Jump to content
  • Member Statistics

    17,610
    Total Members
    7,904
    Most Online
    NH8550
    Newest Member
    NH8550
    Joined

Dec 5-6th clipper threat


George001
 Share

Recommended Posts

Just now, Henry's Weather said:

Seems like it’s worse at vorticity but better at geopotential heights. Worth noting also that 20% increase in temp forecast accuracy three days out should have sizable implications for the energy industry, no?

That's possible but I mean if the accuracy is because it had temperatures of 88-90 (which verified) versus 84-86 which other models had...I can't see that being a huge impact on the power grid. I would want to know more details though. For example, say google AI was showing a large area of high temperatures in the 105-110 range at D10 and the GFS was a bit more muted...100-105. What preparations would be made differently within the energy industry, for example? 

Now...if we're talking where this was showing widespread 100+ while other models were like 70-80 and this 100+ is verifying...now that is noteworthy and certainly something more groundbreaking. 

  • Like 1
Link to comment
Share on other sites

1 minute ago, weatherwiz said:

Want to clarify...I was calling the claim garbage, not the model or the work into it. If a claim is going to be made that a weather event was nailed 10 days our or 15 days out...at least indicate the model held true to that solution for each run leading up to that day. If google AI had a category 3 hitting SNE at D15 and it ended up occurring...if between it showed solutions ranging from OTS or into the mid-Atlantic, or a weak storm...well you can't say it "nailed it". That's what I am calling garbage

And I agree, the watered down article from Barrons is "garbage".  But that's not what you wrote, nor what I took exception to.  To quote you "Was it extremely consistent or did it waver back-and-forth and have a million different solutions? If that is the case then GARBAGE. That's no different than what models currently do."  You're calling the AI "GARBAGE" in this sentence, but as noted in your subsequent post this particular implementation of AI is actually better at some things due to it's hybrid approach.

Again, you're a smart guy just suggesting to temper your immediate knee-jerk distaste of AI reactions and read before you post.  Genuinely best regards. :D

Link to comment
Share on other sites

19 minutes ago, Henry's Weather said:

Seems like it’s worse at vorticity but better at geopotential heights. Worth noting also that 20% increase in temp forecast accuracy three days out should have sizable implications for the energy industry, no?

my dream is to evolve technology to the point where there is no energy market. 

but ... since human kind cannot seem to incentivize doing anything without the potential for maximizing economic gain, that will probably continue to bury such advancements - not dissimilar to how/why big oil has conditioned all ir cultures of the world into believing oil is the only way... and has been in place so long that the fallacy is both institutional but also so multi generationally sewn into perceptions that people will blindly defend oil like a throngs of people drinking 'the cool-aide' without even knowing any reason to suspect it... the system propagandizes itself in that sense and the work is done.

Link to comment
Share on other sites

1 minute ago, metagraphica said:

And I agree, the watered down article from Barrons is "garbage".  But that's not what you wrote, nor what I took exception to.  To quote you "Was it extremely consistent or did it waver back-and-forth and have a million different solutions? If that is the case then GARBAGE. That's no different than what models currently do."  You're calling the AI "GARBAGE" in this sentence, but as noted in your subsequent post this particular implementation of AI is actually better at some things due to it's hybrid approach.

Again, you're a smart guy just suggesting to temper your immediate knee-jerk distaste of AI reactions and read before you post.  Genuinely best regards. :D

Agree, poorly worded by me. I am definitely interested in reading literature on this and I am certainly open to having a completely different view on this. What really irks me though (and not just with AI) is these watered down articles and and all these claims made just to draw people in, especially from companies and organizations who profit on marketing stuff...you can make anything sound good and like the best thing ever and sell it to the average Joe. 

  • Like 1
Link to comment
Share on other sites

27 minutes ago, weatherwiz said:

I do want to invest some time to find any published, peer-reviewed papers which provide highly detailed analysis...

This paper hits on one of the challenges of disruptive (read, not modernized or transformative) technology.  Successfully managing the organizational change management aspect of that disruption is often as valuable as the disruption itself.  

https://journals.ametsoc.org/configurable/content/journals$002fbams$002f105$002f11$002fBAMS-D-24-0044.1.xml

Machine Learning-based AI has been deeply embedded into numerical weather prediction for 20 years.  Generative AI is a whole different thing.  And, you see the acceptance biases of NWS forecasters quite easily in this paper.  And, interestingly, you see those biases morphing over the duration of the study.  A side benefit of the study is the fantastic reference list of NWP and forecasting AI research papers.  Enjoy!

  • Like 2
  • Thanks 1
Link to comment
Share on other sites

13 minutes ago, weatherwiz said:

That's possible but I mean if the accuracy is because it had temperatures of 88-90 (which verified) versus 84-86 which other models had...I can't see that being a huge impact on the power grid. I would want to know more details though. For example, say google AI was showing a large area of high temperatures in the 105-110 range at D10 and the GFS was a bit more muted...100-105. What preparations would be made differently within the energy industry, for example? 

Now...if we're talking where this was showing widespread 100+ while other models were like 70-80 and this 100+ is verifying...now that is noteworthy and certainly something more groundbreaking. 

