January 2026 OBS and Discussion

[Stormlover74]

5 minutes ago, Franklin0529 said:

Gfs likes the mid Atlantic for the weekend. Gets about .5 liquid up here 

Ai or regular? 

[WeatherGeek2025]

1 minute ago, Stormlover74 said:

Ai or regular? 

has to be ai because regular is supressed

[wdrag]

3 hours ago, Neblizzard said:

Thank you for posting Walt.  Hope you’re feeling well, please don’t give up on us.   

Didn't give up on AMWX...

 

I still lurk and will toss out something once in a while but can't lead the threads...just too much at home including a FB weather group that feeds a bunch of friends-acquaintences and work colleagues from ATL-Old Forge NY.  Couldn't stay out in front of it on threads for AMWX without stressing a bit.  Takes time to generate a decent pice of info, including researching the models, patterns etc.

Plenty of very good thread met leaders here - glad you're getting it done! Think plowable snows.  

This is a very good WINTER like I used to remember.   Lots of daily snowscapes, less grass. 

[psv88]

Getting our coldest airmass of the year during our coldest average week of the year. Often happens in late July as well. 

we’re in the “dog days” of winter now

[SACRUS]

 

GFS and ECMWF Core vs AI details: (AI) just for reference

ECMWF’s AI system (AIFS) is a fully separate, AI-native forecast model, not the traditional ECMWF model with machine learning layered on top.

Unlike the main Integrated Forecasting System (IFS), AIFS does not solve physical equations; it uses deep learning trained on decades of reanalysis and operational forecast data to predict the next atmospheric state directly.
It ingests similar inputs (pressure, temperature, wind, humidity fields) but produces forecasts via neural networks rather than numerical integration.
The operational IFS remains the authoritative, physics-based backbone for warnings, ensembles, and high-impact decision support.
ECMWF runs AIFS in parallel, comparing skill, speed, and bias against IFS at multiple lead times.
In medium-range forecasts (≈3–10 days), AIFS has shown skill comparable to—and in some metrics better than—the full physics model, at a fraction of the computational cost.

Key takeaways

• Separate model: AIFS is independent from IFS, not a post-processing or hybrid add-on

• Massively faster: Enables rapid global forecasts and large ensembles with minimal compute

• Complementary role: IFS provides physical realism and extremes; AIFS adds speed and pattern skill
  
   

• AIFS (AI Forecasting System):

  • Research & development: 2022–2023

  • First real-time parallel runs: mid-2023

  • Publicly released experimental real-time forecasts: 2024

  • Status today: Operational parallel model (not replacing IFS)

• ECMWF was the first major global center to run an AI-native global model continuously in real time.

   

--------------------------------------------------------------------------------------------------------------------------------------

NOAA’s GFS AI efforts are not a single AI-native replacement model like ECMWF’s AIFS, but a combination of experimental AI models and AI-enhanced components run alongside the main GFS.

The operational GFS remains a fully physics-based numerical weather prediction system using the FV3 dynamical core.
NOAA’s AI models are trained on decades of global reanalysis and past GFS outputs to forecast future atmospheric states directly, without explicitly solving physical equations.

These AI forecasts are run in parallel to GFS for evaluation, research, and medium-range pattern guidance rather than operational warnings.

In addition, machine learning is increasingly used inside the GFS workflow to improve data quality control, parameterizations, and bias correction.

The strategy prioritizes reliability and explainability, with AI enhancing—but not replacing—the core physics model.

Key takeaways

Hybrid approach: Physics-based GFS plus separate experimental AI models

No AI-only operational GFS: AI runs inform and augment forecasts, not replace them

Risk-aware path: Emphasis on safety, interpretability, and gradual adoption

 

NOAA (GFS + AI)

• GFS (physics model): Operational since the 1980s (FV3 core since 2019)

• NOAA AI global models:

  • Research pilots (ML weather prototypes): 2021–2022

  • Sustained real-time parallel AI runs: 2023

  • Expanded evaluation vs GFS: 2024–2025

  • Status today: Experimental / evaluation only (not operational)

NOAA deliberately moved slower and more conservatively than ECMWF.

