Top all-time · #8201
jackadamblog
Personal blog · jackadam.github.ioprogramming
jackadamblog is a personal blog at jackadam.github.io about programming. Since 2016, 10 different Hacker News readers have linked it 11 times, most often “How Dark Sky, a weather prediction app, works”. The last post was in 2011, but the archive is still widely read.
Too few sampled comments (7) to say how often HN recommends it.?
Why HN links it
HN readers link this 2011 post by a Dark Sky developer to explain how the app's forecasts worked, including radar data, its ML/statistical approach, and on-device computer vision with velocity images.
Summarised by Claude from a sample of 7 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- How Dark Sky, a weather prediction app, works5 people · 6 mentions · first linked 2016-02-22
- How Dark Sky Works (2011)3 people · 3 mentions · first linked 2022-06-07
What Hacker News says?
Really recommend reading http://jackadam.github.io/2011/how-dark-sky-works/ and https://en.wikipedia.org/wiki/Weather_radar#How_a_weather_ra... to get something of a handle on it For one thing, the resolution of radar is finite where one "pixel" (gate) is quite large, and everything under it is assumed to be constant. Precipitation at a spot on the ground is the result of everything happening from sea level up 40,00…
Comment linking /2011/how-dark-sky-works/
on “Apple acquires Dark Sky”Submitted How Dark Sky, a weather prediction app, works as a story · 6 points
HN discussionhttp://jackadam.github.io/2011/how-dark-sky-works/ They used an ML/statistical approach to forecasting, rather than physical modeling. They had some secret sauce in doing fast ML on phones, before libraries like CoreML existed.
Comment linking /2011/how-dark-sky-works/
on “Apple acquires Dark Sky”Submitted How Dark Sky Works (2011) as a story · 4 points
HN discussionhere's an explanation of their 'computer vision approach' to local weather forecasts: https://jackadam.github.io/2011/how-dark-sky-works/ "We create a 3-channel image where the red channel represents velocity in the x-direction, the blue channel represents velocity in the y-direction, and the green channel represents change in storm intensity" and then use computer vision techniques to predict what happens next post…
Comment linking /2011/how-dark-sky-works/
on “WeatherNext 3”Submitted Tiny Face as a story · 2 points
HN discussionThe data is public and comes from NOAA but they are doing their own forecasting. Here is a blog post from one of the devs about their process (2011): http://jackadam.github.io/2011/how-dark-sky-works/
Comment linking /2011/how-dark-sky-works/
on “Dark Sky iOS app will no longer work from Dec 31”Submitted How Dark Sky Works (2011) as a story · 1 points
HN discussionIt's not exactly parallel processing, but the Dark Sky app already does its forecasting calculations on the iPhone: http://jackadam.github.io/2011/how-dark-sky-works/ > The reason we encode velocity data as an image is so we can pass it off to the GPU on the iPhone and iPad. Both the storm prediction and the smooth animations are calculated on the device itself, rather than the server, and all the magic happens dire…
Comment linking /2011/how-dark-sky-works/
on “Supercomputer quietly puts U.S. weather resources back on top”The app update will likely be included with iOS 16. I doubt that. They've probably been working on international support. DarkSky's original API primarily used NOAA data, which would explain why it's not as accurate outside of the U.S. if it still uses that This old blog post from one of the creators discusses it: https://jackadam.github.io/2011/how-dark-sky-works/
Comment linking /2011/how-dark-sky-works/
on “Dark Sky Has a New Home (2020)”I found this old blog article at a high level on how Dark Sky works... about 12 years old now. I always loved this app and was kind of sad when Apple acquired them... but to have Apple come in and just buy your app out is probably a great feeling for the founders :) Anyhow, here's the url: https://jackadam.github.io/2011/how-dark-sky-works
Comment linking /2011/how-dark-sky-works
on “Pirate Weather: A Free, Open, and Documented Forecast API”
