Sure, neat, whatever, call me back when your AI can predict weather accurately and we'll talk.
If the AI singularity can't do more than a week out, we ain't there, kids. Don't fret.
Sure, neat, whatever, call me back when your AI can predict weather accurately and we'll talk.
If the AI singularity can't do more than a week out, we ain't there, kids. Don't fret.
@smari @quinn @whvholst @rysiek I saw something the other day about using NN stuff for improving rain forecasts actually. Basically, combine the large (1km square) predicted atmosheric cells with a much more detailed topographic map and detailed information about historic precipitation and basically do upscaling stuff.
@quinn @whvholst @rysiek weather forecast models had their last major sea change (groan) around 1996, and have since been largely stuck at 50% skill 3 days out. There is so much room for improvement.
@whvholst @rysiek @smari that's not the goal post, specificity is
@quinn @rysiek @smari Shall we shift the goalposts to at least three weeks out?
@smari @quinn @whvholst @rysiek To be clear, this was about higher resolution precipitation prediction (in time and space), not necessarily _further out_ in time.
GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.
All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.