• After witnessing the continued decrease of involvement in the SpotterNetwork staff in serving SN members with troubleshooting issues recently, I have unilaterally decided to terminate the relationship between SpotterNetwork's support and Stormtrack. I have witnessed multiple users unable to receive support weeks after initiating help threads on the forum. I find this lack of response from SpotterNetwork officials disappointing and a failure to hold up their end of the agreement that was made years ago, before I took over management of this site. In my opinion, having Stormtrack users sit and wait for so long to receive help on SpotterNetwork issues on the Stormtrack forums reflects poorly not only on SpotterNetwork, but on Stormtrack and (by association) me as well. Since the issue has not been satisfactorily addressed, I no longer wish for the Stormtrack forum to be associated with SpotterNetwork.

    I apologize to those who continue to have issues with the service and continue to see their issues left unaddressed. Please understand that the connection between ST and SN was put in place long before I had any say over it. But now that I am the "captain of this ship," it is within my right (nay, duty) to make adjustments as I see necessary. Ending this relationship is such an adjustment.

    For those who continue to need help, I recommend navigating a web browswer to SpotterNetwork's About page, and seeking the individuals listed on that page for all further inquiries about SpotterNetwork.

    From this moment forward, the SpotterNetwork sub-forum has been hidden/deleted and there will be no assurance that any SpotterNetwork issues brought up in any of Stormtrack's other sub-forums will be addressed. Do not rely on Stormtrack for help with SpotterNetwork issues.

    Sincerely, Jeff D.

Google MetNet - A Reliable Precip Model?

Randy Jennings

Supporter
Joined
May 18, 2013
Messages
794
In s blog post and accompanying paper, researchers at Google detail an AI system — MetNet — that can predict precipitation up to eight hours into the future. They say that it outperforms the current state-of-the-art physics model in use by the U.S. National Oceanic and Atmospheric Administration (NOAA) and that it makes a prediction over the entire U.S. in seconds as opposed to an hour.


 
They are taking existing precip and moving it. That may be effective - but it doesn't account for precip that forms after FH0. So in essence - might be good for future project, but useless as-is.
 
Anytime corporate America gets involved with a large-scale weather project I wouldn’t rest on the laurels of NOAA and NWS. With the likes of Google and their deep pockets I’d be looking over my shoulder for the day when privatization comes knocking at the front door. They have a massive amount of computational resources and can also pay salaries well beyond the standard GS11-13 meteorologists make in civil service after earning a PhD. I think it bears watching simply because we cannot seem to equal or best the Euro models. We’re closing the gap but still have work to do. Please don’t take offense @Jeff Duda as I know this is personal to you. After all it’s just my humble opinion.
 
I don't think anyone is suggesting otherwise :) But NWS short-range modeling is far superior to the ECMWF so make sure to apples and oranges...
 
Yeah, we're aware of it at ESRL/GSD (i.e., the HRRR group). Definitely some competition there. I haven't fully scrutinized the work yet (they didn't give adequate details to perform a rigorous scientific comparison anyway).

There is no doubt that machine learning/AI has a place in weather forecasting/NWP, and it certainly appears that, in this restricted framework, Google's software may indeed outperform the HRRR at very short ranges. One big thing that separates ML/AI forecasting from full-blown dynamical forecasting is that ML/AI is still restricted to past data sets and mostly serves as post-processing to existing forecast data, whereas the dynamical method actually uses the laws of physics directly to perform a weather forecast. Thus, ML/AI has an upper bound to how good it can forecast, especially temporally.
 
Back
Top