Cloud Hosting

It said Hurricane Lee would make landfall in Nova Scotia three days sooner than traditional methods predicted.

This year the Earth has been hit by a record number of unpredictable extreme weather events made worse by climate change. Predicting them faster and with greater accuracy could enable us to prepare better for natural disasters and help save lives. A new AI model from Google DeepMind could make that easier.

In research published in Science today, Google DeepMinds model, GraphCast, was able to predict weather conditions up to 10 days in advance, more accurately and much faster than the current gold standard. GraphCast outperformed the model from the European Centre for Medium-Range Weather Forecasts (ECMWF) in more than 90% of over 1,300 test areas. And on predictions for Earths tropospherethe lowest part of the atmosphere, where most weather happensGraphCast outperformed the ECMWFs model on more than 99% of weather variables, such as rain and air temperature

Crucially, GraphCast can also offer meteorologists accurate warnings, much earlier than standard models, of conditions such as extreme temperatures and the paths of cyclones. In September, GraphCast accurately predicted that Hurricane Lee would make landfall in Nova Scotia nine days in advance, says Rmi Lam, a staff research scientist at Google DeepMind.Traditional weather forecasting models pinpointed the hurricane to Nova Scotia only six days in advance.

Dont settle for half the story.Get paywall-free access to technology news for the here and now.

Weather prediction is one of the most challenging problems that humanity has been working on for a long, long time. And if you look at what has happened in the last few years with climate change, this is an incredibly important problem, says Pushmeet Kohli, the vice president of research at Google DeepMind.

Traditionally, meteorologists use massive computer simulations to make weather predictions. They are very energy intensive and time consuming to run, because the simulations take into account many physics-based equations and different weather variables such as temperature, precipitation, pressure, wind, humidity, and cloudiness, one by one.

GraphCast uses machine learning to do these calculations in under a minute. Instead of using the physics-based equations, it bases its predictions on four decades of historical weather data. GraphCast uses graph neural networks, which map Earths surface into more than a million grid points. At each grid point, the model predicts the temperature, wind speed and direction, and mean sea-level pressure, as well as other conditions like humidity. The neural network is then able to find patterns and draw conclusions about what will happen next for each of these data points.

For the past year, weather forecasting has been going through a revolution as models such as GraphCast, Huaweis Pangu-Weather and Nvidias FourcastNet have made meteorologists rethink the role AI can play in weather forecasting. GraphCast improves on the performance of other competing models, such as Pangu-Weather, and is able to predict more weather variables, says Lam.The ECMWF is already using it.

When Google DeepMind first debuted GraphCast last December, it felt like Christmas, says Peter Dueben, head of Earth system modeling at ECMWF, who was not involved in the research.

It showed that these models are so good that we cannot avoid them anymore, he says.

GraphCast is a reckoning moment for weather prediction because it shows that predictions can be made using historical data, says Aditya Grover, an assistant professor of computer science at UCLA, who developed ClimaX, a foundation model that allows researchers to do different tasks relating to modeling the Earths weather and climate.

DeepMinds model is great work and extremely exciting, says Oliver Fuhrer, the head of the numerical prediction department at MeteoSwiss, the Swiss Federal Office of Meteorology and Climatology. Fuhrer says that other weather agencies, such as the ECMWF and the Swedish Meteorological and Hydrological Institute, have also used the graph neural network architecture proposed by Google DeepMind to build their own models.

But GraphCast is not perfect. It still lags behind conventional weather forecasting models in some areas, such as precipitation, Dueben says. Meteorologists will still have to use conventional models alongside machine-learning models to offer better predictions.

Google DeepMind is also making GraphCast open source. This is a good development, says UCLAs Grover.

With climate change on the rise, its very important that big organizations, which have had the luxury of so much compute, also think about giving back [to the scientific community], he says.

Continued here:
Google DeepMinds weather AI can forecast extreme weather faster and more accurately - MIT Technology Review

A new AI model from Google DeepMind is the worlds most accurate 10-day global weather forecasting system, according to the London-based lab.

