Tom Andersson

419 posts

Tom Andersson banner
Tom Andersson

Tom Andersson

@tom_r_andersson

Research Engineer @GoogleDeepMind; Building AI for climate change mitigation & adaptation; @WMO Young Scientist of the Year 2022; he/him

Katılım Şubat 2021
377 Takip Edilen758 Takipçiler
Sabitlenmiş Tweet
Tom Andersson
Tom Andersson@tom_r_andersson·
So excited to share our new @Nature paper on GenCast, an ML-based probabilistic weather forecasting model: nature.com/articles/s4158… It represents a substantial step forward in how we predict weather and assess the risk of extreme events. 🌪️🧵
Google DeepMind@GoogleDeepMind

Today in @Nature, we’re presenting GenCast: our new AI weather model which gives us the probabilities of different weather conditions up to 15 days ahead with state-of-the-art accuracy. ☁️⚡ Here’s how the technology works. 🧵goo.gle/49trAOv

English
2
2
28
1.8K
Tom Andersson retweetledi
Peter Battaglia
Peter Battaglia@PeterWBattaglia·
We rely on accurate weather predictions for critical decisions - from supply chains to energy grids to crop planning. AI is transforming how we forecast weather. Thrilled to share WeatherNext 2 - our latest work in groundbreaking forecasting technology! Learn more: blog.google/technology/goo…
English
10
32
221
65K
Tom Andersson retweetledi
Pope Leo XIV
Pope Leo XIV@Pontifex·
Technological innovation can be a form of participation in the divine act of creation. It carries an ethical and spiritual weight, for every design choice expresses a vision of humanity. The Church therefore calls all builders of #AI to cultivate moral discernment as a fundamental part of their work—to develop systems that reflect justice, solidarity, and a genuine reverence for life.
English
2.1K
5K
34K
5.5M
Tom Andersson
Tom Andersson@tom_r_andersson·
@RyanMaue FNv3's maximum sustained winds have much less bias than global NWP models so probably a better indicator of category than MSLP. You can access the raw FNv3 data via the download button on Weather Lab: deepmind.google.com/science/weathe…
English
1
0
0
144
Ryan Maue
Ryan Maue@RyanMaue·
Usually, pressure sub-920s is Category 5 in the Caribbean. Perhaps I was being too generous considering your more precise counts based upon max wind. But, not by much! I'm used to not trusting NWP 10-meter winds since they're biased low & use MSLP or UV850*0.9 Is there some place to look under the hood at FNV3?
English
1
0
2
683
Matt Onderlinde
Matt Onderlinde@Weathernerds·
Coming soon (probably tomorrow) to Weathernerds: Google Deep Mind AI track forecasts (FNV3 & GenCast). These are proving to be pretty useful for genesis, track, and even intensity forecasting.
Matt Onderlinde tweet media
English
14
33
333
47.4K
Noémi Éltető
Noémi Éltető@EltetoNoemi·
Back at it! I'm happy to share that I joined DeepMind in London full-time, and I will be working on automated tools for neuroscientific discovery. Disclaimer: I am not a go player, I just love this painting.
Noémi Éltető tweet media
English
57
34
1.5K
102.2K
Andrew Brady
Andrew Brady@Brady_Wx·
This is interesting: thus far with Hurricane #Erin, the novel ML models from @GoogleDeepMind are beating the traditional models (and consensus products!) from NHC/NOAA! Exciting!
Andrew Brady tweet mediaAndrew Brady tweet media
English
9
0
12
4.3K
Tom Andersson retweetledi
Peter Battaglia
Peter Battaglia@PeterWBattaglia·
Today we’re thrilled to announce that real-time and historical AI-based weather forecasts from @Google’s WeatherNext suite of models are now available on Earth Engine and BigQuery. Anyone can access and use these data for research, analysis and operational decision making, which we hope will help accelerate research and development in the weather and climate community. You can check out the AI-powered forecasts here: deepmind.google/technologies/w…
English
7
47
268
31.1K
Alek Petty
Alek Petty@alekpetty·
@tom_r_andersson Exciting to see this Tom! As a former sea ice forecaster, do you know of any plans for a more sea ice/polar focus here?! Would love to learn more if so...!
English
1
0
2
23
Tom Andersson
Tom Andersson@tom_r_andersson·
So excited to share our new @Nature paper on GenCast, an ML-based probabilistic weather forecasting model: nature.com/articles/s4158… It represents a substantial step forward in how we predict weather and assess the risk of extreme events. 🌪️🧵
Google DeepMind@GoogleDeepMind

Today in @Nature, we’re presenting GenCast: our new AI weather model which gives us the probabilities of different weather conditions up to 15 days ahead with state-of-the-art accuracy. ☁️⚡ Here’s how the technology works. 🧵goo.gle/49trAOv

English
2
2
28
1.8K
Tom Andersson
Tom Andersson@tom_r_andersson·
Like its predecessor (GraphCast), the weights & code of GenCast have been made publicly available: github.com/google-deepmin… We’re looking forward to seeing how the community builds on this!
English
1
0
2
181
Tom Andersson
Tom Andersson@tom_r_andersson·
GenCast uses diffusion to generate multiple 15-day forecast trajectories for the atmosphere. It assigns more accurate probabilities to possible weather scenarios than the SoTA physics-based ensemble system from ECMWF, across a 2019 evaluation period.
English
1
0
6
327
Tom Andersson
Tom Andersson@tom_r_andersson·
*may still post very occasionally
English
0
0
0
103

Keşfet

@RyanMaue @Weathernerds @FerranAlet @EltetoNoemi @Brady_Wx @GoogleDeepMind @PeterWBattaglia @NHC_Atlantic