How Dark Sky Works (Weather prediction using computer vision)

Re:How Dark Sky Works (Weather prediction using computer vis... by thegrossman on Wednesday November 09, 2011 @09:51AM (#3215615)

As promised in an earlier thread (http://news.ycombinator.com/item?id=3186978), I've written a blog post describing how Dark Sky operates under the hood.

[ Parent | on HN ]

Re:How Dark Sky Works (Weather prediction using computer vis... by lsllc on Wednesday November 09, 2011 @10:39AM (#3215874)

Fantastic, can't wait to get the app! I've always wondered about taking weather radar over time and creating a "heat map" of rainfall to prove that during the summer the t-storms seem to split in half, pass us by and rejoin, leaving me to go out and have to water the lawn while ALL the adjoining towns get inches of rain!

[ Parent | on HN ]

Re:How Dark Sky Works (Weather prediction using computer vis... by maxerickson on Wednesday November 09, 2011 @10:32AM (#3215828)

Have you compared the results of your computer vision approach to the velocity data provided by the NWS?

[ Parent | on HN ]

Re:How Dark Sky Works (Weather prediction using computer vis... by thegrossman on Wednesday November 09, 2011 @12:04PM (#3216293)

You mean the wind velocity data directly from the doppler radar? Yeah... it turns out that wind velocity isn't super accurate for predicting where the storm is going.

If you watch a storm building up over time, you'll often see it staying in one place or even moving against the wind. Almost like a traffic jam on a highway.

So that's why we take a computer vision approach rather than basing it on wind-speed.

[ Parent | on HN ]