I'm interested in applying ML to weather and climate.
Exeter
Joined July 2011
- Tweets440
- Following570
- Followers406
- Likes1.7K
A short post announcing our recent publication on nowcasting precipitation! A collaboration between @DeepMind @metoffice @informatics_lab medium.com/informatics-lab/d…
Rachel Prudden retweeted
Thank you to a truly amazing set of colleagues whose contributions in so many different ways made this possible: @SumanRavuri @LencKarel @MirowskiPiotr @d_kangin @RachelPrudden @niallhrobinson and many other amazing people. ♥️🚀🥳🤩🎉
It's been a long journey! #rightwhatsnext indeed
This Post is from an account that no longer exists. Learn more
Rachel Prudden retweeted
Causal networks to the rescue! 🤩Want to disentangle and quantify causal pathways of teleconnections in the climate system? @Marlene_Climate does a terrific job at explaining all you need to know in our new BAMS paper @RachelPrudden @SamanthaVAdams @niallhrobinson 🎉 @ametsoc
This Post is from an account that no longer exists. Learn more
I recently gave a seminar on probabilistic reasoning as part of the Oxford ML and Physics seminar series. Take a look!
@informaticslab
medium.com/informatics-lab/p…
Also, their YouTube channel is great to browse
youtube.com/channel/UCLBre8Z…
The second installment of my two-part series on spatial reasoning in random fields is now up! Emergent effects from combining spatial and point observations.
medium.com/informatics-lab/s…
First part here teapawt.org/RachelPrudden/status/1…
Would you like to learn how to use Gaussian processes for super-resolution? First in a two-part series of blog posts:
rachel-prudden.medium.com/sp…
Would you like to learn how to use Gaussian processes for super-resolution? First in a two-part series of blog posts:
rachel-prudden.medium.com/sp…
And the accompanying paper
teapawt.org/RachelPrudden/status/1…
New preprint on arXiv!
"Stochastic downscaling to chaotic weather regimes using spatially conditioned Gaussian random fields with adaptive covariance"
@informatics_lab
arxiv.org/abs/2105.08188
New preprint on arXiv!
"Stochastic downscaling to chaotic weather regimes using spatially conditioned Gaussian random fields with adaptive covariance"
@informatics_lab
arxiv.org/abs/2105.08188
This looks super helpful.
Excited to share our new paper on benchmarking simulation-based inference!
Check out our interactive website w/short summary
With @janfiete, @dvdgbg, @ppjgoncalves and @jakhmack
Paper: arxiv.org/abs/2101.04653
Code: github.com/sbi-benchmark/sbi…
sbi-benchmark.github.io
Rachel Prudden retweeted
Really enjoying the great suggestions people have had on more research taste exercises/strategies. Curating at the end of colah.github.io/notes/taste/
Ideas from @RachelPrudden, @andy_matuschak, @michael_nielsen (via @shreydjain13), @arthurallshire, @PreetumNakkiran
I'm excited about this direction. Lots of potential in both atmospheric science and machine learning, IMO.
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
New blog post! I discuss probabilistic programming with Pyro for event detection. @informatics_lab rachel-prudden.medium.com/pr…
Yeah, I need to figure this out.
Which ML experiment management tool do you use?
• Paper
• @googlesheets
• @TensorBoard
• @wandb
• @neptune_ai
• @Cometml
• @MLflow
• @guildai
• @kuberflow
• @PolyaxonAI
• @DVCorg
Rachel Prudden retweeted
Nowcasting was a new and fun field for us, and after a while we thought to write a paper we wished we had when we started. Thankful for hard work by @RachelPrudden & team 🎉 This areas exposes many core questions in ML so a great for advancing research arxiv.org/abs/2005.04988
A preprint of our review paper is now on the arXiv! arxiv.org/abs/2005.04988 We cover approaches to radar-based precipitation nowcasting, including ML techniques.