Named GraphCast, the model promises medium-range weather forecasts of unprecedented accuracy. In a study published today, GraphCast was shown to be more precise and faster than the industry gold standard for weather simulation, the High-Resolution Forecast (HRES).

The system also predicted extreme weather further into the future than was previously possible.

These insights were analysed by the European Centre for Medium-Range Weather Forecasts (ECMWF), an intergovernmental organisation that produces the HRES.

A live version of GraphCast was deployed on the ECMWF website. In September, the system accurately predicted around nine days in advance that Hurricane Lee would make landfall in Nova Scotia.

In contrast, traditional forecasting methods only spotlighted Nova Scotia about six days beforehand. They also provided less consistent predictions of the time and location of landfall.

Intriguingly, GraphCast can identify dangerous weather events without being trained to find them. After integrating a simple cyclone tracker, the model predicted cyclone movements more accurately than the HRES method.

Such data could save lives and livelihoods. As the climate becomes more extreme and unpredictable, fast and accurate forecasts will provide increasingly vital insights for disaster planning.

Matthew Chantry, a machine learning coordinator at the ECMWF, believes his industry has reached an inflection point.

Theres probably more work to be done to create reliable operational products, but this is likely the beginning of a revolution, Chantry said at a press briefing.

Meteorological organisations, he added, had previously expected AI to be most useful when merged with physics. But recent breakthroughs show that machine learning can also directly forecast the weather.

Conventional weather forecasts are based on intricate physics equations. These are then adapted into algorithms that run on supercomputers.

The process can be painstaking. It also requires specialist knowledge and vast computing resources.

GraphCast harnesses a different technique. The model combines machine learning with Graph Neural Networks (GNNs), an architecture thats adept at processing spatially structured data.

To learn the causes and effects that determine weather changes, the system was trained on decades of weather information.

Traditional approaches are also incorporated. The ECMWF supplied GraphCast with training data from around 40 years of weather reanalysis, which encompassed monitoring from satellites, radars and weather stations.

When there are gaps in the observations, physics-based prediction methods fill them in. The result is a detailed history of global weather. GraphCast uses these lessons from the past to predict the future.

GraphCast makes predictions at a spatial resolution of 0.25-degrees latitude/longitude.

To put that into perspective, imagine the Earth divided into a million grid points. At each point, the model predicts five Earth-surface variable and six atmospheric variables. Together, they cover the planets entire atmosphere in 3D over 37 levels.

The variables encompass temperature, wind, humidity, precipitation, and sea-level pressure. They also incorporate geopotential the gravitational potential energy of a unit mass, at a particular location, relative to mean sea level.

In tests, the results were impressive. GraphCast significantly outperformed the most accurate operational deterministic systems on 90% of 1,380 test targets.

The disparity was even starker in the troposphere the lowest layer of Earths atmosphere and the location of most weather phenomena. In this region, GraphCast outperformed HRES on 99.7% of the test variables for future weather.

GraphCast is also highly efficient. A 10-day forecast takes under a minute to complete on a single Google TPU v4 machine.

A conventional approach, by comparison, can take hours of computation in a supercomputer with hundreds of machines.

Despite the promising early results, GraphCast could still benefit from further refinement. In the cyclone predictions, for instance, the model proved accurate at tracking movements, but less effective at measuring intensity.

Gentry is keen to see how much this can improve.

At the moment, thats an area where GraphCast and machine learning models still lag a little bit behind physical models Im hopeful that this can be an area for further improvement, but this shows that its still a nascent technology, he said.

Those improvements could now come from anywhere, because DeepMind has open-sourced the model code. Global organisations and individuals alike can now experiment with GraphCast and add their own improvements.

The potential applications are, ironically, unpredictable. The forecasts could, for instance, inform renewable energy production and air traffic routing. But they could also be applied to tasks that havent even been imagined.

