Topics
Latest
AI
Amazon
Image Credits:lim_pix / Getty Images
Apps
Biotech & Health
Climate
Image Credits:lim_pix / Getty Images
Cloud Computing
Commerce Department
Crypto
Enterprise
EVs
Fintech
fund raise
Gadgets
Gaming
Government & Policy
Hardware
Layoffs
Media & Entertainment
Meta
Microsoft
concealment
Robotics
Security
societal
place
Startups
TikTok
Transportation
speculation
More from TechCrunch
Events
Startup Battlefield
StrictlyVC
Podcasts
video
Partner Content
TechCrunch Brand Studio
Crunchboard
Contact Us
Google ’s DeepMind team unveiled an AI mannikin for weather prediction this workweek cry GenCast .
Ina newspaper publisher publish in Nature , DeepMind researchers state they found that GenCast surpass the European Centre for Medium - Range Weather Forecasts ’ ENS — on the face of it the world ’s top operational forecasting system .
And ina blog post , the DeepMind team offer a more accessible account of the tech : While its previous weather model was “ deterministic , and render a single , good estimation of succeeding conditions , ” GenCast “ comprises an ensemble of 50 or more forecasting , each representing a possible weather trajectory , ” creating a “ complex chance distribution of next weather scenario . ”
As for how it stacks up against ENS , the squad say it trained GenCast on conditions information up to 2018 , then compared its prognosis for 2019 , finding that GenCast was more exact 97.2 percent of the sentence .
Google says GenCast is part of its suite of AI - based atmospheric condition models , which it ’s starting to incorporate into Google Search and Maps . It also plans to release tangible - time and historical forecast from GenCast , which anyone can apply into their own enquiry and models .
