Jump to content
  • Member Statistics

    17,860
    Total Members
    7,904
    Most Online
    Malkir008
    Newest Member
    Malkir008
    Joined

Potential extensive winter event, I-95 west and with again a chance for NYC first inch(es) of snow Mon or more likely Tue Jan 16, 2024 (serves as OBS thread as well)


wdrag
 Share

Recommended Posts

  On 1/12/2024 at 6:55 PM, wdrag said:

I can only presume AI assisted modeling was tested for improved guidance prior to its implementation.  Recommend staying with WiC and check their afternoon EPD when it comes out

Expand  

I'm not sure why anyone would use AI to forecast the weather.

1) AI is a glorified analog so it won't perform well for anomalous events.

2) We don't know what's incorporated in AI models so we can't correct for known biases.

3) Why use AI when we already have trusted NWP models?

AI can be used to improve the accuracy of NWP output that have a known, and predictable bias though. For example, improving wind speed: < https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018JD029590 >.

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

  On 1/12/2024 at 7:28 PM, MegaMike said:

I'm not sure why anyone would use AI to forecast the weather.

1) AI is a glorified analog so it won't perform well for anomalous events.

2) We don't know what's incorporated in AI models so we can't correct for known biases.

3) Why use AI when we already have trusted NWP models?

AI can be used to improve the accuracy of NWP output that have a known, and predictable bias though. For example, improving wind speed: < https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018JD029590 >.

Expand  

just dropping into say that i'm from latham originally and it warms my heart to see someone on this board from the 518

  • Like 1
Link to comment
Share on other sites

  On 1/12/2024 at 7:28 PM, MegaMike said:

I'm not sure why anyone would use AI to forecast the weather.

1) AI is a glorified analog so it won't perform well for anomalous events.

2) We don't know what's incorporated in AI models so we can't correct for known biases.

3) Why use AI when we already have trusted NWP models?

AI can be used to improve the accuracy of NWP output that have a known, and predictable bias though. For example, improving wind speed: < https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018JD029590 >.

Expand  

my brother in christ, they're trying to takeover the world

  • Weenie 1
Link to comment
Share on other sites

  On 1/12/2024 at 7:28 PM, MegaMike said:

I'm not sure why anyone would use AI to forecast the weather.

1) AI is a glorified analog so it won't perform well for anomalous events.

2) We don't know what's incorporated in AI models so we can't correct for known biases.

3) Why use AI when we already have trusted NWP models?

AI can be used to improve the accuracy of NWP output that have a known, and predictable bias though. For example, improving wind speed: < https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2018JD029590 >.

Expand  

Trusted models?  AI could be a good thing, especially when you can adjust for errors in the program say at day 3 and correct for biases.  Might improve long range patterns?  I would think the AI would correct for known biases, otherwise, why use AI?  I would think no model would handle an anomalous event well?  Or perhaps instead of AI, have human intervention adjusting at say, day 3 in a long range model to correct for a suspected error?

Link to comment
Share on other sites

  On 1/12/2024 at 10:00 PM, uofmiami said:

 

Expand  

As I have been saying all along, it comes down to whether or not the Southern vort is timed well with the incoming trough. If it's too fast like the 12z ECMWF and now 18z GFS shows, the trough will kick it out. If it's too slow it could phase early and you could get a super amplified trough and rain at the coast. Has to be timed perfectly. Still time for this one but there is no denying that this was a major nod towards the Euro.

  • Confused 1
Link to comment
Share on other sites

  On 1/12/2024 at 10:04 PM, SBUWX23 said:

The euro has more snow than the GFS now. Models are nodding at nothing other than uncertainty 

Expand  

The Euro has been consistently slower with the trough axis dropping down from the upper Plains. Until this timing issue is fully resolved there will be some uncertainty. The hope is that it is still poorly sampled as @Typhoon Tip alluded too earlier. 

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...