[[link removed]]

GOOGLE A.I. AGENT ACES 15-DAY WEATHER FORECASTS  
[[link removed]]


 

William J. Broad
December 4, 2024
New York Times
[[link removed]]


*
[[link removed]]
*
[[link removed]]
*
*
[[link removed]]

_ GenCast, from the company’s DeepMind division, outperformed the
world’s best predictions of deadly storms as well as everyday
weather. _

A satellite image of a bomb cyclone over the North American Pacific
Coast last month, CIRA/NOAA, via Reuters

 

In the 1960s, weather scientists found that the chaotic nature of
Earth’s atmosphere would put a limit on how far into the future
their forecasts might peer. Two weeks seemed to be the limit
[[link removed]].
Still, by the early 2000s, the great difficulty of the undertaking
kept reliable forecasts restricted to about a week
[[link removed]].

Now, a new artificial intelligence tool from DeepMind, a Google
company in London that develops A.I. applications, has smashed through
the old barriers and achieved what its makers call unmatched skill and
speed in devising 15-day weather forecasts. They report
[[link removed]] in the journal
Nature on Wednesday that their new model can, among other things,
outperform the world’s best forecasts meant to track deadly storms
and save lives.

“It’s a big deal,” said Kerry Emanuel
[[link removed]], a professor emeritus of atmospheric
science at the Massachusetts Institute of Technology who was not
involved in the DeepMind research. “It’s an important step
forward.”

In 2019, Dr. Emanuel and six other experts, writing in the Journal of
the Atmospheric Sciences
[[link removed]],
argued that advancing the development of reliable forecasts to a
length of 15 days from 10 days would have “enormous socioeconomic
benefits” by helping the public avoid the worst effects of extreme
weather.

Ilan Price
[[link removed]],
the new paper’s lead author and a senior research scientist at
DeepMind, described the new A.I. agent, which the team calls GenCast,
as much faster than traditional methods. “And it’s more
accurate,” he added.

He and his colleagues found that GenCast ran circles around
DeepMind’s previous A.I. weather program
[[link removed]],
which debuted in late 2023
[[link removed]] with
reliable 10-day forecasts. Rémi Lam
[[link removed]], the lead scientist on that
project and one of a dozen co-authors on the new paper, described the
company’s weather team as having made surprisingly fast progress.

“I’m a little bit reluctant to say it, but it’s like we’ve
made decades worth of improvements in one year,” he said in an
interview. “We’re seeing really, really rapid progress.”

The world leader in atmospheric prediction is the European Center for
Medium-Range Weather Forecasts [[link removed]].
Comparative tests regularly show that its projections exceed all
others in accuracy.

DeepMind tested its new A.I. program against the center’s Ensemble
Prediction System
[[link removed]] —
a service that 35 nations
[[link removed]] rely on to
produce their own weather forecasts. The team compared how the 15-day
forecasts of both systems performed in predicting a designated set of
1,320 global wind speeds, temperatures and other atmospheric features.

The Nature report said the new agent outdid the center’s forecasts
97.2 percent of time. The A.I. achievement, the authors wrote
[[link removed]], “helps open
the next chapter in operational weather forecasting.”

Matthew Chantry
[[link removed]],
an A.I. specialist at the European Center for Medium-Range Weather
Forecasts, said his agency was already adopting some of its features.

“That’s how highly we think of it,” he said. Machine learning in
general, Dr. Chantry added, was accelerating human bids to outmaneuver
some of nature’s deadliest threats.

DeepMind’s weather advance comes two months after other A.I.
researchers in the company shared the Nobel Prize
[[link removed]] for
chemistry. The scientific news forms a bright counterpoint to public
fears
[[link removed]] of
A.I. stealing jobs and driving humans to the edge of obsolescence.

The natural chaos in Earth’s atmosphere means that all weather
forecasts, including the two-week variety, grow less reliable as they
peer further into the future. Even so, AccuWeather offers
[[link removed]] 90-day forecasts. And
the Old Farmer’s Almanac says it can gaze
[[link removed]] ahead 60 days.

 

DeepMind backs its 15-day declaration with pages of evidence laid out
in one of the world’s leading science journals, Nature. So too,
Google posted an online blog
[[link removed]] that
details the A.I. advance.

The new GenCast agent takes a radically different approach from
mainstream forecasting, which uses room-size supercomputers that turn
millions of global observations and calculations into predictions.
Instead, the DeepMind agent runs on smaller machines and studies the
atmospheric patterns of the past to learn the subtle dynamics that
result in the planet’s weather.

