MegaMike Posted January 15 Share Posted January 15 10 minutes ago, Winter Wizard said: From what I've gathered, verification stats have had Euro AI ensemble and EPS as pretty much neck and neck...sometimes the AI has had a slight edge but definitely not the magic bullet that some people imply. The AI has done better with individual storms, especially this hurricane season, but it also got its clock cleaned in others. Just like with every other model. My two cents is there is promise, but the jury is still out on when they are most useful and to what extent. There will always be limitations when the models are mostly data-driven instead of physics based. I never imagined this forum diverge into a discussion about AI Admittedly, your last sentence is difficult to accept. I'm sure most of us feel the same too. To add to the discussion, here's the 12z ensemble spread and diagnostic prate/type at 90hr... Still uncertainty amongst the ensembles/models so we're not entirely dead yet. If I had to stratify it as is (for measurable precipitation), I'd call it the AIs+ICON+CMC vs. GFS+ECMWF+UKMET. Link to comment Share on other sites More sharing options...
DJln491 Posted January 15 Share Posted January 15 1 3 Link to comment Share on other sites More sharing options...
CoastalWx Posted January 15 Share Posted January 15 Icon with a move east. Link to comment Share on other sites More sharing options...
ORH_wxman Posted January 15 Share Posted January 15 8 minutes ago, CoastalWx said: Icon with a move east. Reggie with a move west. Prob wrong but still plenty of model disagreement. 2 Link to comment Share on other sites More sharing options...
Spanks45 Posted January 15 Share Posted January 15 Just now, ORH_wxman said: Reggie with a move west. Prob wrong but still plenty of model disagreement. Quite surprised how that looked....it was west with Saturday too, but would sacrifice Saturday for the look Sunday. The timing is odd too, snowing here on Sunday, early morning Link to comment Share on other sites More sharing options...
CoastalWx Posted January 15 Share Posted January 15 6 minutes ago, ORH_wxman said: Reggie with a move west. Prob wrong but still plenty of model disagreement. I just looked. Nice little event Link to comment Share on other sites More sharing options...
weathafella Posted January 15 Share Posted January 15 Reggie is like Brady Anderson. One big season. 11 years ago 1 3 Link to comment Share on other sites More sharing options...
ineedsnow Posted January 15 Share Posted January 15 18z GFS west but not west enough Link to comment Share on other sites More sharing options...
Sey-Mour Snow Posted January 15 Share Posted January 15 AIGFS another “solid it” Link to comment Share on other sites More sharing options...
MJO812 Posted January 15 Share Posted January 15 Just now, ineedsnow said: 18z GFS west but not west enough Yep tick tick Link to comment Share on other sites More sharing options...
CoastalWx Posted January 15 Share Posted January 15 Good shift west in gfs and AI is solid Link to comment Share on other sites More sharing options...
Sey-Mour Snow Posted January 15 Share Posted January 15 Just now, CoastalWx said: Good shift west in gfs and AI is solid Ya that’s a big shift from 12z, rgem and rrfs with gfs moving west at least give the AIs some backup Link to comment Share on other sites More sharing options...
CoastalWx Posted January 15 Share Posted January 15 Just now, Sey-Mour Snow said: Ya that’s a big shift from 12z, rgem and rrfs with gfs moving west at least give the AIs some backup I can’t do it 5 1 1 Link to comment Share on other sites More sharing options...
brooklynwx99 Posted January 15 Share Posted January 15 1 minute ago, Sey-Mour Snow said: Ya that’s a big shift from 12z, rgem and rrfs with gfs moving west at least give the AIs some backup the RGEM is actually really similar to the AI models... has the main precip with the PVA ahead of the main vort 1 Link to comment Share on other sites More sharing options...
weathafella Posted January 15 Share Posted January 15 GFS AI has been relatively steadfast. 4 1 Link to comment Share on other sites More sharing options...
UnitedWx Posted January 15 Share Posted January 15 2 hours ago, eduggs said: I don't agree with this at all. I think it leads many people off a cliff. People think their intuition regarding loosely defined concepts like "pattern" is superior to supercomputers developed specifically to model exactly what's possible in the atmosphere. It's pure ego. I, well I really don't get that at all. SO many times we've heard good Mets say why XYZ solution doesn't make sense... as in today's "storm". The good ones raised flags everywhere when certainmodelsstartedshowingbig hits, seen it a million times over the years... and then you have the social media twats. Link to comment Share on other sites More sharing options...
ineedsnow Posted January 15 Share Posted January 15 GEFS will be better 1 Link to comment Share on other sites More sharing options...
George001 Posted January 15 Share Posted January 15 3 hours ago, CoastalWx said: Even the euro AI ensembles got more bullish. This is ridiculous lol. Gotta think they crumble soon. I continue to stand with the Pope on this one. 1 1 Link to comment Share on other sites More sharing options...
The 4 Seasons Posted January 15 Share Posted January 15 Lol I get severe whiplash reading through these pages. Still worth watching for a moderate event but obviously a big hit looks off the table. Still concerning EC wants nothing to do with it hopefully some kind of agreement at 00Z. 1 Link to comment Share on other sites More sharing options...
Kitz Craver Posted January 15 Share Posted January 15 Fodder, but that’s one tasty Reggie 1 Link to comment Share on other sites More sharing options...
