This seems to imply that there isn't any high-resolution precipitation data available that could provide these "minute-by-minute" forecasts, but that isn't true. The National Weather Service provides several radar products that give data with resolutions in the range of 500 m using their NEXRAD technology[0]. This allows for some pretty good estimates of when precipitation will start and end over the next hour or so. This kind of forecast product is called a precipitation nowcast. Other nations have similar systems.
If you use the NOAA desktop tool[1] to view the data from NEXRAD stations, you can compare to services like DarkSky and see that they are very likely using it without much editing.
The simplest nowcasts use optical flow techniques rather than meteorological modelling. On short time scales (less than an hour), these methods can give passable results. I built a tool[2] that pulls this NWS data from their Web server and gives you a nowcast.
Moreover, I've used minute-by-minute forecasts myself, and (at least where I lived at the time) they were quite accurate. My use case was "where is a 30 minute gap when I can walk home without getting soaked", and I never once got soaked. So much of the OP falls into the category of things-I-know-to-be-false-from-experience.
The article really has a strong vibe of "algorithms are faulty, we need humans in the loop to make sure they're behaving well!", with a hidden assumption of "humans are less faulty than algorithms". That's an empirical assertion to be determined on a domain-by-domain basis. It's certainly true that having a human in the loop leads to worse outcomes in chess (unless the human has enough modesty to just not do anything). The same is increasingly true of other domains as well.
Perhaps someday, incorrect, largely content-free FUD articles about how algorithms suck will themselves be written entirely by algorithms.
This is pushing way too many of my buttons, so I'll just close by pointing out (on the other side of the apps/humans scale) that a substantial fraction of the time, when I check the weather on NWS, it says something like "Today's high: 56; current temperature: 58". I certainly hope that a human in the loop would fix that problem.
> It's certainly true that having a human in the loop leads to worse outcomes in chess (unless the human has enough modesty to just not do anything).
No, this is actually totally false. There is a world championship in computer-aided correspondence chess [1], and you won't get anywhere near the top ranks by having "enough modesty to just not do anything."
I think that strengthens the point, don't you? Deep blue could beat humans a long time ago, and it's still the case that computers don't need humans to play chess, and play it better than humans do.
> and it's still the case that computers don't need humans to play chess,
Sure, I guess
> and play it better than humans do.
In the sense that they can beat humans in a 1v1, yes.
But none of that is relevant to the original claim, which is that a human in the loop makes a computer play worse--i.e., that human+computer is worse than computer alone. This claim is false, as the ICCF championship demonstrates each year.
I can’t comment on America, but when I lived in Amsterdam everyone I knew used an app called Buienradar for this exact use case. The accuracy was astonishing.
I hadn't tested it before, but yes, it looks like there's coverage for some major Canadian cities near the border, including Montreal, Ottawa, Toronto, and Vancouver. You can check your locations of interest on this map[0] (requires JS). Just click "Maximum Radar Ranges" on the left and see if you fall within the coverage circles.
As I write this, there's some light precipitation just north of Toronto, and threecast seems to give reasonable output there. Note that the radar coverage areas aren't always perfect circles because terrain can block the radar beam.
Canada may have a similar system with better coverage, but I'm not sure.
I'm not a huge enthusiast for home automation (we don't use any voice assistants), but we have a few Mirabella IoT light globes that can turn on/off on a schedule or in response to weather conditions.
Mainly I just have lights turn on before sunset, which works fine, but one of the programs I set up was for some indoor lights to turn on when it rains, as it usually gets quite gloomy here during rain.
It's quite common for that program to activate and turn the lights on when it's hot and sunny with no rain or clouds anywhere nearby.
I gather it must be because they're using this kind of weather forecast data and not doing any live/recent updating.
Get an ambient light sensor and program your automation to light the lights when it's actually dark and gloomy, not when it's gloomy at, say, the nearest airport or where else they like to stick their measurement equipment.
Take this with a grain of salt, but I’ve heard that there are stupid legal reasons (lobbied for by the private sector) why government agencies such as the NOAA are prohibited from offering their own apps or services. If that’s true then I think it might be worth directing your anger there first and foremost.
Accuweather (which relies heavily on the national weather service data for its forecasts) lobbied for a bill in 2005 to prevent the weather service to provide data directly to people; the bill failed.
Then during the Trump presidency the former Accuweather CEO (whose family still owns the company) was nominated undersecretary of the weather service, but he failed the confirmation hearings.
NOAA weather, on the web, has always worked for me. I've never used an app. The website is slightly klunky, but works. I get around town by bike, so it's helpful to have some indication of what I'm heading into.
> Basically, there’s no reliable way for users to get vetted weather information on their phones.
Browsers should work, right? I check the (Australian) Bureau of Meteorology website all the time on my phone. We use it to plan family trips and when to do the washing.
If you use the NOAA desktop tool[1] to view the data from NEXRAD stations, you can compare to services like DarkSky and see that they are very likely using it without much editing.
The simplest nowcasts use optical flow techniques rather than meteorological modelling. On short time scales (less than an hour), these methods can give passable results. I built a tool[2] that pulls this NWS data from their Web server and gives you a nowcast.
[0]: https://en.wikipedia.org/wiki/Nexrad#Super_resolution
[1]: https://www.ncdc.noaa.gov/wct/
[2]: https://github.com/bmgxyz/threecast