#ensembles — Public Fediverse posts

WeatherNext – [An] AI Model Achieves Breakthrough In Forecasting Cyclones
--
https://deepmind.google/blog/weathernext-ai-model-achieves-breakthrough-in-forecasting-cyclones/ <-- shared technical Google DeepMind blog post
--
https://doi.org/10.1038/s41586-026-10953-2 <-- shared paper
--
https://deepmind.google/science/weatherlab/ <-- shared data
--
https://github.com/google-deepmind/weathernext <-- shared GitHub repository
--
H/T @juliet Rothenberg | Product Director of Earth & Resilience AI at Google
[this post should not be considered an endorsement of a particular organisation or their approach]
“[The Google WeatherNext AI team] are showing how the WeatherNext AI model from Google DeepMind and Google Research has achieved state-of-the-art accuracy in predicting a cyclone's track, intensity, and wind structure. On average, the WeatherNext Cyclones model gives forecasters an extra day’s worth of predictive accuracy- delivering an advance equivalent to roughly a decade of historical meteorological progress 🌀
Here is how WeatherNext is transforming cyclone forecasting:
• Gaining an Extra Day of Advanced Warning: WN 3-day forecasts are as good as what prior models were able to provide for 2-day forecasts, giving critical time for emergency response.
• Overcoming Traditional Trade-offs: WN bridges the gap between massive global atmospheric currents (which steer a cyclone's path) and fine-grained thermodynamic processes around its core (which drive its intensity) into a single AI model.
• Unprecedented Ensemble Scale: Using Functional Generative Networks (FGNs), WN now generates 1,000-member ensembles in less than a minute on a TPU to capture rare, consequential tail-risks like sudden rapid intensification – which means forecasters can see a broader range of possible scenarios.
• Real-World Impact: During the 2025 Atlantic hurricane season, the WN model helped the National Hurricane Center (NHC) make a historic forecast for Hurricane Melissa by predicting rapid intensification and landfall five days in advance.
[The] teams are open sourcing the operationalized models (WeatherNext Cyclones and WeatherNext 2), alongside a compact version (WeatherNext 2-mini) that can run on a single TPU in a free public Colab notebook – all with a goal of empowering local organizations worldwide.
Weather affects everyone. By combining advanced AI with the real-world expertise of human forecasters, we can build a collaborative ecosystem that saves lives and helps communities adapt to a changing climate…”
#Google #DeepMind #GoogleResearch #AI #ensembles #FunctionalGenerativeNetworks #WeatherNext #cyclone #operationalised #model #modeling #forecasting #spatialanalyis #spatiotemporal #track #intensity #windstructure #hurricane #weather #climate #metrology #cyclonetrack #risk #hazard #emergencyresponse #planning #tool #earlywarning #scale #magnitude #path #track #thermodynamic #scenarios #opensource #impacts #tropicalcyclones #WeatherNextCyclones #weathermodel #atmospheric #predictions #mitigation #warning #robust #publicsafety #infrastructure
@Google | @WeatherNext

#CFP

The Sound of Empire – MusiCol International Symposia 2026

📍 Nice, France – Music as Relation (13–15 April 2026)
📍 Paris, France – Music and Media (16–18 April 2026)

Themes: music & agency in colonial capitals; #ensembles, #education, #religion, #theatre; #recordings, #radio, and evolving auralities. Interdisciplinary & comparative approaches welcome.

Deadline: 15/10/2025

https://musicol.ucsd.edu/wp6b/

#Musicology #Ethnomusicology #ColonialStudies

#Tribune | DU RÔLE DES STRUCTURES DE LA PRODUCTION CULTURELLE DANS LA POSSIBILITÉ MORALE DU DÉPASSEMENT ✒️

La tribune du mois d'avril rédigée par Erwan Vernay, délégué général de @grandsformats est à lire ici : https://bit.ly/3R1vrdq

#financements #coupesbudgetaires #politiquespubliques #cultureenlutte #Collectifs #ensembles #jazz #GrandsFormats

'An Asymptotic Study of Discriminant and Vote-Averaging Schemes for Randomly-Projected Linear Discriminants', by Lama B. Niyazi, Abla Kammoun, Hayssam Dahrouj, Mohamed-Slim Alouini, Tareq Y. Al-Naffouri.

http://jmlr.org/papers/v25/22-1367.html

#classifiers #ensembles #en

Bon. Dans la définition d'une partition, il y a "tous les éléments sont non vides". Or dans beaucoup de cas on se fout que tous les éléments soient non vides.

