tcumulus

Paper: https://storage.googleapis.com/deepmind-media/papers/weather...

TLDR: the input data for the model now also includes real-time observations (satellite and weather stations) on top of the typical (re)analysis data, improving model resolution, run frequency and timestep frequency.

The Netherlands might not have the most extensive or fast rail network, but it's frequencies are pretty much unbeatable. In some places it runs more as a metro network than a heavy rail one. This visualisation shows that nicely!

It's not comprehensive. More than 75% of the passenger lines are missing in Belgium. I imagine this is the same for many other countries, especially the ones with a lot of passenger service.

Indeed, you can imagine this as some sort of advanced physics-based interpolation of various measurements (land stations, satellite data, ...) to fill in every cell in a latitude-longitude grid. This is not only used for ERA5 (training data for the models), but also to determine the initial conditions for every grid cell which are used to roll out the forecast. So AI weather models depend greatly on the NWP/physics used in for reanalysis and initial conditions. That being said, there is also research being conducted in training models straight from the raw data (weather stations, satellite, ...), thus bypassing the "interpolation" step.

Everything in AI seems to be focused on LLMs lately. But in my opinion, powerful problem-specific models like this are even more interesting. The SOTA AI models used in weather forecasting are already outperforming the classic NWP models while being orders of magnitude more efficient (inference). Most are based on multi scale (hierarchical) Graph Neural Networks, an architecture which is not often talked about. The original Graphcast paper is worth a read if you think this is interesting: https://arxiv.org/abs/2212.12794

Well if you count every minor service outage which maybe 0.1% of the users are non-critically affected by, you quickly get to 0.6%. So, this doesn't really tell you anything.

New book by Eric Riess (writer of the Lean Startup) came out today. Haven't had the chance to read it yet, but certainly sounds interesting.

Excerpt from the Amazon page: "In Incorruptible, Ries reveals the hidden forces that cause even great organizations to drift from their values and shows how to design businesses that can withstand that pressure. Drawing on two decades of work with founders, CEOs, and investors around the world, offers the blueprint for “mission-locked” organizations that can grow, prosper, and endure without losing their soul."

Very interesting, but sounds like an extra complication to use binary search on time to find the right position of the sun, when you can just directly calculate this, eg. using the formulas in here: https://gml.noaa.gov/grad/solcalc/solareqns.PDF

With captions :D

I've worked a lot with weather data in the past (and I still am), and I have to appreciate all the work that went into this. Weather model data is notoriously messy with many different formats and standards, and then I'm not even talking about radar data, etc. Probably when you've got this all abstracted away behind an API it is easier to build such a powerful application as this.

Depends on which model. Only really the ECMWF weather model is not fully free. The German, French, Dutch, ... models are all free (regional and global models). Of course, these global models are generally less accurate than ECMWF, still ECMWF has a lot of free data available too. US models are also freely available, and quite easy to work with (as opposed to some European ones).

Wow, looks like a very cool project! Feel free to experiment with the Sunsethue API! Send me an email if you'd need a higher quota to play around with.

I know that this is shameless self-promotion, but maybe this could interest you: https://sunsethue.com/ :)

For the ones who might be interested, Yr.no uses the ECMWF (European weather model) as their main data source. This model scores the best on benchmarks of the global weather models (available for the whole world), but AI models are catching up on some parameters. Still, there are local weather models available with a much higher resolution (these are regional and only have forecasts up to a couple days). Examples are ICON-D2, Arome, Harmonie for parts of Europe, and HRRR for the US. I'm not sure which apps use these models though.

Some interesting points: "Removing cross-border bottlenecks through binding timelines to be set by 2027 and the identification of options for higher speeds, including well-above 250 km/h when economically viable."

"A 2026 proposal will aim to improve cross-border rail ticketing and booking systems, making it easier for passengers to plan and purchase seamless cross-border journeys, with better access to passenger rights protection when using multiple operators."

"Removing entry barriers for new high-speed operators. Better coordination of track capacity, fair track access charges, and non-discriminatory access to service facilities will make it easier for new companies to offer high-speed rail services, boosting competition and making high-speed rail more affordable."

Well, at least I now know that my Belgian university's Blackboard environment is running on AWS :)

There even is a section on Chatelet Les Halles if you scroll down. Insane station.

My bad, should have indeed used AMOC in the title. Translated the titles of the Flemish and Dutch public broadcasters which used the word "golfstroom" in their titles.

It may take long to significantly weaken, the article also states that effects of a weakening AMOC can occur much sooner than that.

Should have used AMOC indeed, in Dutch media the word "golfstroom" was used, and I translated it without putting too much thought into it.