The Times Australia
The Times World News

.
Men's Weekly

.

AI weather models can now beat the best traditional forecasts

  • Written by Vassili Kitsios, Senior Research Scientist, Climate Forecasting, CSIRO

A new machine-learning weather prediction model called GenCast can outperform the best traditional forecasting systems in at least some situations, according to a paper by Google DeepMind researchers[1] published today in Nature.

Using a diffusion model approach similar to artificial intelligence (AI) image generators, the system generates multiple forecasts to capture the complex behaviour of the atmosphere. It does so with a fraction of the time and computing resources required for traditional approaches.

How weather forecasts work

The weather predictions we use in practice are produced by running multiple numerical simulations of the atmosphere.

Each simulation starts from a slightly different estimate of the current weather. This is because we don’t know exactly what the weather is at this instant everywhere in the world. To know that, we would need sensor measurements everywhere.

These numerical simulations use a model of the world’s atmosphere divided into a grid of three-dimensional blocks. By solving equations describing the fundamental physical laws of nature, the simulations predict what will happen in the atmosphere.

Known as general circulation models, these simulations need a lot of computing power. They are usually run at high-performance supercomputing facilities.

Machine-learning the weather

The past few years have seen an explosion in efforts to produce weather prediction models using machine learning[2]. Typically, these approaches don’t incorporate our knowledge of the laws of nature the way general circulation models do.

Most of these models use some form of neural network to learn patterns in historical data and produce a single future forecast. However, this approach produces predictions that lose detail as they progress into the future, gradually becoming “smoother”. This smoothness is not what we see in real weather systems.

Researchers at Google’s DeepMind AI research lab have just published a paper in Nature[3] describing their latest machine-learning model, GenCast.

GenCast mitigates this smoothing effect by generating an ensemble of multiple forecasts. Each individual forecast is less smooth, and better resembles the complexity observed in nature.

The best estimate of the actual future then comes from averaging the different forecasts. The size of the differences between the individual forecasts indicates how much uncertainty there is.

According to the GenCast paper, this probabilistic approach creates more accurate forecasts than the best numerical weather prediction system in the world – the one at the European Centre for Medium-Range Weather Forecasts[4].

Generative AI – for weather

GenCast is trained on what is called reanalysis data from the years 1979 to 2018. This data is produced by the kind of general circulation models we talked about earlier, which are additionally corrected to resemble actual historical weather observations to produce a more consistent picture of the world’s weather.

The GenCast model makes predictions of several variables such as temperature, pressure, humidity and wind speed at the surface and at 13 different heights, on a grid that divides the world up into 0.25-degree regions of latitude and longitude.

GenCast is what is called a “diffusion model”, similar to AI image generators. However, instead of taking text and producing an image, it takes the current state of the atmosphere and produces an estimate of what it will be like in 12 hours.

This works by first setting the values of the atmospheric variables 12 hours into the future as random noise. GenCast then uses a neural network to find structures in the noise that are compatible with the current and previous weather variables. An ensemble of multiple forecasts can be generated by starting with different random noise.

Forecasts are run out to 15 days, taking 8 minutes on a single processor called a tensor processor unit (TPU). This is significantly faster than a general circulation model. The training of the model took five days using 32 TPUs.

Machine-learning forecasts could become more widespread in the coming years as they become more efficient and reliable.

However, classical numerical weather prediction and reanalysed data will still be required. Not only are they needed to provide the initial conditions for the machine learning weather forecasts, they also produce the input data to continually fine-tune the machine learning models.

What about the climate?

Current machine learning weather forecasting systems are not appropriate for climate projections, for three reasons.

Firstly, to make weather predictions weeks into the future, you can assume that the ocean, land and sea ice won’t change. This is not the case for climate predictions over multiple decades.

Secondly, weather prediction is highly dependent on the details of the current weather. However, climate projections are concerned with the statistics of the climate decades into the future, for which today’s weather is irrelevant. Future carbon emissions are the greater determinant of the future state of the climate.