Yeah I don’t really know about the energy economy at scale, but if forecasts are consistently a few degrees more accurate, then of course energy companies would prefer those forecasts because over the long run, they are more prepared to efficiently provide energy

  • Like 1
Link to comment
Share on other sites

2 minutes ago, das said:

This paper hits on one of the challenges of disruptive (read, not modernized or transformative) technology.  Successfully managing the organizational change management aspect of that disruption is often as valuable as the disruption itself.  

https://journals.ametsoc.org/configurable/content/journals$002fbams$002f105$002f11$002fBAMS-D-24-0044.1.xml

Machine Learning-based AI has been deeply embedded into numerical weather prediction for 20 years.  Generative AI is a whole different thing.  And, you see the acceptance biases of NWS forecasters quite easily in this paper.  And, interestingly, you see those biases morphing over the duration of the study.  A side benefit of the study is the fantastic reference list of NWP and forecasting AI research papers.  Enjoy!

Definitely going to give this a read, thank you!

And that was something I was going to mention too...don't current NWP models already have some degree of AI integrated into them? But looks and sounds like that will be established in the paper. 

Link to comment
Share on other sites

Special Weather Statement
National Weather Service Gray ME
1251 PM EST Thu Dec 5 2024

MEZ012-018>020-023>025-033-NHZ004-051845-
Southern Oxford-Interior Cumberland Highlands-Androscoggin-Interior
York-Coastal York-Central Interior Cumberland-Coastal
Cumberland-Sagadahoc-Northern Carroll-
1251 PM EST Thu Dec 5 2024

...An area of heavy snow showers and a few snow sqaulls will affect
northeastern York... southern Oxford...southern
Androscoggin...Cumberland and central Sagadahoc Counties...

At 1250 PM EST...An area of heavy snow showers was along a line
extending from Fryeburg to 9 miles south of Kennebunkport...and
moving east at 35 MPH.

Locations impacted include...
Portland, Lewiston, South Portland, Auburn, Biddeford, Brunswick,
Westbrook, Bridgton, Fryeburg, Mechanic Falls, Naples, Turner,
Topsham, Cumberland, Saco, Gorham, Falmouth, Kennebunk, Cape
Elizabeth, and Buxton.

This includes the following highways...
 Interstate 295 between mile markers 1 and 30.
 Interstate 95 between mile markers 25 and 85.

This also includes...
  Sebago Lake, Pleasant Mountain, Long Lake, Fortunes Rock Beach, and
Higgins Beach.
  Peaks Island, Long Island, Cushing Island, Cousins Island, and
Bailey Island.

LAT...LON 4411 7103 4427 7021 4366 6982 4369 6996
      4368 6999 4363 7000 4362 7005 4357 7010
      4358 7016 4351 7020 4349 7033 4343 7029
      4333 7039 4330 7050
TIME...MOT...LOC 1750Z 261DEG 34KT 4405 7091 4327 7041
$$

JC

  • Like 1
Link to comment
Share on other sites

17 minutes ago, Typhoon Tip said:

my dream is to evolve technology to the point where there is no energy market. 

but ... since human kind cannot seem to incentivize doing anything without the potential for maximizing economic gain, that will probably continue to bury such advancements - not dissimilar to how/why big oil has conditioned all ir cultures of the world into believing oil is the only way... and has been in place so long that the fallacy is both institutional but also so multi generationally sewn into perceptions that people will blindly defend oil like a throngs of people drinking 'the cool-aide' without even knowing any reason to suspect it... the system propagandizes itself in that sense and the work is done.

Yeah, regio beta paradox. Institutional entrenchment

Link to comment
Share on other sites

27 minutes ago, dryslot said:
Special Weather Statement
National Weather Service Gray ME
1251 PM EST Thu Dec 5 2024

MEZ012-018>020-023>025-033-NHZ004-051845-
Southern Oxford-Interior Cumberland Highlands-Androscoggin-Interior
York-Coastal York-Central Interior Cumberland-Coastal
Cumberland-Sagadahoc-Northern Carroll-
1251 PM EST Thu Dec 5 2024

...An area of heavy snow showers and a few snow sqaulls will affect
northeastern York... southern Oxford...southern
Androscoggin...Cumberland and central Sagadahoc Counties...

At 1250 PM EST...An area of heavy snow showers was along a line
extending from Fryeburg to 9 miles south of Kennebunkport...and
moving east at 35 MPH.

Locations impacted include...
Portland, Lewiston, South Portland, Auburn, Biddeford, Brunswick,
Westbrook, Bridgton, Fryeburg, Mechanic Falls, Naples, Turner,
Topsham, Cumberland, Saco, Gorham, Falmouth, Kennebunk, Cape
Elizabeth, and Buxton.

This includes the following highways...
 Interstate 295 between mile markers 1 and 30.
 Interstate 95 between mile markers 25 and 85.

This also includes...
  Sebago Lake, Pleasant Mountain, Long Lake, Fortunes Rock Beach, and
Higgins Beach.
  Peaks Island, Long Island, Cushing Island, Cousins Island, and
Bailey Island.

LAT...LON 4411 7103 4427 7021 4366 6982 4369 6996
      4368 6999 4363 7000 4362 7005 4357 7010
      4358 7016 4351 7020 4349 7033 4343 7029
      4333 7039 4330 7050
TIME...MOT...LOC 1750Z 261DEG 34KT 4405 7091 4327 7041
$$

JC

Didn’t really stick much in CON. 

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share

  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...