expected, according to NOAA's three-day forecast. Calmer auroral activity is expected through Saturday night, with a maximum Kp index of just over three and two for Friday and Saturday, respectively, NOAA's projections suggest. The northern lights have the highest chance of being seen throughout Canada, with a minimal opportunity—marked by a 'view line'—forecast through northern Iowa and other northern states. A lesser chance is expected in northern Washington, northern Idaho, Montana, North Dakota, northern Minnesota, northern Wisconsin and Upper Michigan, with a near-zero chance forecast for parts of northern Wyoming, South Dakota, northern Iowa, northern New York, New Hampshire, Vermont and Maine. While Alaska is forecast with a high likelihood, the state won't be dark enough at the time. (See map below.) Thursday's view line. NOAA recommends traveling to the north and finding a high, north-facing vantage point away from light pollution. If in the right area in optimal weather conditions, the aurora borealis can be visible even with lower geomagnetic activity, including a Kp index of three or four, the agency said, noting the northern lights are best seen within at least two hours of 10 p.m. and 2 a.m. local time. Photography experts told National Geographic a wide-angle lens and an aperture or F-stop of four or lower are recommended, though other settings like ISO and shutter speed will likely need to be adjusted depending on the strength of the aurora borealis. With a smartphone, the experts suggest using a tripod to stabilize the image long enough to capture the northern lights displays. They also recommend disabling flash and enabling night mode. An increase in northern lights displays throughout the U.S. follows a peak in solar activity reached in October 2024, NOAA and NASA said. This peak features more solar flares and coronal mass ejections, which produce the northern lights as electrons from these events collide with oxygen and nitrogen in the Earth's atmosphere. Though the northern lights can be seen throughout the year, they are most visible between late September and March when nights are longer, experts said.
CNN
20 hours ago
- Climate
- CNN
Erick makes landfall as a Category 3 hurricane, the strongest to hit Mexico so early in the year
Hurricane Erick slammed into Mexico's Oaxaca state as a dangerous Category 3 storm Thursday morning, unleashing powerful winds at the coast while spreading heavy rain over the region. The hurricane made landfall about 20 miles east of Punta Maldonado, Mexico, just after 6 a.m. CDT Thursday, according to NOAA's National Hurricane Center. Winds of 125 mph were roaring around its center at landfall. The storm came ashore about 100 miles east of Acapulco, the city devastated by Hurricane Otis in October 2023. Erick is the first major hurricane – Category 3 or greater – on record to hit Mexico before July. The hurricane maxed out as a ferocious Category 4 storm with 145 mph winds just off the coast in the earliest hours of Thursday morning. It underwent extreme rapid intensification from Tuesday night into Wednesday night, strengthening from a tropical storm to a Category 4 hurricane in just 24 hours. Rapid intensification is becoming more frequent in a world warming due to fossil fuel pollution. Erick will deteriorate quickly as it tracks through Mexico's steep mountains Thursday and is should dissipate by early Friday. It was already a Category 1 hurricane a few hours after landfall. Despite that, it will drop a troubling amount of rain in a short period that could cause dangerous flooding. The East Pacific hurricane season has been very busy since it began in mid-May. Erick is already the fifth named storm of the season – storms are named when they reach at least tropical storm-strength – and the second hurricane. The basin doesn't typically have its second hurricane until mid-July, according to NOAA. The Atlantic hurricane season is also underway, but has yet to churn out its first named storm and there's little prospect for it in the next few days. President Claudia Sheinbaum said in a video message Wednesday night that all activities in the region in Erick's path were suspended and she urged people to stay in their homes or to move to shelters if they lived in low-lying areas, the Associated Press reported. Acapulco's port closed Tuesday evening. Guerrero state Gov. Evelyn Salgado said all movement in Acapulco and other beach communities was to be suspended at 8 p.m. Wednesday in a post on X, and schools across the state were to remain closed through Thursday. Salgado said 582 shelters were set to receive people who might evacuate their homes across Guerrero. Laura Velázquez, Mexico's national civil defense coordinator, said Erick was forecast to bring 'torrential' rains to Guerrero, Oaxaca and Chiapas states, according to the AP. The mountainous region along the southern coast is especially prone to mudslides with numerous rivers at risk of flooding. Nearly 16 inches of rain could fall through the end of the week in some portions of Guerrero's mountainous terrain, according to the NHC. This could trigger life-threatening flooding or mudslides. Up to 8 inches of rain is possible in the same timeframe for coastal areas of Oaxaca and Guerrero. Acapulco could record up to 6 inches of rain from Erick, but will not face the hurricane's most powerful winds. Tropical storm-force gusts up to 45 mph are possible in the area Thursday. In Acapulco on Wednesday, there was a strong presence of National Guard and police in the streets, but most visible were trucks from the national power company, the AP reported. Crews worked to clear drainage canals and brush. The memory of Hurricane Otis haunted some residents as they prepared for Erick. Otis underwent some of the most extreme rapid intensification on record and strengthened to a Category 5 hurricane just before landfall. Carlos Ozuna Romero, 51, lost his restaurant at the edge of an Acapulco beach when Otis slammed the resort with devastating winds, he told the AP. On Wednesday, he directed workers storing tables and chairs. 'Authorities' warnings fill us with fear and obviously make us remember everything we've already been through,' Ozuna Romero said in reference to Otis. CNN Meteorologist Monica Garrett contributed to this report.