Theres a lot of downstream use cases for weather forecasts, said Peter Battaglia, Google DeepMinds research director. And were not aware of all of those.

See the original post:
DeepMind says new AI is world's most accurate 10-day weather forecaster - TNW

Can AI tell you if you will need an umbrella?

SEBASTIEN BOZON/AFP via Getty Images

AI can predict the weather 10 days ahead more accurately than current state-of-the-art simulations, says AI firm Google DeepMind but meteorologists have warned against abandoning weather models based in real physical principles and just relying on patterns in data, while pointing out shortcomings in the AI approach.

Existing weather forecasts are based on mathematical models, which use physics and powerful supercomputers to deterministically predict what will happen in the future. These models have slowly become more accurate by adding finer detail, which in turn requires more computation and therefore ever more powerful computers and higher energy demands.

Rmi Lam at Google DeepMind and his colleagues have taken a different approach. Their GraphCast AI model is trained on four decades of historical weather data from satellites, radar and ground measurements, identifying patterns that not even Google DeepMind understands. Like many machine-learning AI models, its not very easy to interpret how the model works, says Lam.

To make a forecast, it uses real meteorological readings, taken from more than a million points around the planet at two given moments in time six hours apart, and predicts the weather six hours ahead. Those predictions can then be used as the inputs for another round, forecasting a further six hours into the future.

Researchers at DeepMind ran this process with data from the European Centre for Medium-Range Weather Forecasts (ECMWF) to create a 10-day forecast. They say it beat the ECMWFs gold-standard high-resolution forecast (HRES) by giving more accurate predictions on more than 90 per cent of tested data points. At some altitudes, this accuracy rose as high as 99.7 per cent.

Matthew Chantry at the ECMWF, who worked with Google DeepMind, says his organisation had previously seen AI as a tool to supplement existing mathematical models, but that in the past 18 months it has come to be regarded as something that could actually provide forecasts on its own.

We at the ECMWF view this as a hugely exciting technology to lower the energy costs of making forecasts, but also potentially improve them. Theres probably more work to be done to create reliable operational products, but this is likely the beginning of a revolution this is our assessment in how weather forecasts are created, he says. Google DeepMind says that making 10-day forecasts with GraphCast takes less than a minute on a high-end PC, while HRES can take hours of supercomputer time.

But some meteorologists have expressed caution about turning weather forecasting over to AI.Ian Renfrew at the University of East Anglia, UK, says GraphCast currently lacks the ability to marshal data for its own starting state, a process known as data assimilation. In traditional forecasts, this data is carefully placed into the simulation after thorough checks against physics and chemistry calculations to ensure accuracy and consistency. Currently, GraphCast needs to use starting states prepared in the same way by the ECMWFs own tools.

Google is not going to be running weather forecasts anytime soon, because they cannot do the data assimilation, says Renfrew. And the data assimilation is typically half to two-thirds of the computing time in these forecasting systems.

He says that he would also have concerns about ditching deterministic models based on chemistry and physics entirely and relying on AI output alone.

You can have the best forecast model in the world, but if the public dont trust you, and dont act, then whats the point? If you set out an order to evacuate 30 miles of coastline in Florida, and then nothing happens, then youve blown decades of trust that has been built up, he says. The advantage of a deterministic model is you can interrogate it and if you do get bad forecasts, you can interrogate why theyre bad forecasts and try to target those aspects for improvement.

Topics:

Originally posted here:
DeepMind AI can beat the best weather forecasts - but there is a catch - New Scientist

Have you ever changed your mind about something a song, a food, an activity, a person that you were sure you loved or hated?

Do you tend to be open-minded and flexible about your likes and dislikes? Or are you generally set in your tastes? Are you willing to give something or somebody a second chance? How about admitting you were colossally wrong in your initial judgment?

