All Activity
- Past hour
-
Head to the Ben Franklin bridge pronto is all i can say. He will probably leave Saquon on the bench for every 4th quarter for the rest of his career. Good luck.
-
January 2026 regional war/obs/disco thread
dendrite replied to Baroclinic Zone's topic in New England
-
January 2026 regional war/obs/disco thread
CoastalWx replied to Baroclinic Zone's topic in New England
I think 2nd time. But yeah it’s nice. -
Jan 17-18 Sunday Funday Storm
LakeNormanStormin replied to NorthHillsWx's topic in Southeastern States
Who started the storm thread? You're fired lol -
reel this in
-
Storm potential January 18th-19th
anthonymm replied to WeatherGeek2025's topic in New York City Metro
Euro op, and every other physics based model except Canadian -
-
First Legit Storm Potential of the Season Upon Us
weatherwiz replied to 40/70 Benchmark's topic in New England
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? -
Lol. New York's trash is definitely not our treasure.
-
actually not to weenie out but the euro develops the storm at 192-198 lol
-
Yeah I’d say almost none of the models really moved east much in that cycle, but everything trended flatter and weaker. That ain’t gonna cut it for (almost) everyone. More amped is probably also slower since it’d wanna turn the corner instead of slide straight out to sea. We can worry about temps when we actually get something to fall.
-
Storm potential January 18th-19th
Santa Claus replied to WeatherGeek2025's topic in New York City Metro
looks like someone we know -
Winter 2025-26 Medium/Long Range Discussion
roardog replied to michsnowfreak's topic in Lakes/Ohio Valley
Spring snowstorms actually have the benefit of potentially much warmer air to the south causing a stronger storm. It just has to have cold enough air to work with on the cold side which isn’t always a guarantee the deeper into March you go. -
Does this mean GreyHat will be extending his trip until Monday now?
-
Hell of a signal at range. Look at all that HP to the N/NW.
-
had to say hello, i'm panicking! these models suck. And Ai GFS is supposed to replace regular gfs i don't know about that. Can we get some snow wtf
-
If the last 24 hours has taught us anything it’s just reaffirmed that the GFS is simply trash
-
January 2026 regional war/obs/disco thread
Damage In Tolland replied to Baroclinic Zone's topic in New England
No 50’s ASOUT. None -
Fr fr this Euro run be bussin at the end. It did bring the rizz no cap.
-
January 2026 regional war/obs/disco thread
Damage In Tolland replied to Baroclinic Zone's topic in New England
Didn’t touch 50 at all but glad you did 4-5 times and got outside to do spring cleanup etc -
Philly Eagles interviewing Todd Monken for possible OC job. You Ravens folks, what are your thoughts.on him when he was in Baltimore? Im not very familiar tbh
-
My eyes lit up when I saw I was quoted by @SnowenOutThere, and it lit up even more when I saw what he sent.
-
January 2026 regional war/obs/disco thread
dendrite replied to Baroclinic Zone's topic in New England
48hrs+ of 38° or above. Wow. -
Celsius lol good one
-
Low of 40, high of 45. Helluva way to run a cool down!
