HAPPY BIRTHDAY DEAN
Chat
-
pommystuart
- Posts: 1809
- Joined: Mon May 18, 2020 12:48 am
- Location: Cooranbong, NSW, Australia.
Happy Birthday Dean.
Hope you have a great day.
-
pommystuart
- Posts: 1809
- Joined: Mon May 18, 2020 12:48 am
- Location: Cooranbong, NSW, Australia.
FYI
Just came across this 2016 article mentioned in the New Scientist 13th July 2024 edition.
https://www.eenews.net/articles/on-kodi ... -99-8-out/
Neat idea about using the flywheel.
https://www.eenews.net/articles/on-kodi ... -99-8-out/
Neat idea about using the flywheel.
Re: Chat
Model mixes AI and physics to do global forecasts
Image of some of the atmospheric circulation seen during NeuralGCM runs. (credit: Google)
Right now, the world's best weather forecast model is a General Circulation Model, or GCM, put together by the European Center for Medium-Range Weather Forecasts.
A GCM is in part based on code that calculates the physics of various atmospheric processes that we understand well.
For a lot of the rest, GCMs rely on what's termed "parameterization," which attempts to use empirically determined relationships to approximate what's going on with processes where we don't fully understand the physics.
Lately, GCMs have faced some competition from machine-learning techniques, which train AI systems to recognize patterns in meteorological data and use those to predict the conditions that will result over the next few days.
Their forecasts, however, tend to get a bit vague after more than a few days and can't deal with the sort of long-term factors that need to be considered when GCMs are used to study climate change.
On Monday, a team from Google's AI group and the European Centre for Medium-Range Weather Forecasts are announcing NeuralGCM, a system that mixes physics-based atmospheric circulation with AI parameterization of other meteorological influences.
Neural GCM is computationally efficient and performs very well in weather forecast benchmarks.
Strikingly, it can also produce reasonable-looking output for runs that cover decades, potentially allowing it to address some climate-relevant questions.
While it can't handle a lot of what we use climate models for, there are some obvious routes for potential improvements.
Full article: https://arstechnica.com/?p=2038449
Image of some of the atmospheric circulation seen during NeuralGCM runs. (credit: Google)
Right now, the world's best weather forecast model is a General Circulation Model, or GCM, put together by the European Center for Medium-Range Weather Forecasts.
A GCM is in part based on code that calculates the physics of various atmospheric processes that we understand well.
For a lot of the rest, GCMs rely on what's termed "parameterization," which attempts to use empirically determined relationships to approximate what's going on with processes where we don't fully understand the physics.
Lately, GCMs have faced some competition from machine-learning techniques, which train AI systems to recognize patterns in meteorological data and use those to predict the conditions that will result over the next few days.
Their forecasts, however, tend to get a bit vague after more than a few days and can't deal with the sort of long-term factors that need to be considered when GCMs are used to study climate change.
On Monday, a team from Google's AI group and the European Centre for Medium-Range Weather Forecasts are announcing NeuralGCM, a system that mixes physics-based atmospheric circulation with AI parameterization of other meteorological influences.
Neural GCM is computationally efficient and performs very well in weather forecast benchmarks.
Strikingly, it can also produce reasonable-looking output for runs that cover decades, potentially allowing it to address some climate-relevant questions.
While it can't handle a lot of what we use climate models for, there are some obvious routes for potential improvements.
Full article: https://arstechnica.com/?p=2038449
Re: Chat
Facebook has reminded me that I posted this 12 years ago today:
On Naval-History.Net, we have published the edited logs of 314 WWI-era Royal Navy ships.
Not sure where those figures came from. It was a long time ago!The Royal Navy logs are complete: 302 ships, 1,090,690 pages. US logs coming soon!
https://oldweather.wordpress.com/2012/0 ... ervations/
On Naval-History.Net, we have published the edited logs of 314 WWI-era Royal Navy ships.
-
pommystuart
- Posts: 1809
- Joined: Mon May 18, 2020 12:48 am
- Location: Cooranbong, NSW, Australia.
Re: Chat
For further details see this link. No joke, it will slay you.
https://www.smh.com.au/technology/aussi ... xwbip.html
(As an aside see also, https://cosmosmagazine.com/earth/water/ ... re-flavour)
and https://developer.mozilla.org/en-US/doc ... Status/418
Last edited by pommystuart on Thu Jul 25, 2024 3:37 am, edited 1 time in total.
-
joke_slayer
- Posts: 185
- Joined: Wed Feb 24, 2021 12:03 am
- Location: Scotland
Re: Chat
Thank you <3
Been enjoying a nice holiday with my family
Been enjoying a nice holiday with my family
