The "ungamable impact" of OSS really resonates with me: www.thonking.ai/i/158277004/... Sadly it does not necessarily align with what makes for a sucessful career in Big Tech. But it's worth trying anyways! :)

Is there a link between #ClimateChange & increasing risk/severity of #wildfire in California--including the still-unfolding disaster? Yes. Is climate change the only factor at play? No, of course not. So what's really going on? [Thread] #CAfire #CAwx #LAfires iopscience.iop.org/a...

This is a huge milestone for cloud-native big scientific data!

Hi, thanks for the mention. Here's a 7-day paywall-free link to the main feature: www.bloomberg.com/graphics/202...

Some thoughts on the use of AI/ML in climate modeling... @realclimate.org ¡AI Caramba! www.realclimate.org/index.php/ar...

Can incorporating AI improve precipitation in global weather and climate models? Yes! In the latest NeuralGCM paper, we show that training on satellite-based precipitation results in significant improvements over traditional atmospheric models: arxiv.org/abs/2412.11973

Interested in AI weather/climate modeling at #AGU24? I'll be giving an overview talk on NeuralGCM at 11:30am Wed at the Google booth, and an talk on modeling precipitation with NeuralGCM at 4:25pm Wed in the session A34A.

There's nothing like the feeling of starting a codebase from scratch.

One of my favourite data discoveries this year: Google's mind-blowing ARCO-ERA5 dataset: hourly data for ~300 climate variables, available globally from 1940! 🤯 Loadable with a single line of Python code from a single cloud-friendly Zarr file! Below: a month of wind waves + swell: 🌊

Fast JAX simulations of all the PDEs--whee!

The new ACE2 climate emulator from Oliver Watt-Meyer et al has very compelling results, with results that look comparable to NeuralGCM. Congrats to the AI2 team! arxiv.org/abs/2411.112...

Curious how the latest AI weather models compare? Keeping WeatherBench2 up to date has been a bit trickier than we thought, but @raspstephan.bsky.social has put together a spreadsheet with quick estimates: docs.google.com/spreadsheets... Here's my version of the main plot.

My teammates at Google finally published (in Nature!) one of my favorite projects: using millions of cellphones to map the ionosphere and improve GPS location accuracy: research.google/blog/mapping...

This year, Google's Research Scholar program for early-career professors is specifically solicitating proposals on large-language and multi-modal machine learning models for science: research.google/outreach/resea… Applications will open next week and are due by the end of November.

Google Earth Engine has amazing datasets and functionality, but I've always wished it worked well with my favorite Python tools. XEE (Xarray + Earth Engine) by my friend @alexmerose.com fills that gap! github.com/google/Xee