------------------------------------------------------------------------------------------------------------------------------------

At 96h (Day 4), ECMWF’s physics-based IFS/HRES and the AI model (AIFS) are often very close on large-scale “pattern” skill (e.g., 500-hPa height), with AIFS frequently matching IFS despite being cheaper to run.
At 144h (Day 6), verification shown by ECMWF commonly has AIFS slightly ahead on upper-air headline scores (ACC/RMSE for fields like 500-hPa geopotential height), which is exactly where ML models tend to shine.
At 168h (Day 7), AIFS’ advantage can persist for broad circulation patterns, but that does not mean it’s “better at everything.”
IFS still tends to win on fine-scale/high-impact details that depend on explicit physics and higher resolution (e.g., local precipitation structure, boundary-layer processes), while AIFS can be more “smooth” because it’s learned and typically coarser.
Importantly, AIFS is its own model (AI-native), but it uses the same initial conditions as IFS (from ECMWF’s assimilation/analysis pipeline), so the comparison is about the forecast engine, not the starting point.
Bottom line: by Day 4/6/7, AIFS often matches or edges IFS on upper-air pattern skill, while IFS remains stronger for physically constrained, local extremes and “weather sensible” detail.

• 96h: usually “tie-ish” on big patterns; IFS often better on local detail

• 144h: AIFS commonly slightly better on headline upper-air skill (pattern metrics)
  
  168h: AIFS can stay ahead on large scales, but IFS remains the safer bet for extremes/structure

 

----------------------------------------------------------------------------------------------------------------------------

 

NOAA’s physics-based GFS still outperforms its experimental AI models at shorter lead times, especially where mesoscale detail and physical constraints matter.
At 96 hours (Day 4), the operational GFS generally verifies better against observations for precipitation placement, fronts, and boundary-layer–driven features, while AI runs are competitive mainly on broad upper-air patterns.
By 144 hours (Day 6), NOAA’s parallel AI models often match GFS on large-scale circulation metrics (e.g., 500-mb height anomalies) but begin to diverge more in sensible weather details.
At 168 hours (Day 7), AI models can sometimes show similar or slightly better pattern skill than GFS, reflecting strengths in learned climatology and flow regimes.
However, GFS remains more reliable for physically rare or extreme events (strong cyclogenesis, sharp gradients, convective outbreaks).
Because NOAA’s AI systems are still experimental and not ensemble-anchored, GFS remains the authoritative model for verification, warnings, and downstream products.

Key takeaways

• 96h: GFS usually verifies better overall; AI competitive mainly on upper-air patterns

• 144h: AI ≈ GFS on large scales; GFS better on precipitation and structure

• 168h: AI can edge pattern scores, but GFS remains stronger for extremes and decision use

 

Highest overall pattern skill (global):

1. GraphCast

2. ECMWF AIFS

3. FourCastNet / Pangu-Weather

Best operational reliability:

1. ECMWF IFS

2. NOAA GFS

Best short-range precipitation AI:

• MetNet-3

 

[SACRUS]

[kat5hurricane]

I'm very concerned about suppression, that's some serious cold pressing down this weekend. As is the case most of the time with these patterns, the best chance for a big storm is when the pattern relaxes a bit but at least we have some tracking to do in the meantime which is a god send after 3-4 winters of not even mere tracking.

[Franklin0529]

8 minutes ago, Stormlover74 said:

Ai or regular? 

AI sorry regular GFS is suppressed. But it did come a little further nw previous run 

[NEG NAO]

17 minutes ago, Franklin0529 said:

Gfs likes the mid Atlantic for the weekend. Gets about .5 liquid up here 

with snowfall ratio's higher than 10:1 probably

[TJW014]

6 minutes ago, PhiEaglesfan712 said:

Did it not in 2013-14 and 2014-15, when we had impressive cold? The nearby lakes in my area (Aetna Lake in Medford, NJ) was completely frozen over in late February/early March 2015.

2014 the bay did ice over, but it was deemed too thin (4" at the shoreline) for ice boat racing.