In I Thought I Hated Pop Music. Dancing Queen Changed My Mind., Jeff Tweedy, the singer and guitarist of the band Wilco, writes about his newfound love for Abba, the Swedish supergroup from the 1970s:

Its important to admit when youre wrong. And though I once bristled at the notion that there could ever be such a thing as a wrong musical opinion, I have since come to accept that there is, in fact, such a thing. I know because I had one: I was colossally wrong about the song Dancing Queen by Abba.

Im happy I can admit it, maybe even a touch proud of myself for not digging in my heels and hating this song for even a second longer than I had to (unlike some friends I know who are still holding out). To me, looking back, the weirdest part is that I ever felt I had to hate something so clearly irresistible.

In a way, I blame the time and place where I grew up. The mid-1970s, when Dancing Queen came out, was a time when there were very strict lines being drawn between cultural camps. As a kid who liked punk rock, this tune was situated deep in enemy territory, at the intersection of pop and disco.

I am, perhaps, a bit skeptical by nature, but scanning the horizons of my memory seeing what I saw around me from about the mid-70s to the late 80s Id say there was something else going on, too. I was just a kid. And in that particular nanosecond of geological time, kids hated stuff.

In particular, my group of friends and I despised a lot of music and, by extension, the morons who would dare admit that they liked something we hated. Music. Can you believe it? It seems hard to imagine now that a group of preteens could be capable of conjuring vein-bulging fury at the mere mention of the band Styx. But we were. And we did.

Why did we feel this way? Mostly, I think, because hating certain music gave us a way of defining ourselves. Our identities were indistinct, and drawing a line in the sand between what we liked and what we hated made our young hearts feel whole.

Mr. Tweedy writes about the moment many years later when his thinking completely changed. He was standing in a grocery store aisle, staring at the overhead speaker, just reeling at this familiar melody and how exuberantly sad it was. Having the time of your life! He explains: It was a real come to Jesus moment. A come to Agnetha, Bjrn, Benny and Anni-Frid moment.

He continues:

Before that day, I, along with many others, had denied myself an undeniable joy. Countless fantastic records and deep grooves were dismissed and derided out of ignorance. But of course, this song and this music was always going to win eventually. Because its just too special to ignore forever.

To this day, whenever I think I dislike a piece of music, I think about Dancing Queen and am humbled.

That song taught me that I cant ever completely trust my negative reactions. I was burned so badly by this one song being withheld from my heart for so long. I try to never listen to music now without first examining my own mind and politely asking whatever blind spots Im afflicted with to move aside long enough for my gut to be the judge. And even then, if I dont like something, I make a mental note to try it again in 10 years.

Students, read the entire article and then tell us:

What have you changed your mind about? Tell us about something that you once liked, loved, hated or dismissed but that you later dramatically revised your judgment about. Was it hard to admit to yourself or to others that you were wrong?

How have your tastes changed or grown over time? Do you tend to be open-minded and flexible about your likes and dislikes? Or, once you love or hate something, do you never waiver?

Mr. Tweedy writes that in the 1970s, when Dancing Queen came out, there were very strict lines being drawn between cultural camps and that, as a kid who liked punk rock, the song was situated deep in enemy territory. Does that resonate with your own experiences? Do you ever feel as if you arent allowed to like or dislike certain things because of your own cultural identification?

Mr. Tweedy ends his essay, So if you take anything away from this, I hope it will be this recommendation: Spend some time looking for a song (or a book or a film or a painting or a person) you might have unfairly maligned. Do you agree with his advice? Are we all too quick to pass judgment on things, and might that make us miss out on great experiences and joys? In the future, do you think you will try to give your dislikes and hates another chance?

Students 13 and older in the United States and Britain, and 16 and older elsewhere, are invited to comment. All comments are moderated by the Learning Network staff, but please keep in mind that once your comment is accepted, it will be made public and may appear in print.

Find more Student Opinion questions here. Teachers, check out this guide to learn how you can incorporate these prompts into your classroom.

Read more:
What Have You Changed Your Mind About? - The New York Times