Jump to content

  • Member Statistics

    18,148
    Total Members
    7,904
    Most Online
    happyclam13
    Newest Member
    happyclam13
    Joined

Tracking either the biggest storm to affect at a regional scale since perhaps 2013 ... or, a complete whiff. Pick-em'

Typhoon Tip

By Typhoon Tip,
in New England

 Share

Recommended Posts

wxsniss

wxsniss

Posted
Posted
  On 1/8/2025 at 9:51 PM, WxWatcher007 said:

 

And that’s what fascinates me. There is this element of unpredictability that occurs on both a mesoscale and synoptic level that has an enormous impact on people and the environment. It’s the EF5 that destroys a house and spares another. It’s the snow/mix line that gives one part of town 6” of snow and a place a few miles away half that. It’s being 20 miles from the eye of a hurricane and watching it wobble as landfall approaches. It’s watching a window for a blizzard open and close. There is so much to consider. 
 

 

Expand  

Fortunately, whether because of limitations in input data +/- inadequate computing, my hunch is AI forecasting has a very long way to go before it can nail these highly impactful nuances. Which I'm ok with... this hobby would lose much of its suspense and thrill if we had perfect deterministic models.

  • Like 1
Link to comment
Share on other sites
  • Replies 1.6k
  • Created
  • Last Reply

Top Posters In This Topic

Popular Days

Top Posters In This Topic

Popular Days

Popular Posts

ORH_wxman
ORH_wxman

Ineedsnow is like the sunfish you kept catching at the lake off the dock when you were a kid. You’d throw it back in the lake and then it wound still get hooked when you threw the bait in a minute lat

weatherwiz
weatherwiz

can make our own 

dendrite
dendrite

PoPo melting down with skynet. Hate to see it. 

Posted Images

dendrite

dendrite

Posted
Posted
  On 1/9/2025 at 10:47 AM, CoastalWx said:

Nam is the only one doing that. Although as many said, could be some -SN around. We’ll watch the nrn stream tendencies. 

Expand  

Seems like it’s feeling that northern stream PVA bowling in from our west Sat. Nammy is probably overdone, but maybe we meet somewhere in the middle? RGEM had a hint of an extra “burst” and the sim radars kinda have that norluny look hanging offshore.

I’d love a 2” refresher up here before the next shot of cold arrives. 

  • Like 2
Link to comment
Share on other sites
mahk_webstah

mahk_webstah

Posted
Posted
  On 1/9/2025 at 11:18 AM, dendrite said:

Seems like it’s feeling that northern stream PVA bowling in from our west Sat. Nammy is probably overdone, but maybe we meet somewhere in the middle? RGEM had a hint of an extra “burst” and the sim radars kinda have that norluny look hanging offshore.

I’d love a 2” refresher up here before the next shot of cold arrives. 

Expand  

We could use it just to look nicer.  Big local differences in snow cover.  On my small hill in water st just patchy snow in the woods but mostly bare.  Drive a mile to long st to webster and then 127, mostly snow covered but a bit patchy.  At Salisbury and down 4 to Andover full snow covered of several inches and the same if not more in New London.

Link to comment
Share on other sites
OceanStWx

OceanStWx

Posted
Posted
  On 1/9/2025 at 1:24 AM, wxsniss said:

Fortunately, whether because of limitations in input data +/- inadequate computing, my hunch is AI forecasting has a very long way to go before it can nail these highly impactful nuances. Which I'm ok with... this hobby would lose much of its suspense and thrill if we had perfect deterministic models.

Expand  

For the time being, AI is going to be trained off of what has happened in the past. And much of that reanalysis type stuff. In order to really suss out the details AI will need the full resolution of the atmosphere, and so it will suffer the same problems as traditional modeling in that respect.

I think we'll see far more advancement in the pattern recognition type machine learning (think Colorado State severe weather stuff).

  • Thanks 1
  • 100% 1
Link to comment
Share on other sites
CoastalWx

CoastalWx

Posted
Posted
  On 1/9/2025 at 11:18 AM, dendrite said:

Seems like it’s feeling that northern stream PVA bowling in from our west Sat. Nammy is probably overdone, but maybe we meet somewhere in the middle? RGEM had a hint of an extra “burst” and the sim radars kinda have that norluny look hanging offshore.

I’d love a 2” refresher up here before the next shot of cold arrives. 

Expand  

Yeah. 1-2 would be nice even if half of it is gone Sunday. 

  • Like 2
Link to comment
Share on other sites
UnitedWx

UnitedWx

Posted
Posted
  On 1/9/2025 at 12:36 PM, OceanStWx said:

For the time being, AI is going to be trained off of what has happened in the past. And much of that reanalysis type stuff. In order to really suss out the details AI will need the full resolution of the atmosphere, and so it will suffer the same problems as traditional modeling in that respect.

I think we'll see far more advancement in the pattern recognition type machine learning (think Colorado State severe weather stuff).

Expand  

100 percent. Better data in, better computation. That really isn't any different in data between models, so my expectations for AI models to be more stellar is quite low. I'm waiting for the 5 boob low super storms to show up on one of the AIs :lol:

Link to comment
Share on other sites
OceanStWx

OceanStWx

Posted
Posted
  On 1/9/2025 at 12:52 PM, UnitedWx said:

100 percent. Better data in, better computation. That really isn't any different in data between models, so my expectations for AI models to be more stellar is quite low. I'm waiting for the 5 boob low super storms to show up on one of the AIs :lol:

Expand  

Just a six fingered circle jerk waiting to happen.

  • Haha 1
Link to comment
Share on other sites
weatherwiz

weatherwiz

Posted
Posted
  On 1/9/2025 at 12:36 PM, OceanStWx said:

For the time being, AI is going to be trained off of what has happened in the past. And much of that reanalysis type stuff. In order to really suss out the details AI will need the full resolution of the atmosphere, and so it will suffer the same problems as traditional modeling in that respect.

I think we'll see far more advancement in the pattern recognition type machine learning (think Colorado State severe weather stuff).

Expand  

This is such a beautiful way of putting it. 

  • 100% 1
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
Go to topic listing

  • Recently Browsing   0 members

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