Sign in

Julien Brajard

@brajard.bsky.social
290 followers 79 following 30 posts

Senior Researcher at the Nansen Center in Bergen. Working with machine learning, Earth System modeling, and data assimilation.

PostsRepliesMedia
Reposted by Julien Brajard
Aida Alvera-Azcárate @aida-alvera.bsky.social · 08/01/2026
‪ 📣 One week left!! 📣 🌊 Call for abstracts #EGU26 !!! Please consider our session: ITS1.9/OS4.1 Machine Learning for Ocean Science meetingorganizer.copernicus.org/EGU26/sessio... Deadline 15 January 2026 @brajard.bsky.social @rachelfurner.bsky.social @redouanelg.bsky.social
A slide showing a blue surface with waves and superposed 0s and 1s on the left, and text describing the session and details for submission:

ITS1.9/OS4.1
Machine Learning for Ocean Science

https://meetingorganizer.copernicus.org/EGU26/sessionprogramme/5869#

Session abstract:
Machine learning (ML) methods have emerged as powerful tools to tackle various challenges in ocean science, encompassing physical oceanography, biogeochemistry, and sea ice research.
This session aims to explore the application of ML methods in ocean science, with a focus on advancing our understanding and addressing key challenges in the field. Our objective is to foster discussions, share recent advancements, and explore future directions in the field of ML methods for ocean science.
A wide range of machine learning techniques can be considered including supervised learning, unsupervised learning, interpretable techniques, and physics-informed and generative models. The applications to be addressed span both observational and modeling approaches.

Observational approaches include for example:
- Identifying patterns and features in oceanic fields
- Filling observational gaps of in-situ or satellite observations
- Inferring unobserved variables or unobserved scales
- Automating quality control of data

- Modeling approaches can address (but are not restricted to):
- Designing new parameterization schemes in ocean models
- Emulating partially or completely ocean models
- Parameter tuning and model uncertainty

The session also welcomes submissions at the interface between modeling and observations, such as data assimilation, data-model fusion, or bias correction.

Researchers and practitioners working in the domain of ocean science, as well as those interested in the application of ML methods, are encouraged to attend and participate in this session.
023
Reposted by Julien Brajard
Aida Alvera-Azcárate @aida-alvera.bsky.social · 05/11/2025
📣 🌊 Call for abstracts #EGU26 !!! Please consider our session: ITS1.9/OS4.1 Machine Learning for Ocean Science meetingorganizer.copernicus.org/EGU26/abstra... Deadline 15 January 2026 (1 December for travel grant applications) @brajard.bsky.social @rachelfurner.bsky.social @redouanelg.bsky.social
A slide showing a blue surface with waves and superposed 0s and 1s on the left, and text describing the session and details for submission:

ITS1.9/OS4.1
Machine Learning for Ocean Science

https://meetingorganizer.copernicus.org/EGU26/sessionprogramme/5869#

Session abstract:
Machine learning (ML) methods have emerged as powerful tools to tackle various challenges in ocean science, encompassing physical oceanography, biogeochemistry, and sea ice research.
This session aims to explore the application of ML methods in ocean science, with a focus on advancing our understanding and addressing key challenges in the field. Our objective is to foster discussions, share recent advancements, and explore future directions in the field of ML methods for ocean science.
A wide range of machine learning techniques can be considered including supervised learning, unsupervised learning, interpretable techniques, and physics-informed and generative models. The applications to be addressed span both observational and modeling approaches.

Observational approaches include for example:
- Identifying patterns and features in oceanic fields
- Filling observational gaps of in-situ or satellite observations
- Inferring unobserved variables or unobserved scales
- Automating quality control of data

- Modeling approaches can address (but are not restricted to):
- Designing new parameterization schemes in ocean models
- Emulating partially or completely ocean models
- Parameter tuning and model uncertainty

The session also welcomes submissions at the interface between modeling and observations, such as data assimilation, data-model fusion, or bias correction.

