There's another tool which seemed to coordinate with the launch of WeatherNext 3 last week, the "Operational WeatehrBench" from Brightband -> https://owb.brightband.com/
It features a couple of AI and NWP model forecasts for comparison.
There is little to no evidence that the current degradation of the US upper air backbone is regularly contributing to degraded forecast skill. That might change as we head into the more active northern hemisphere winter.
They are, as are plenty of folks in the community. I expect to see some good talks on this at the AMS Annual Meeting in January, based solely on my own peer network and what colleagues have mentioned they're working on.
> I've heard some commentary in the past that 5G interferes with data measurements heavily used for weather forecasts (something about satellite measurements?)
The short version of the "spectrum" issue is that 5G is being allocated in bands very close to the microwave spectra where atmospheric water vapor emits. A bevy of public and commercial satellites in low-Earth orbit passively monitor these microwave spectra and produce extremely important information that is assimilated into numerical weather models.
The federal government sets limits on "out-of-band emissions" for operators emitting in the allocated 5G spectra. These emissions can bleed over into the microwave water vapor bands, creating noise that masks the natural presence of water vapor. The limits for this out-of-band emission is on the order of ~10-20 dB, and there's some work in the atmospheric science literature suggesting that this is enough to confound certain water vapor retrievals. That basically means we lose these observations that help constrain the forecast.
There isn't much indication that this is a serious issue in day-to-day meteorology at the moment. But it's an issue which will be significantly more difficult to unroll and claw back than to simply protect key spectra in the first place.
WeatherNext 2 was based on the FGN architecture described in [1]. It was explicitly designed and trained to produce ensemble forecasts (it was trained in such a way that the output ensemble optimized a CRPS metrics). In fact, it was a set of 4 different model weights, each of which was seeded with a random noise vector to produce an array of 16 forecasts for a total of 64 ensemble members. WeatherNext 3 trimmed that down from 4 to 2 separate model weights to use.
> Problem is that the WN3 grid is still quite rough (5km) - but a that's a brutal improvement for many places compared to many other global models.
That's a pretty apples-and-oranges comparison. One would almost always use a high-resolution regional model if you needed certain details for different forecasting applications like renewable energy.
It's also worth noting that the 5km outputs are from a model decoder head that was trained against temperature and dewpoint at surface stations. According to the Rasp et al (2026) preprint, this head was designed for continuous sampling; the choice of a 5km grid is arbitrary. What we don't actually know is how well the model handles shocks like a frontal passage or impacts from things like outflow from storms - or even evaporative cooling from precipitation. We are limited to the output that DeepMind publishes; we can't run the model and stress test these things on our own.
That's all a long way to say that the 5km resolution is (a) limited to temperature fields, and (b) we don't know if the "additional" resolution has any impact whatsoever on the phenomena that one would typically use a mesoscale-resolving forecast for.
I wish there was a way that your comment could be pinned.
The context is so important here and radically re-frames the impact of GDM's results. Folks need to understand that with modern forecasting tools, we anticipate tropical cyclones to develop 5-10 days before they ever threaten landfall. The "2-day" vs "3-day" improvement in forecast skill is better interpreted as a modest reduction in forecast uncertainty - the "cone" on the hurricane track map gets a little narrower.
It's not like there's a "literal extra day" of preparation time for folks who may be impacted by the storm. They get the same amount of time they always have. Nothing actually changes on-the-ground for really any consumer of hurricane forecast data anywhere in the world.
And that's not a sleight against GDM. It's just a simple statement of how good contemporary weather forecasting is, and how good it was before AI forecast models came onto the scene some 5 years ago.
It features a couple of AI and NWP model forecasts for comparison.
reply