The machine-learning model takes less than a minute to predict future weather worldwide more precisely than other approaches.

That's saying something because the super-accurate and processing intensive ECMWF takes 12 hours per iteration. But then again, GraphCast was trained on the ECMWF predictions, among others.

The snag:

"In the meantime, problems with machine-learning approaches must be ironed out. Unlike NWP models, researchers cannot fully understand how AIs such as GraphCast work because the decision-making processes happen in AI’s ‘black box’, says Grover. “
This calls into question their reliability,” he says."

How could they possibly not understand how it works???

https://www.nature.com/articles/d41586-023-03552-y

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

On Wed, 22 Nov 2023 13:19:55 -0800 (PST), Fred Bloggs <bloggs.fredbloggs.fred@gmail.com> wrote:

The machine-learning model takes less than a minute to predict future weather worldwide more precisely than other approaches.

That's saying something because the super-accurate and processing intensive ECMWF takes 12 hours per iteration. But then again, GraphCast was trained on the ECMWF predictions, among others.

The snag:

"In the meantime, problems with machine-learning approaches must be ironed out. Unlike NWP models, researchers cannot fully understand how AIs such as GraphCast work because the decision-making processes happen in AI�s �black box�, says Grover. �This

calls into question their reliability,� he says."

How could they possibly not understand how it works???

https://www.nature.com/articles/d41586-023-03552-y

My wife is much better than any of the supercomputer models at
predicting if it will rain tomorrow.

Nothing artificial about her!

But no amount of intelligence can predict the future state of a wildly
chaotic system.

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

On Thursday, November 23, 2023 at 8:33:38 AM UTC+11, john larkin wrote:

On Wed, 22 Nov 2023 13:19:55 -0800 (PST), Fred Bloggs <bloggs.fred...@gmail.com> wrote:

The machine-learning model takes less than a minute to predict future weather worldwide more precisely than other approaches.

That's saying something because the super-accurate and processing intensive ECMWF takes 12 hours per iteration. But then again, GraphCast was trained on the ECMWF predictions, among others.

The snag:

"In the meantime, problems with machine-learning approaches must be ironed out. Unlike NWP models, researchers cannot fully understand how AIs such as GraphCast work because the decision-making processes happen in AI’s ‘black box’, says Grover. �

��This calls into question their reliability,” he says."

How could they possibly not understand how it works???

https://www.nature.com/articles/d41586-023-03552-y

My wife is much better than any of the supercomputer models at
predicting if it will rain tomorrow.

Nothing artificial about her!

But no amount of intelligence can predict the future state of a wildly chaotic system.

Not moment to moment. But climate change is predictable in terms of short term averages.

--
Bill Sloman, Sydney

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

XPost: free.spam

The idiot Anthony William Sloman <bill.sloman@ieee.org> persisting in being an Off-topic troll...

--
Anthony William Sloman <bill.sloman@ieee.org> wrote:

X-Received: by 2002:ac8:5988:0:b0:421:c757:a89a with SMTP id e8-20020ac85988000000b00421c757a89amr144725qte.4.1700711890012;
Wed, 22 Nov 2023 19:58:10 -0800 (PST)
X-Received: by 2002:a65:6459:0:b0:5bd:d3f7:5192 with SMTP id
s25-20020a656459000000b005bdd3f75192mr799784pgv.6.1700711889623; Wed, 22 Nov
2023 19:58:09 -0800 (PST)
Path: not-for-mail
Newsgroups: sci.electronics.design
Date: Wed, 22 Nov 2023 19:58:09 -0800 (PST)
In-Reply-To: <smsslip231e394c4u3pmnjjhpurt55mlpm@4ax.com>
Injection-Info: google-groups.googlegroups.com; posting-host=59.102.83.245; posting-account=SJ46pgoAAABuUDuHc5uDiXN30ATE-zi-
NNTP-Posting-Host: 59.102.83.245
References: <3644daac-c3a5-4dbb-a039-cfb94e78fde7n@googlegroups.com> <smsslip231e394c4u3pmnjjhpurt55mlpm@4ax.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <72aafb45-1148-49a4-b54f-28ea1b4fc3a7n@googlegroups.com>
Subject: =?UTF-8?Q?Re=3A_DeepMind_AI_accurately_forecasts_weather_=E2=80=94_on_?=
=?UTF-8?Q?a_desktop_computer?=
From: Anthony William Sloman <bill.sloman@ieee.org>
Injection-Date: Thu, 23 Nov 2023 03:58:10 +0000
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Received-Bytes: 2814

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)

XPost: free.spam

The arsehole john larkin <jl@650pot.com> persisting in being an Off-topic troll...

--
john larkin <jl@650pot.com> wrote:

Path: not-for-mail
NNTP-Posting-Date: Wed, 22 Nov 2023 21:33:21 +0000
From: john larkin <jl@650pot.com>
Newsgroups: sci.electronics.design
Subject: Re: DeepMind AI accurately forecasts weather — on a desktop computer
Date: Wed, 22 Nov 2023 13:33:21 -0800
Message-ID: <smsslip231e394c4u3pmnjjhpurt55mlpm@4ax.com>
References: <3644daac-c3a5-4dbb-a039-cfb94e78fde7n@googlegroups.com> User-Agent: ForteAgent/8.00.32.1272
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
Lines: 23
X-Trace: sv3-ZzgjpTrlmo+PHFQImFfSCscpjX72+OM1KKyeWQsWkXZoVW02El77d4tQEyig+kfumrUAK+7RVEbSUzK!RSKZ4XMz5Z0st0NJgxk0CK8aTVKgmCn9i1NniUqDreMwDBRg+Lv2YoKdA9vwxV6mcZp+MwGfVwsk!40XxQg==
X-Complaints-To: www.supernews.com/docs/abuse.html
X-DMCA-Complaints-To: www.supernews.com/docs/dmca.html
X-Abuse-and-DMCA-Info: Please be sure to forward a copy of ALL headers X-Abuse-and-DMCA-Info: Otherwise we will be unable to process your complaint properly
X-Postfilter: 1.3.40
Bytes: 2169
X-Received-Bytes: 2307

--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)