Researchers and practitioners working in the domain of ocean science, as well as those interested in the application of ML methods, are encouraged to attend and participate in this session.
053
Julien Brajard @brajard.bsky.social · 28/09/2025
NB: small error in the right row of figures 8 and 9.
000
Julien Brajard @brajard.bsky.social · 28/09/2025
Conditional Flow matching is a very efficient generative AI concept, close to diffusion models. Here is a wonderful and visual explanation of how it works! dl.heeere.com/conditional-...
dl.heeere.com
A Visual Dive into Conditional Flow Matching | ICLR Blogposts 2025
Conditional flow matching (CFM) was introduced by three simultaneous papers at ICLR 2023, through different approaches (conditional matching, rectifying flows and stochastic interpolants). <br/> The m...
100
Julien Brajard @brajard.bsky.social · 12/07/2025
We have 2 positions open at the Nansen Environmental and Remote Sensing Center (NERSC), one in data assimilation (same group as mine) and one in the ocean modelling group. Application deadline: 18th August www.jobbnorge.no/en/available... www.jobbnorge.no/en/available...
jobbnorge.no
Researcher Position in Data Assimilation&nbsp; (281670) | Nansen Environmental and Remote Sensing Center
Job title: Researcher Position in Data Assimilation&nbsp; (281670), Employer: Nansen Environmental and Remote Sensing Center, Deadline: Monday, August 18, 2025
030
Julien Brajard @brajard.bsky.social · 12/07/2025
Interested in working in a world-leading and motivating research group, located in one of the most beautiful places on Earth?
100
Julien Brajard @brajard.bsky.social · 16/06/2025
Well done guys! But I don’t think I was part of the team 😉
000
Julien Brajard @brajard.bsky.social · 10/06/2025
The call is open to all researcher working in a French institution. The links for the videocall: 📅 Wednesday, June 11, 2025 – 4:00 PM (Paris time) cnrs.zoom.us/j/9818976076... 📅 Thursday, June 12, 2025 – 12:30 PM (Paris time) univ-lille-fr.zoom.us/j/9520884409...
cnrs.zoom.us
Join our Cloud HD Video Meeting
Zoom is the leader in modern enterprise cloud communications.
010
Julien Brajard @brajard.bsky.social · 10/06/2025
Join the PNTS committee during one of the upcoming videoconferences to ask your questions and learn more about the program: 📅 Wednesday, June 11, 2025 – 4:00 PM (Paris time) 🔗 Join via Zoom (CNRS) 📅 Thursday, June 12, 2025 – 12:30 PM (Paris time) 🔗 Join via Zoom (Lille University)
100
Julien Brajard @brajard.bsky.social · 10/06/2025
The program is open to French researchers—including non-permanent staff—and offers funding for project development in these areas. 📢 Learn more and apply here (deadline: 5 Sept. 2025): programmes.insu.cnrs.fr/pnts/appel_o...
programmes.insu.cnrs.fr
Appel à projets en cours - Programmes de l'INSU
L’appel à projets PNTS 2026 est ouvert sur Sigap du 1er juin 2025 au 5 septembre 2025, 17h (heure de Paris). Fichier attaché Taille Texte de l’appel à projets PNTS 2026 907 Ko Dossier scientifique PNT...
100
Julien Brajard @brajard.bsky.social · 10/06/2025
🚨 Call for Proposals – PNTS Program 🇫🇷 The PNTS (Programme National de Télédétection Spatiale) supports researchers developing algorithms and validation procedures for remote sensing data across diverse domains: ocean, atmosphere, continental surfaces, and solid Earth.
programmes.insu.cnrs.fr
Appel à projets en cours - Programmes de l'INSU
L’appel à projets PNTS 2026 est ouvert sur Sigap du 1er juin 2025 au 5 septembre 2025, 17h (heure de Paris). Fichier attaché Taille Texte de l’appel à projets PNTS 2026 907 Ko Dossier scientifique PNT...
100
Reposted by Julien Brajard
LEAP-STC @leapstc.bsky.social · 03/06/2025
