As a sailor I’m really into getting a good weather prediction and most of the models are quite inaccurate. I learned on here about an ML based weather model startup that posted predictions on their website called Atmo.AI (edited) that was mind blowingly accurate and had incredible spacial resolution- it could accurately predict, e.g. the wind shadow behind islands, something none of the mainstream weather models even come close to doing. I used it everyday and it was almost always dead right at predicting wind speeds in almost any specific spot. I won a lot of sailboat races with it. I hope this tech gets taken up by NOAA, or other major weather predictors.
Anyone on here know what happened to Atmo and if the tech is ever going to come back so people can use it? It's a travesty that this tech exists but isn't being used- a lot of lives would be saved if NOAA were using this already existing technology.
Edit: Apparently as another poster pointed out I had just forgotten the correct name of it, and it is still around. I edited this to reflect that.
Weird, as a sailor I find GFS to be highly accurate taking into account an understanding of what it does, what it does not do, and how to interpret it.
GFS does not account for sea/shore breeze for instance, so if you're in an area where that may occur, then you will have to apply your own judgement about the conditions.
Now, if you were to feed weather station readings into an ML model, would the ML model be better at predicting the weather? Well I think it'd be better at predicting the things that the weather model does not model in the locality of the weather station, sure.
I've found GFS fine for that, but it is one of the worst models for inland or near shore sailing, even most of the other popular models that you can access from sailing weather apps like NAM and ECMWF are much more accurate in specific locations with unique geography. The resolution is just too low to account for any interacting geography with GFS. It gives the same forecast over huge areas with radically different conditions.
I don't use GFS just by looking at the wind layer though. Wind layer forecasts do not include terrain or local effects as you noted. But the necessary info is in the forecast and is accurate.
For instance, in the great lakes we tend to have large diurnal temperature swings and therefore strong sea/shore breezes. If the model is forecasting big temperature changes and an anticyclone with low wind-layer forecast, this is ripe for strong sea/shore breezes.
The biggest hazard we have in the great lakes is convective storms (squalls). They do not show up in forecasts because convective cells are very small. However, The GFS gribs do have pressure forecasts, and perception, and most importantly CAPE and CIN forecast layers. Combined with WPC synaptic charts you have the info needed to determine if 1) convective storms are likely to occur and 2) if they do occur, the probability that they will be severe.
The GFS is a coarser model which covers the entire globe, so while the overall situation at the synoptic scale will tend be modeled quite well (at least inside of a few days into the future), the resolution of smaller-scale weather phenomena taking into account local factors just isn't going to be there.
For something maybe more useful on the local scale, you can also look at a model like the HRRR (which I believe does take into account the terrain and other local effects from things like larger bodies of water). While this model only really covers the conterminous United States and southern Canada, I've generally found it good for showing the shorter-term, local weather details, including forecasting convective storms and winds on and around the Great Lakes.
Thanks, I think I need to spend some more time studying meteorology so I can also better interpret how the data predicts actual hazards, as you are doing. I'm not even familiar with many of the acronyms you mention. I am simply comparing how well the predicted wind speeds are reflected in real life, in specific places where I am potentially in the wind shadow of relatively small hills, islands, etc. It is the flow around these objects that requires a high resolution model, as small shifts in wind direction make the wind shadows shift and change in size a lot. The actual overall prevailing conditions are so identical here from day to day in Northern California, there is hardly a need for large scale models unless the rare storm comes through.
I have noticed that where I am, the inland/offshore temperature differential is alone a pretty good predictor of overall wind speeds near the coast, not accounting for geography.
Thanks, I'll check it out! I've read "High Performance Sailing" by Frank Bethwaite, who was a sailing meteorologist and covers some things- but it is more focused on extreme micro-prediction.
Many companies offer customized, high resolution weather simulations that resolve those sorts of features. It's purely a cost vs value proposition - only a tiny sliver of users actually need this sort of spatial resolution, and typically over a very small area, so there is no reason for a global weather forecast model to be cranked up to it.
> Anyone on here know what happened to Atmo and if the tech is ever going to come back so people can use it? It's a travesty that this tech exists but isn't being used- a lot of lives would be saved if NOAA were using this already existing technology.
They're a thriving start-up as far as I've heard. Weather is a tough industry. Given that hourly-refreshing, high-resolution forecasts are freely available already from NOAA, I doubt that proprietary forecasts like these really move the needle in terms of protecting public life / property.
For sailboat racing I care about “micrometeorology” - e.g. things like which of two slightly different courses only 1/10th of a mile apart to the same destination will be windier 45 minutes from now?
Amazingly, these models are starting to be able to actually predict that, but I agree that not a lot of people care about that level of detail.
It depends on the type of sailing and where the race will be taking you. The participants in a race such as the Vendée Globe [0] are almost certainly using the likes of synoptic scale models like the GFS and ECMWF to plan their routes.
Yes for the vast majority, the immediate weather conditions can be ascertained by looking out the window.
I'd like more accuracy for the next 1-5 days as that's the time horizion I tend to use to plan to work outside on various projects, and am often frustrated by rain when the prior day's forecast didn't anticipate any. Or the opposite.
Do you mean atmo.ai? Atmos.ai seems to be something very different: "Atmos AI streamlines the Carbon Accounting, GHG Emissions, and Environmental, Social, and Governance (ESG) reporting processes for companies of all shapes and sizes."
Ok, I am embarrassed, I simply forgot the name of it, and thought it had disappeared when I tried to find it again. Seems it is still alive and well. I swear this isn't viral marketing for them, I was legitimately confused.
I edited my post above to use the correct name, but realize it doesn't make too much sense anymore.
I've met the Atmo founders a few times, very nice people and the company seems to be doing well. The tech is definitely getting used, but I think they're working with goverments more than end users
How do I use Atmo for locations other than the bay area demo linked on their website? I tried URL tweaking without much luck. I have a friend who does a lot of sailing races who would love this!
I don't know... I am only using it in the Bay Area. I noticed there are coordinates in the URL that one could try changing, but it is possible they are only running the model for the Bay Area right now?
I've also wondered if they have hand tuned the model to match local observations and geography in the Bay Area, and if it could generally apply elsewhere without a lot of manual work? In particular, it is mind blowingly accurate at getting the wind shadow around Angel Island, which is a complex thing to do, because it involves ocean wind that divides into at least 3 separate streams, and then recombines in complex ways. No other model I've seen can predict which of those 3 stream will dominate, but they usually can.
I've noticed the same with e.g. car navigation/map software- it generally works much better in the Bay Area where the developers and companies making them actually live, than elsewhere. I could imagine that in both cases the developers use it themselves in the place they live, and investigate/fix local errors themselves.
I did try altering the URL and didn't have much luck! It would make a lot of sense if Atmo was only running the model for a smaller area to keep costs from running up. My friend races in SoCal (the Channel Islands and Catalina are common destinations) and the wind shadows and streams are complicated there too.
Your observation about navigation software is accurate in my experience too :)
I couldn’t make much of atmo given the SF constraint, but I use the UK2 model for UK forecasts and it seems to be a similar level of detail and does very well taking topographical and micro weather nuance into account. Depending on your location you might find an equivalent short range model
Anyone on here know what happened to Atmo and if the tech is ever going to come back so people can use it? It's a travesty that this tech exists but isn't being used- a lot of lives would be saved if NOAA were using this already existing technology.
Edit: Apparently as another poster pointed out I had just forgotten the correct name of it, and it is still around. I edited this to reflect that.