burgertime

Not too bad..

Looking at it you can't help but wishcast into phasing sooner. It's so close to looking spectacular for all of you in ENC. Rooting it keeps inching closer to something bigger.

That being said I wouldn't expect so much a "northwest trend" for our low as much as a northwest trend with relation to precip field. Seen this a lot where we get energy overhead and the low associated with it ends up producing more moisture than models can pick up on. Should be a fun little storm if we can keep up these trends. Especially with such cold air aloft.

Everything is going to depend on when those two pieces of energy phase. Also notice the energy in the north swooping down. If that could come in a little faster could help lift this more. I do like that vort energy going right over NC. Again that should help wring out what moisture is there for folks further west in NC.

12z GFS is looking better. At 500mb it's better phased. Need to keep watching these last minute changes.

Can't recall that. Do remember a storm I think in 2011 maybe that CLT was under heavy snow warnings and it ended up being all rain. Now that was a disaster.

March 2009 comes to mind for me. ULL was all over the place and then at the last second folks along I-85 cashed in.

But do they work on government contracts? By the way as global warming becomes more and more of an issue weather models are going to be more and more important. That should bring budgets but it will also bring a lot of secrecy. The government isn't just going to hire any contractor to work on NSA servers for instance. Also congress has proven over and over again that when it comes to NOAA they will not approve anything unless they are forced to because of some catastrophic event.

Yea this isn't a bad look and hopefully you can cash in. In fact I think for most of NC it wouldn't be too bad either. As @NorthHillsWx said this would be very powdery snow so snow ratios wouldn't be great but for most what falls would stick.

Congrats outerbanks!

This is a weird run. Brings back moisture at 57 largely due to a strong vort overhead. Would likely wring out all the moisture. This honestly isn't the worst solution. Especially compared to the NAM run.

Out to 48 GFS is drier than the 12z run. It does have a little bit stronger energy at 500mb so it's still trying to get it there for NC. Better than the NAM for sure.

18z GFS is trying out to 39. Looks more like the 12z solution so far.

In a perfect world yes. But you're dealing with an agency that has already been gutted. Plus because these are either run or partnered with governments you can't just get contracts over night etc.. How does NOAA go about using offshore contractors? Can they trust Russian developers? What about Chinese? What about Indian? This is very very complicated even outside of the development and machine learning aspect.

It 1000% is.

It must be exhausting being a voice of reason

I think it might be time for him to walk the plank to a good ol' fashioned Keelhauling.

+500k ...how can NOAA even attempt to match that? They only got funds for the new GFS super computers due to super storm Sandy. Also machine learning on ads is vastly different than models that use ridiculously sophisticated math and massive data input (though it may be similar to the amount of data from ads?). Again you may be 100% right just when I was on a project to do AI it wasn't that simple. By the way there is an interesting article here which may back you up. https://venturebeat.com/2021/09/29/deepmind-claims-its-ai-weather-forecasting-model-beats-conventional-models/#:~:text=DeepMind claims its AI weather forecasting model beats conventional models,-Kyle Wiggers%40Kyle_L_Wiggers&text=In a paper published in,usefulness in 88% of cases.

If you would bother to learn anything you'd know the models are a guide not a map. For 10 years of being on the board you should be able to look at the models, remember how storms have played out in the past and then decide for yourself what is likely to happen. Not live and die by each model run FFS.

Not sure what field you're in but it's really not that easy. I had to help with a simple AI project with a LOT of budget. First you have to find the people which is difficult. Then there is a lot of trail and error. Simple things like finding discrepancies in finance programs can take a year to implement. Just not sure we're there yet for weather models... not to mention quantum computing is still very much in it's early years. But could be wrong and maybe you have more experience.

lol...damn looks like I came back just in time. At least you all have a cliff to jump from. Here I'm just always looking up at the cliff. I've seen 2 good snow storms in almost 7 years.

Also near the end it starts blowing that low up. This is a plausible solution but it doesn't mean it is THE solution. Start the cliff diving if all the models converge around 12z Thursday.

Yea still looks like it could be a fun one for you guys. Also this is just one run....

Not to get too far off here but how would one really implement it? Seems like it would be very tough and extremely costly. I'm sure these huge super computers of the globals already use some sort of AI or advance learning. We're dealing with some insane computations. It's probably something that takes years to really implement with such focused AI.