Please join us for a Summer'25 Lecture in #Climate #Data Science w/TOBIAS FINN @ecoledesponts.bsky.social! 📅 THIS THURSDAY || 6/5/25 🕛 12p EST 📍 @columbiaseas.bsky.social Innovation Hub/Zoom 💻 RSVP: www.eventbrite.com/e/1363524320... #LEAPEducation #community #physics #climatemodel #AI #ML
042
Julien Brajard @brajard.bsky.social · 29/04/2025
📢 New CFP: Special Collection in EDS! Calling for work exploring the convergence between #data-driven methodologies (#AI, #machinelearning) and physical modeling for Earth system science, building upon an upcoming workshop #EGU25 (@egu.eu). ℹ️ How to submit: bit.ly/3Eq4WLV 📅 Deadline: 31 Oct 2025
bit.ly
EDS Special Collection on Connecting Data-Driven and Physical Approaches
EDS Special Collection on Connecting Data-Driven and Physical Approaches
031
Julien Brajard @brajard.bsky.social · 29/04/2025
And if you are looking for a venue to publish your work, please consider the following @envdatascience.bsky.social
110
Julien Brajard @brajard.bsky.social · 29/04/2025
The Copernicus Marine Service and the European Digital Twin of the Ocean Orals | Thu, 01 May, 14:00–18:00 (CEST) Room L2 Posters on site | Attendance Thu, 01 May, 10:45–12:30 (CEST) meetingorganizer.copernicus.org/EGU25/sessio...
meetingorganizer.copernicus.org
Session OS4.7
100
Julien Brajard @brajard.bsky.social · 29/04/2025
Machine Learning for Ocean Science Orals | Thu, 01 May, 08:30–12:30 (CEST), 14:00–15:45 (CEST) Room -2.41/42 Posters on site | Attendance Thu, 01 May, 16:15–18:00 (CEST) meetingorganizer.copernicus.org/EGU25/sessio... @rachelfurner.bsky.social @redouanelg.bsky.social @aida-alvera.bsky.social
meetingorganizer.copernicus.org
Session ITS1.2/OS4.8
141
Julien Brajard @brajard.bsky.social · 29/04/2025
If you are at EGU, you can check out those two sessions related to machine learning 🤖 and the ocean 🌊 @egu.eu #egu25
120
Reposted by Julien Brajard
Andreas Kirsch @blackhc.bsky.social · 07/01/2025
Ever wondered why presenting more facts can sometimes *worsen* disagreements, even among rational people? 🤔 It turns out, Bayesian reasoning has some surprising answers - no cognitive biases needed! Let's explore this fascinating paradox quickly ☺️
824283
Reposted by Julien Brajard
NECCTON Project @neccton.bsky.social · 06/03/2025
At the NECCTON Annual Meeting in Trieste, we unveiled co-designed case studies that are reshaping fisheries management and marine conservation. Fresh tools & ideas are setting our oceans on a new course. Learn more: neccton.eu/case-studies @copernicusmarine.bsky.social @plymouthmarine.bsky.social
neccton.eu
NECCTON Case Studies
NECCTON will be working in collaboration with a range of stakeholders to supporting fisheries management and biodiversity conservation through development and exploitation of NECCTON tools and product...
052
Julien Brajard @brajard.bsky.social · 10/01/2025
can you please add me?
120
Reposted by Julien Brajard
Climate Informatics @climformatics.bsky.social · 07/01/2025
[3 days:] 📚🌍 Submit to #CI2025 and have a chance to publish in @cambridgeup.bsky.social "Environmental Data Science" #OpenAccess #Science 2025.climateinformatics.com.br
2025.climateinformatics.com.br
Climate Informatics 2025
Hosted by IBM Research Brazil at _Centro Cultural Fundação Getúlio Vargas (FGV)_ from **April 28 to 30, 2025**.
024
Julien Brajard @brajard.bsky.social · 07/01/2025
In this last session, we are honored to have Julie Deshayes as solicited speaker. @rachelfurner.bsky.social @aida-alvera.bsky.social @redouanelg.bsky.social
023
Julien Brajard @brajard.bsky.social · 07/01/2025
If you are developing or using an original machine learning algorithm for the ocean, this is where you can go: "Machine Learning for Ocean Science" meetingorganizer.copernicus.org/EGU25/sessio...
meetingorganizer.copernicus.org
Session ITS1.2/OS4.8
100
Julien Brajard @brajard.bsky.social · 07/01/2025
