Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

WeatherKit

developer.apple.com

Post reply on HN
Print view View original

181–190 of 203 posts

Re: WeatherKit

#181

Post by mh- »

calsy wrote: post #180
mh- wrote: post #179

Earlier quoted context omitted.

I'm not sure I understand the 2nd part of your comment, but: from first principles, coming up with an all-purpose algorithm or generally-applicable model is going to be harder than making it work for a single "use case". for weather patterns, some parts of the country (speaking of the US here since that's where I'm familiar with) have fairly predictable cold front movements from west to east. others have ocean intera…

Well the weather by nature is a chaotic mess of pressure systems and weather patterns, a major cause being the junction between the hot and cold temperatures of the 2 hemispheres, no? I say 'washing machine' as it is a swirling mass of unpredictability. Yes there are obvious patterns that follow the seasons, but forecasts are required to be much more accurate than predicting the weather by patterns of the season. The…

Thanks for clarifying. And I agree with everything you've written. I'm (clearly!) not an expert. Would be fun to see this done as a challenge similar to the old Netflix recommendations ML challenges.

Re: WeatherKit

#182

Post by calsy »

mh- wrote: post #181
calsy wrote: post #180

Earlier quoted context omitted.

Well the weather by nature is a chaotic mess of pressure systems and weather patterns, a major cause being the junction between the hot and cold temperatures of the 2 hemispheres, no? I say 'washing machine' as it is a swirling mass of unpredictability. Yes there are obvious patterns that follow the seasons, but forecasts are required to be much more accurate than predicting the weather by patterns of the season. The…

Thanks for clarifying. And I agree with everything you've written. I'm (clearly!) not an expert. Would be fun to see this done as a challenge similar to the old Netflix recommendations ML challenges.

I just wanted to know if I was missing something, Maybe there is some way of simplify forecasts for local areas that I'm not aware of. I would be interested to know.

Re: WeatherKit

#183

Post by mh- »

calsy wrote: post #182
mh- wrote: post #181

Earlier quoted context omitted.

Thanks for clarifying. And I agree with everything you've written. I'm (clearly!) not an expert. Would be fun to see this done as a challenge similar to the old Netflix recommendations ML challenges.

I just wanted to know if I was missing something, Maybe there is some way of simplify forecasts for local areas that I'm not aware of. I would be interested to know.

I expect there is if you constrain what we mean by "forecasts".

Like, for my purposes, I'd simply like to know the temperature trend for the next 3-5 days. Will each day's high be hotter or cooler than the previous?

Bonus points: what's the high temperature for the next 3 days (within say, 3°F).

Anecdotally, using these standards, this seems to be consistently wrong where I live for much of the summer. I don't pay attention in the other seasons as the weather is much milder.

Re: WeatherKit

#184

Post by selcuka »

gnicholas wrote: post #164
oefrha wrote: post #161

Earlier quoted context omitted.

You say you’re trying to build a more accurate prediction algorithm to beat meteorologists. Given that goal, you should probably look to acquire a supercomputer first; tech stack wouldn’t be a concern until then.

For our local area, it was actually trivial to develop a better weather prediction algorithm. We're not looking to build something for the whole world, which would be very difficult. At this point, I'm just trying to sort out the tech stack for the website, now that we have our prediction algorithm figured out. We'll of course optimize it over time, but even our v1 blows weather.com out of the water.

What technology did you use to implement your prediction algorithm? It might make sense to use the same language to have less moving parts. If you used Python, for example, you may consider using either Django or Flask for the web site.

Re: WeatherKit

#185

Post by gnicholas »

selcuka wrote: post #184
gnicholas wrote: post #164

Earlier quoted context omitted.

For our local area, it was actually trivial to develop a better weather prediction algorithm. We're not looking to build something for the whole world, which would be very difficult. At this point, I'm just trying to sort out the tech stack for the website, now that we have our prediction algorithm figured out. We'll of course optimize it over time, but even our v1 blows weather.com out of the water.

What technology did you use to implement your prediction algorithm? It might make sense to use the same language to have less moving parts. If you used Python, for example, you may consider using either Django or Flask for the web site.

Thanks, that's helpful! The algorithm is still in a spreadsheet at this point, so it's up for grabs right now.

Re: WeatherKit

#186

Post by gnicholas »

calsy wrote: post #178
gnicholas wrote: post #164

Earlier quoted context omitted.

For our local area, it was actually trivial to develop a better weather prediction algorithm. We're not looking to build something for the whole world, which would be very difficult. At this point, I'm just trying to sort out the tech stack for the website, now that we have our prediction algorithm figured out. We'll of course optimize it over time, but even our v1 blows weather.com out of the water.

Im interested to know how weather forecasts can be trivialised or 'simple' in other words for a local area? It is still dependant on predicting what happens in a washing machine of pressure systems and weather patterns split between 2 hemispheres that are in different seasons.

Perhaps it's just that the existing weather websites are quite so bad! In recent weeks, the forecasted high has been off by as much as 15 degrees.

Re: WeatherKit

#187

Post by e15ctr0n »

A quiet note of appreciation for Adam Grossman, one of the co-founders of Dark Sky. It's one thing to have an idea about a weather app, quite another to pursue it successfully within a small design agency and then make it polished enough over the years to sell it to a giant corporation like Apple. Even during that acquisition, Grossman went to bat for DarkSky's users, making sure that the API was kept live (for 2+ years running now). Post-acquisition, he has evidently become comfortable enough in a corporate environment to help evangelize the API's transition to an Apple-native SDK and Swift API. The creation of the REST API with a full mapping guide means that Grossman continues to bat for DarkSky API developers. The use of the native Swift API to create brand new Apple weather apps also appears to be well done. All-in-all, it has been a remarkable journey from a small, independent agency to a large corporate while keeping core values alive, a journey where many others have flamed out. An inspiration to all. Hats off to you, Grossman!

Re: WeatherKit

#188

Post by account42 »

Thlom wrote: post #27
knadh wrote: post #20

The Norwegian Meteorological Institute has an excellent free HTTP/JSON weather API that covers the globe. No signup required. https://developer.yr.no

Their weather app is also pretty good. It comes with an English language option.

Does the app provide anything valuable that you don't get with the website?

Re: WeatherKit

#189

Post by RivieraKid »

digthenerdy wrote: post #163
RivieraKid wrote: post #151

Earlier quoted context omitted.

Does it have equally good data as WeatherKit? I vaguely remember that yr.no shows raw ECMWF data. WeatherKit probably provides weather.com data, which are postprocessed from ECMWF and perhaps other models and they provide the best forecasts. The main issue with raw model data is that they are not adjusted for local altitude.

According to https://developer.apple.com/WeatherKit WeatheKit uses a forecast from Apple, and the data sources listed on https://WeatherKit.apple.com/legal-attribution.html don’t include The Weather Channel or weather.com.

Oh ok. So they're probably using the acquired DarkSky forecast.

Re: WeatherKit

#190

Post by megax »

While I appreciate the foreseeable improvements in the native (Apple) weather app, I will sorely miss the no-nonsense UI of DarkSky.

It has been my go-to for years now, especially as it relates to my photography hobby. I sure hope someone steps up to replace the DarkSky experience as Apple will surely cherry pick a small subset of their core pieces to implement, likely leaving the best weather geek features on the chopping block.

Post reply on HN