Comment by cryptoz
3 years ago
Another Dark Sky thread, another opportunity to ask the community if anyone knows about Apple doing research with the barometers in their phones. Dark Sky claimed they 'did' but they never expanded on what that meant for them. Did they actually use the barometer data collected from the app? Or did it just get sent to /dev/null as I suspect?
And if Apple bought that code, did they use it themselves? Is Apple doing anything to improve weather forecast accuracy in the main weather models by running data assimilation on cleaned barometer data?
If not it is such a wasted opportunity that I just get so angry about. If so....please tell us more.
I suspect barometer data from phones would be junk unless you can correlate it with other data. The phone’s barometer is sensitive enough to detect the pressure difference (altitude change) of a few cm. That makes it extremely noisy for detecting slow moving metrics like the weather.
Yes, but, significant work was done at an academic level between 2011 and 2017, researchers at universities, grad student projects, etc, that resulted in usable data being extracted. I worked on this problem for ~10 years off and on. It is absolutely doable.
Especially since you don't actually _need_ raw pressure data to be useful. Pressure rate of change over time is still useful and produces improved accuracy in some local forecasts.
But not only that, the researchers at UW under Cliff Mass found that you can do on-device ML to clean the quality of the data, remove errors, and live-adjust to MSLP on-device, without even needing the dense network of sensors nearby for error correction.
It's 100% doable, but it just takes some hard science and effort.
> That makes it extremely noisy for detecting slow moving metrics like the weather
Yes, but, the noise problem was solved half a decade ago.
Huh. This is why I love HN. I didn’t know about that but looking up these papers to see if this approach would be useful to some other stuff I’m working on with similar-ish noise problems that conventional algorithms aren’t working for.
1 reply →
Not really?
A 10cm change in elevation at sea level results in a 0.0001% change in atmospheric pressure [0]. On the other hand, weather-relevant pressure changes operate on scales of ~0.1% [1]. By my math, a small weather-relevant pressure change would be equivalent of someone changing their elevation by 100 meters.
Additionally, on a modern phone the barometric data can be adjusted against the accelerometer and GPS to mitigate changes in elevation (especially relative to, as you say, a slow-moving measurement).
[0] https://www.mide.com/air-pressure-at-altitude-calculator [1] https://barometricpressure.app/content/understanding-high-lo...
Why say "not really" when you can simply test this yourself with a sensor dumping app. Planes have been using this technology for about a hundred years with accuracy down to the foot.
It isn't the GPS or position of the device you need to correlate, its trustworthy data. Is the device on an elevator, or did the pressure actually drop?