If you develop new products or models for the ocean, please consider the session "The Copernicus Marine Service and the European Digital Twin of the Ocean " meetingorganizer.copernicus.org/EGU25/sessio...
meetingorganizer.copernicus.org
Session OS4.7
100
Julien Brajard @brajard.bsky.social · 07/01/2025
Happy New Year 2025!🌍 To start well the year, please consider submitting an abstract to EGU. #EGU25 @eurogeosciences.bsky.social
meetingorganizer.copernicus.org
Session OS4.7
133
Julien Brajard @brajard.bsky.social · 02/12/2024
These diffusion models are incredibly versatile!
031
Julien Brajard @brajard.bsky.social · 29/11/2024
Only 3 days left to submit an abstract to the Living Planet Symposium!
032
Julien Brajard @brajard.bsky.social · 27/11/2024
Nice session to consider with a great team of conveners 😀
043
Julien Brajard @brajard.bsky.social · 27/11/2024
🌊
000
Julien Brajard @brajard.bsky.social · 25/11/2024
Are you interested in the links between physical modeling and machine learning? What is the potential of hybrid physics/data models? Please consider submitting to the special issue of the "Environmental Data Science" journal www.cambridge.org/core/journal... @cambridgeup.bsky.social
020
Julien Brajard @brajard.bsky.social · 25/11/2024
The preprint is here (not the final version but close enough): arxiv.org/abs/2408.09627
arxiv.org
Machine Learning for the Physics of Climate
An exponential growth in computing power, which has brought more sophisticated and higher resolution simulations of the climate system, and an exponential increase in observations since the first weat...
000
Julien Brajard @brajard.bsky.social · 25/11/2024
I am very glad to share this review paper: 📃 "Machine Learning for the Physics of Climate." As stated in the title, the review targets the opportunities and challenges of machine learning for climate physics. www.nature.com/articles/s42... @pedramh.bsky.social
nature.com
Machine learning for the physics of climate - Nature Reviews Physics
Artificial intelligence techniques, specifically machine learning, are being increasingly applied to climate physics owing to the growing availability of big data and increasing computational power. T...
3275
Julien Brajard @brajard.bsky.social · 24/11/2024
Very pedagogical introduction to transformers with beautiful visuals.
030
Reposted by Julien Brajard
Tom Andersson 🌍 @tom-andersson.bsky.social · 24/11/2024
Beautiful introduction to transformers in this lecture by 3blue1brown / Grant Sanderson: youtu.be/KJtZARuO3JY?...
youtu.be
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
YouTube video by Grant Sanderson
141
Reposted by Julien Brajard
Marius Årthun @mariusarthun.bsky.social · 21/11/2024
A good opportunity for a first post. Come work with us!
069
Julien Brajard @brajard.bsky.social · 20/11/2024
I'm thrilled to be part of the amazing convener team and looking forward the works presented—especially on data assimilation with machine learning! Submit your abstract and join us for an inspiring exchange of ideas! 💡 www.registration.lps25.esa.int/Presentation...
registration.lps25.esa.int
000
Julien Brajard @brajard.bsky.social · 20/11/2024
The Living Planet Symposium 2025 conference will take place 23–27 June 2025 in Vienna, Austria! 🌍 🔔 Abstract submission deadline: 1 December 2024 I warmly invite you to contribute to our session: D.02.04 Machine Learning for Earth System Observation and Prediction
registration.lps25.esa.int
221
Julien Brajard @brajard.bsky.social · 20/11/2024
Hello @bsky.app! I'll be posting occasionally to share updates on my work, conference sessions, and online meetings related to machine learning applications in Earth System Science, particularly focused on the Arctic and the Ocean. 🌊❄️ Looking forward to connecting with others in this space!
030