Thirdly, weather prediction is a “big data” problem. There are vast amounts of relevant observational data, which is what you need to train a complex machine learning model.

Climate projection is a “small data” problem, with relatively little available data. This is because the relevant physical phenomena (such as sea levels or climate drivers such as the El Niño–Southern Oscillation) evolve much more slowly than the weather.

There are ways to address these problems. One approach is to use our knowledge of physics to simplify our models[5], meaning they require less data for machine learning.

Another approach is to use physics-informed neural networks[6] to try to fit the data and also satisfy the laws of nature. A third is to use physics to set “ground rules”[7] for a system, then use machine learning to determine the specific model parameters.

Machine learning has a role to play in the future of both weather forecasting and climate projections. However, fundamental physics – fluid mechanics[8] and thermodynamics – will continue to play a crucial role.

Read more https://theconversation.com/ai-weather-models-can-now-beat-the-best-traditional-forecasts-245168

Times Magazine

Effective Commercial Pest Control Solutions for a Safer Workplace

Keeping a workplace clean, safe, and free from pests is essential for maintaining productivity, protecting employee health, and upholding a company's reputation. Pests pose health risks, can cause structural damage, and can lead to serious legal an...

The Science Behind Reverse Osmosis and Why It Matters

What is reverse osmosis? Reverse osmosis (RO) is a water purification process that removes contaminants by forcing water through a semi-permeable membrane. This membrane allows only water molecules to pass through while blocking impurities such as...

Foodbank Queensland celebrates local hero for National Volunteer Week

Stephen Carey is a bit bananas.   He splits his time between his insurance broker business, caring for his young family, and volunteering for Foodbank Queensland one day a week. He’s even run the Bridge to Brisbane in a banana suit to raise mon...

Senior of the Year Nominations Open

The Allan Labor Government is encouraging all Victorians to recognise the valuable contributions of older members of our community by nominating them for the 2025 Victorian Senior of the Year Awards.  Minister for Ageing Ingrid Stitt today annou...

CNC Machining Meets Stage Design - Black Swan State Theatre Company & Tommotek

When artistry meets precision engineering, incredible things happen. That’s exactly what unfolded when Tommotek worked alongside the Black Swan State Theatre Company on several of their innovative stage productions. With tight deadlines and intrica...

Uniden Baby Video Monitor Review

Uniden has released another award-winning product as part of their ‘Baby Watch’ series. The BW4501 Baby Monitor is an easy to use camera for keeping eyes and ears on your little one. The camera is easy to set up and can be mounted to the wall or a...

The Times Features

Running Across Australia: What Really Holds the Body Together?

How William Goodge’s 3,800km run reveals the connection between movement, mindset, and mental resilience As a business owner, I’ve come to realise that the biggest wins rarely com...

Telehealth is Transforming Healthcare Services in Australia

It has traditionally not been easy to access timely healthcare in Australia, particularly for people who live in remote areas. Many of them spend hours on the road just to see a...

Launchd Acquires Huume, Strengthening Creative Firepower Across Talent-Led Marketing

Launchd, a leader in talent, technology and brand partnerships, has announced its acquisition of influencer talent management agency Huume from IZEA. The move comes as the medi...

Vietnam's "Gold Coast" Emerges as Extraordinary Investment Frontier and Australian Inspired Way of Life

$2 Billion super-city in Vung Tau set to replicate Australia's Gold Coast success story A culturally metamorphic development aptly named "Gold Coast" is set to reshape Vietna...

Choosing the Wrong Agent Is the #1 Regret Among Aussie Property Sellers

Selling your home is often one of the largest financial transactions you’ll make, and for many Australians, it’s also one of the most emotional. A new survey of Australian home se...

Travel Insurance for Families: What Does it Cover and Why it’s Essential

Planning a family trip is exciting, but unexpected mishaps can turn your dream vacation into a stressful ordeal. That’s where travel insurance comes in—it’s your safety net when ...