The DeepMind team trained GenCast on a massive archive of weather
data
[[link removed]] curated
by the European center. The training period went from 1979 to 2018, or
40 years. The team then tested how well the agent could predict
2019’s weather.

Such training empowers all types of generative A.I. — the kind
that’s creative. Mimicking how humans learn, it spots patterns
[[link removed]] in
mountains of data and then makes new, original material that has
similar characteristics.

Dr. Lam of DeepMind noted that GenCast’s generative skills were
rooted in factual data gathered from nature rather than the internet,
notorious for its confusing mix of facts, biases and fallacies. “We
have a ground truth,” he said of its dependence on natural
phenomena. “We have a reality check.”

 

The new agent’s forecasts are probabilistic — like those on the
weather apps of smartphones. For instance, GenCast can give a range of
percentages for the likelihood of rain in a specific region on a given
day.

In contrast, its DeepMind predecessor, GraphCast
[[link removed]],
offers a single forecast for a particular time and location. Known as
deterministic, its method is essentially a best guess that gives no
indication of the prediction’s uncertainty.

Probabilistic forecasts are considered more nuanced
[[link removed]] and
sophisticated than the deterministic kind, and are more difficult to
create. Typically, a GenCast forecast draws from a set of 50 or more
predictions that produce its range of probabilities.

Despite all the effort that goes into those calculations, Dr. Price of
DeepMind said, the new agent can generate a 15-day forecast in minutes
compared with hours for a supercomputer. That can make its projections
much timelier — an advantage in tracking fast-moving storms.

GenCast, the team says, can predict with great accuracy the paths of
hurricanes, which annually can take thousands of lives and rack up
hundreds of billions of dollars in property damage. The Nature paper
said comparative testing showed that its hurricane track predictions
consistently outdid those of the European center.

 

Dr. Emanuel of M.I.T. said the DeepMind team failed to mention that
its new agent provides little information about hurricane intensity.

Dr. Price, the paper’s lead author, concurred. He said the problem
lay in training data limitations on hurricane wind speed. The weather
team, he added, was confident it could devise a solution.

GenCast will most likely complement current methods rather than
replace them, Dr. Emanuel argued. Each type, he said, has its own
strengths and weaknesses in predicting the riot of variable phenomena
that constitute the weather.

“The status quo isn’t going to disappear,” Dr. Emanuel said.
“Perhaps the two of them working together will prove to be the best
way forward.”

For its part, the DeepMind team acknowledged its heavy reliance on the
conventional world of weather readings — noting, for instance, how
its A.I. training data comes from the giant European weather archive.
Its computations also start with a snapshot of the world’s current
weather, what the team calls initial conditions.

 

The team hopes that other weather experts will test its new
technology. Dr. Price said that the DeepMind team would share online
[[link removed]] its A.I. agent and
underlying computer code.

He added that GenCast’s weather predictions would soon be posted
publicly on Google’s Earth Engine
[[link removed]] and Big Query
[[link removed]], giving scientists access to the
new forecasts.

“We’re excited for the community to use and build on our
research,” Dr. Price said.

Dr. Chantry of the European center said Google and DeepMind might have
hidden their A.I. advance behind a wall of corporate secrecy, using it
“to make a better weather forecast for their own apps and telling no
one how they did it.”

Instead, he added, the emerging field has embraced a public openness
that’s helping “lots and lots of people engage in this
revolution.”

_William J. Broad [[link removed]] has
reported on science at The Times since 1983. He is based in New
York. More about William J. Broad
[[link removed]]_

_Get the best of the New York Times
[[link removed]] in your Inbox with a free
newsletter. Gain unlimited access to all of The Times with a digital
subscription [[link removed]]._

* artificial intelligence
[[link removed]]
* Deepmind
[[link removed]]
* Science
[[link removed]]

*
[[link removed]]
*
[[link removed]]
*
*
[[link removed]]

 

 

 

INTERPRET THE WORLD AND CHANGE IT

 

 

Submit via web
[[link removed]]

Submit via email
Frequently asked questions
[[link removed]]
Manage subscription
[[link removed]]
Visit xxxxxx.org
[[link removed]]

Twitter [[link removed]]

Facebook [[link removed]]

 




[link removed]

To unsubscribe, click the following link:
[link removed]