2015 was more significant, at least in my memory. We had the ice boats out there, think we measured 7" off Good Luck Point and Wannamaker Cove. I remember somebody's truck went through the ice off Pine Beach in March.

 I guess my subjective definition of "completely freezing over" is thick enough for the ice boats (6")

 

[Jt17]

with ratio's higher probably

That's prob 8-10 inches if it's going to be in the midteens while it's snowing. A little less suppression like the previous run and you get 15+ inches of crazy fluffy stuff


.

[NEG NAO]

5 minutes ago, Franklin0529 said:

AI sorry regular GFS is suppressed. But it did come a little further nw previous run 

regular GFS is usually suppressed or over amped at this range its Al version is supposed to be an improved version of the model

[Stormlover74]

Cmc might be close

[SHELEG]

Seems like the AI GFS is trending more towards suppression. 

[MANDA]

How much snow will it take this coming weekend to make you happy?

1-3"

2-4"

3-6"

4-8"

6-10"

8-14"

14"+

 

For me I'd be thrilled with 6-10", anything less would be a disappointment.  I'm prepared to be disappointed and my expectations are low.

Just my early thoughts.  Lots of time to watch and track though.  Watch the trends especially in the AI guidance as we go through the next few days.

[NEG NAO]

3 minutes ago, Stormlover74 said:

Cmc might be close

I wouldn't want to be exactly in the bullseye this far out anyways - and even the northern edge will have higher than normal snowfall ratio's.

[Franklin0529]

CMC is almost a nuke. 

[Stormlover74]

1 minute ago, Franklin0529 said:

CMC is almost a nuke. 

Crushes mid atlantic with alot of snow and ice. Moderate hit up here at least

Edit big hit for us

[Franklin0529]

Just now, Stormlover74 said:

Crushes mid atlantic with alot of snow and ice. Moderate hit up here. 

Yup. It definitely came north though. I like where we are right now. Especially since alot of times the strength of the high is over done

[WeatherGeek2025]

5 minutes ago, SHELEG said:

Seems like the AI GFS is trending more towards suppression. 

i don't think so, it's wobbling within 50-75 miles the last two runs. It's way more consistent than any other model at this point. I'm going with it until proven wrong

[Stormlover74]

Just keeps going...Saturday night thru sunday night

[Franklin0529]

2 minutes ago, Stormlover74 said:

Crushes mid atlantic with alot of snow and ice. Moderate hit up here at least

Edit big hit for us

CMC is a foot in the city more south 

[NEG NAO]

2 minutes ago, Franklin0529 said:

CMC is almost a nuke. 

I am showing 24hr  liquid because of higher ratio's and its 100% snow - do the fiquring for your location at say 10:1 15:1 or 20:1 ?

[Franklin0529]

Just now, NEG NAO said:

I am showing 24hr  liquid because of higher ratio's and its 100% snow - do the fiquring for your location at say 10:1 15:1 or 20:1 ?

Yea it's a foot in city more as you go south 

[Jt17]

Seems like the AI GFS is trending more towards suppression. 

1 run is not a trend


.

[SACRUS]

8 minutes ago, MANDA said:

How much snow will it take this coming weekend to make you happy?

1-3"

2-4"

3-6"

4-8"

6-10"

8-14"

14"+

 

For me I'd be thrilled with 6-10", anything less would be a disappointment.  I'm prepared to be disappointed and my expectations are low.

Just my early thoughts.  Lots of time to watch and track though.  Watch the trends especially in the AI guidance as we go through the next few days.

 

im torn between anything or 14+ / go big or go home.

[SACRUS]

1 minute ago, Jt17 said:

1 run is not a trend


.

Suspect we'll have the typical wax on / wax off windshield wiper suprssed / crushed run to run or model to model through Wed AM before honing in.

[Stormlover74]

Cmc is snow with temps of 5 to 10 sunday morning

[Yanksfan]

1 minute ago, Stormlover74 said:

Cmc is snow with temps of 5 to 10 sunday morning

If that’s the case snow amounts would be 75-100% higher than what’s depicted. 

[milleand]

thought this was a good read