HoarfrostHubb Posted January 15 Share Posted January 15 13 minutes ago, The 4 Seasons said: Lol I get severe whiplash reading through these pages. Still worth watching for a moderate event but obviously a big hit looks off the table. Still concerning EC wants nothing to do with it hopefully some kind of agreement at 00Z. Yeah. I’m definitely it buying anything for my area, unless something drastic changes. further east could still get something. Link to comment Share on other sites More sharing options...
WeatherGeek2025 Posted January 15 Share Posted January 15 i said this earlier.. anyone remember nemo tracking.. how did the models react 3 days prior to getting hit? this reminds me of Nemo but the opposite. euro was on the western front that time showing 36 inches for NYC, ended up with like 8 inches. also gfs ended up showing the most eastern solutions than lost it for a day than brought it back! Euro never wavered until the storm was about to hit! this reminds me of that but the opposite meaning GfS should start showing western hits again by tonight the latest otherwise my theory is wrong. Also euro isn't as good since that last upgrade a few years back 1 1 Link to comment Share on other sites More sharing options...
MegaMike Posted January 15 Share Posted January 15 17 minutes ago, ineedsnow said: GEFS will be better Definitely! I'll never live this one down if AI outperforms NWP. 4 Link to comment Share on other sites More sharing options...
ORH_wxman Posted January 15 Share Posted January 15 Let’s get the euro something better than a Cape scraper. At least get some advisory stuff to E MA coast and we’ll have something to work with at 3 days out. 7 Link to comment Share on other sites More sharing options...
WeatherGeek2025 Posted January 15 Share Posted January 15 1 minute ago, ORH_wxman said: Let’s get the euro something better than a Cape scraper. At least get some advisory stuff to E MA coast and we’ll have something to work with at 3 days out. this reminds me of Nemo but the opposite. euro was on the western front that time showing 36 inches for NYC, ended up with like 8 inches. also gfs ended up showing the most eastern solutions than lost it for a day than brought it back! Euro never wavered until the storm was about to hit! this reminds me of that but the opposite meaning GfS should start showing western hits again by tonight the latest otherwise my theory is wrong. Also euro isn't as good since that last upgrade a few years back and 1 2 1 Link to comment Share on other sites More sharing options...
brooklynwx99 Posted January 15 Share Posted January 15 bro what 2 1 Link to comment Share on other sites More sharing options...
George001 Posted January 15 Share Posted January 15 2 minutes ago, WeatherGeek2025 said: this reminds me of Nemo but the opposite. euro was on the western front that time showing 36 inches for NYC, ended up with like 8 inches. also gfs ended up showing the most eastern solutions than lost it for a day than brought it back! Euro never wavered until the storm was about to hit! this reminds me of that but the opposite meaning GfS should start showing western hits again by tonight the latest otherwise my theory is wrong. Also euro isn't as good since that last upgrade a few years back and Completely different setup. The pattern is more progressive. Link to comment Share on other sites More sharing options...
Go Kart Mozart Posted January 15 Share Posted January 15 4 hours ago, weatherwiz said: As stated the idea of they're supposed to "learn" is totally overblown. Traditional models already have some AI built into them and already do this to an extent. From what I understand (and this may not apply equally to AI models) is AI assists with the initializing scheme whereas it combs through ingested data and will "remove" what it believes to be bad data or an outlier based on a slew of historical information. The goal here is, or the idea is, this will lead to a more accurate initialization which is important because once you move forward in time you start to introduce error and that error becomes compounded over time...that is why forecast models (OP) are generally useless beyond D7-10 and can even be relatively useless past D5 if there is alot going on. Error also occurs because of rounding and approximations, especially approximations. AI models are built on a wealth of historical data where it runs and looks for similarities, both to the initialized field and then forecasts based on how these similarities evolved in the past. The challenges in all of this is, there is still a lot we don't understand about weather, particularly when it comes down to processes which occur during storm evolution and it becomes even more of a challenge because for forecast models to ingest this data we have to be able to parameterize it. There is much more to this then just verifying a specific level or variable and even that leads to a lot of questions. Probably in a tame weather pattern that is not hostile, AI will outperform but what good is that or what value is that really adding? Good points. I do think AI currently has solid value beyond just "tame patterns". In any case, just wait until we have a blend of AI, physical inputs, and quantum computing. In a way, I hope modelling doesn't get too good, it will take the fun out this. Like watching the UConn women play Xavier or some team like that. Link to comment Share on other sites More sharing options...
Damage In Tolland Posted January 15 Share Posted January 15 5 minutes ago, WeatherGeek2025 said: this reminds me of Nemo but the opposite. euro was on the western front that time showing 36 inches for NYC, ended up with like 8 inches. also gfs ended up showing the most eastern solutions than lost it for a day than brought it back! Euro never wavered until the storm was about to hit! this reminds me of that but the opposite meaning GfS should start showing western hits again by tonight the latest otherwise my theory is wrong. Also euro isn't as good since that last upgrade a few years back and Cocked? 1 2 Link to comment Share on other sites More sharing options...
WeatherGeek2025 Posted January 15 Share Posted January 15 3 minutes ago, brooklynwx99 said: bro what i'm convinced we live in a simulation Link to comment Share on other sites More sharing options...
Recommended Posts
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 accountSign in
Already have an account? Sign in here.
Sign In Now