J'ai envie de pouvoir dire par exemple que si 𝐴₁ ... 𝐴ₙ est une partition de Ω, 𝐵∩𝐴₁ ... 𝐵∩𝐴ₙ est une partition de 𝐵, sans m'emmerder davantage. (Très utile pour démontrer la formule des probabilités totales).

Je fais quoi ? Changer la définition en disant que la plupart des auteurs demandent en outre que les 𝐴ᵢ soient non vides ? Ou bien est-ce qu'il y a un mot consacré comme "partition relax" ?

#math #ensembles

'Unsupervised Tree Boosting for Learning Probability Distributions', by Naoki Awaya, Li Ma.

http://jmlr.org/papers/v25/22-0980.html

#boosting #ensembles #distributional

Découvrez les fondements des mathématiques (logique formelle, arithmétique de Peano, théorie des ensembles, théorie des nombres, théorie des modèles, théorie de la calculabilité, théorie des catégories et des topos, structures algébriques...), dans les trois premiers volumes des "Éléments de mathématiques pour le XXIe siècle".
Détails et extraits : https://paysmaths.net
#mathématiques #maths #math #axiomes #logique #ensembles #catégories

`In this work, we show that for balanced datasets, there is no significant difference between logit and probability ensembles in terms of accuracy and ranked calibration. In contrast, we show that in long-tailed datasets, there are gains from logit ensembling when combined with imbalance bias reduction losses. In turn, our results show that we can have consistent performance improvements using loss-aware #ensembles when dealing with long-tail data.`

https://openreview.net/pdf?id=l4GYs60kre

Bayesian Quadrature for Neural Ensemble Search

Saad Hamid, Xingchen Wan, Martin Jørgensen, Binxin Ru, Michael A Osborne

Action editor: Kevin Swersky.

https://openreview.net/forum?id=T5sXdAO3EQ

#ensembles #ensemble #ensembling

'Flexible Model Aggregation for Quantile Regression', by Rasool Fakoor, Taesup Kim, Jonas Mueller, Alexander J. Smola, Ryan J. Tibshirani.

http://jmlr.org/papers/v24/22-0799.html

#quantile #quantiles #ensembles

Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrapping

Vikranth Dwaracherla, Zheng Wen, Ian Osband, Xiuyuan Lu, Seyed Mohammad Asghari, Benjamin Van Roy

Action editor: Gergely Neu.

https://openreview.net/forum?id=IqJsyulDUX

#ensemble #ensembles #bootstrapping

Thanks to Phil's Picks for including "NY Ensembles" in his selection "Phil’s Picks 2022 Top 10 New Jazz Albums" and for a great review of the album 🙏 📰🎶 😊

https://philspicks.wordpress.com/2022/12/31/diversity-shined-through-in-2022s-field-of-new-jazz-albums

https://philspicks.wordpress.com/tag/chris-torkewitz

Thanks to all the musicians on the album for their beautiful playing and soloing! 🙌🎶
.
.
.
.
#philspicks #nyensembles #bestof2022 #jazzalbums #jazzalbum #musik #album #albumrelease #ensembles #jazz #classical #musicians #music #release #composition #vinyl #review #sound #spotify #applemusic

'A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness', by Jeremiah Zhe Liu et al.

http://jmlr.org/papers/v24/22-0479.html

#ensembles #uncertainty #deep

Greedy Bayesian Posterior Approximation with Deep Ensembles

Aleksei Tiulpin, Matthew B. Blaschko

https://openreview.net/forum?id=P1DuPJzVTN

#greedy_ensembles_training #ensembles #ensemble

'IALE: Imitating Active Learner Ensembles', by Christoffer Löffler, Christopher Mutschler.

http://jmlr.org/papers/v23/21-0387.html

#learns #ensembles #learner

Been following the Bentz et al line of #language #complexity research since the 2018 #evolang workshop, great to see this paper out now: https://www.degruyter.com/document/doi/10.1515/lingvan-2021-0054/html?lang=en

But also cool, more thinking in #ensembles!
Us in https://arxiv.org/abs/2205.10271: "instead [of a single metric of visual complexity] use an array of estimates that captures complimentary aspects of complexity"
Bentz et al: "capture the complexity of a language by a vector of measurements, rather than a single value"

I am seeing many many writers and visual artists here which is fabulous - but not so many #AustralianMusicians, #Ensembles, #TheatrePractitioners, #CircusFolk, #FilmMakers, #ArtGalleries etc - if you find some can you let me know as I want to follow #Artspeople in Australia. thanks #Mastopals.

Hi everyone. New server. I'm Ben Sanderson - #climate scientist at #CICERO in Oslo, previously at #NCAR Some hashtags:
#CMIP
#scenario
#emulation
#uncertainty
#emissions
#carbon
#feedbacks
#policy
#ensembles
#SCM