Jekyll2022-03-02T12:49:15-08:00https://rfablet.github.io/feed.xmlRonan Fabletpersonal descriptionRonan Fabletronan.fablet[at]imt-atlantique.frNew animations of deep learning application to sea surface dynamics and SWOT data2020-07-01T00:00:00-07:002020-07-01T00:00:00-07:00https://rfablet.github.io/posts/2020/07/blog-post-11<div style="text-align: justify">
New animations available online: <a href="https://www.youtube.com/watch?v=fKIlVmeq9dk"> animation #1</a> and <a href="https://www.youtube.com/watch?v=n3r6dXsRo9k"> animation #2</a> for deep learning solutions for the reconstruction of sea surface dynamics from SWOT data.
Associated preprints: <a href="https://arxiv.org/abs/2006.03653"> arxiv link</a>
Associated code available from <a href="https://github.com/CIA-Oceanix"> oceanix github</a>
</div>Ronan Fabletronan.fablet[at]imt-atlantique.frNew animations available online: animation #1 and animation #2 for deep learning solutions for the reconstruction of sea surface dynamics from SWOT data. Associated preprints: arxiv link Associated code available from oceanix githubCan we jointly learn variational models and solvers for inverse problems?2020-06-10T00:00:00-07:002020-06-10T00:00:00-07:00https://rfablet.github.io/posts/2020/01/blog-post-10<div style="text-align: justify">
<img src="https://rfablet.github.io/images/fig_MNIST0770_All.png" width="350" align="right" />
We've just posted online a new preprint co-authored with Lucas Drumetz and Francois Rousseau on the joint learning of variational models and associated solvers to address inverse problems (e.g., inpainting, denoising, space-time interpolation, data assimilation,...)
<a href="https://arxiv.org/abs/2006.03653"> pdf on Arxiv</a> / <a href="https://github.com/CIA-Oceanix/DinAE_4DVarNN_torch"> Associated code on OceaniX github<a>
</a></a></div>Ronan Fabletronan.fablet[at]imt-atlantique.frWe've just posted online a new preprint co-authored with Lucas Drumetz and Francois Rousseau on the joint learning of variational models and associated solvers to address inverse problems (e.g., inpainting, denoising, space-time interpolation, data assimilation,...) pdf on Arxiv / Associated code on OceaniX githubNew PhD position on Deep learning & Space Oceanography in collaboration with CNES2020-02-15T00:00:00-08:002020-02-15T00:00:00-08:00https://rfablet.github.io/posts/2020/01/blog-post-8<p>We are pleased to call for applications for a <strong>CNES PhD position at IMT Atlantique (Brest, France)</strong> on Deep Learning
for Space Oceanigraphy newly-funded <a href="https://rfablet.github.io/projects/2019-melody"> MELODY project</a> and
<a href="https://rfablet.github.io/projects/2019-oceanix"> AI chair OceaniX</a>. More information in the proposed PhD position and the application procedure at:
<a href="https://recrutement.cnes.fr/en/annonce/899896-200-end-to-end-learning-of-geophysically-sound-cnn-representations-29200-brest"> link</a></p>
<p><strong>Deadline for application on CNES site:</strong> March 31st, 2020</p>Ronan Fabletronan.fablet[at]imt-atlantique.frWe are pleased to call for applications for a CNES PhD position at IMT Atlantique (Brest, France) on Deep Learning for Space Oceanigraphy newly-funded MELODY project and AI chair OceaniX. More information in the proposed PhD position and the application procedure at: linkCan we get the best of physical models and CNNs for geophysical flows?2020-02-13T00:00:00-08:002020-02-13T00:00:00-08:00https://rfablet.github.io/posts/2020/01/blog-post-9<div style="text-align: justify">
<img src="https://rfablet.github.io/images/figPDENetGen_Burgers202002.jpg" width="384" align="right" />
We've just posted online a new preprint co-authored with Olivier Pannekoucke on PDE-NetGen 1.0:
from symbolic PDE representations of physical processes to trainable neural network representations.
<a href="https://arxiv.org/pdf/2002.01029.pdf"> Arxiv</a> / <a href="https://github.com/opannekoucke/pdenetgen"> Associated code</a>
</div>Ronan Fabletronan.fablet[at]imt-atlantique.frWe've just posted online a new preprint co-authored with Olivier Pannekoucke on PDE-NetGen 1.0: from symbolic PDE representations of physical processes to trainable neural network representations. Arxiv / Associated codeTenured position at IMT Atlantique in Data Science2020-01-17T00:00:00-08:002020-01-17T00:00:00-08:00https://rfablet.github.io/posts/2020/01/blog-post-7<p>We are pleased to call for applications for a <strong>tenured position (Associate Professor) at IMT Atlantique (Brest, France)</strong>
in the Signal & Communications Department. This position is opened in the context of the newly-funded AI chair OceaniX:
https://rfablet.github.io/projects/2019-oceanix.</p>
<p><strong>Deadline for application:</strong> March 31st, 2020</p>
<p>The detailed description of the position and of the application procedure can be found at:
https://www.imt-atlantique.fr/en/associate-professor-data-science</p>Ronan Fabletronan.fablet[at]imt-atlantique.frWe are pleased to call for applications for a tenured position (Associate Professor) at IMT Atlantique (Brest, France) in the Signal & Communications Department. This position is opened in the context of the newly-funded AI chair OceaniX: https://rfablet.github.io/projects/2019-oceanix.AI Chair OceaniX funded by ANR2019-12-13T00:00:00-08:002019-12-13T00:00:00-08:00https://rfablet.github.io/posts/2019/31/blog-post-6<p>We just received very good news from ANR. Our AI chair proposal <strong>Oceanix</strong> (Physics-Informed AI for Observation-driven Ocean AnalytiX) has been selected by the ANR. More details from this <a href="https://rfablet.github.io/projects/2019-oceanix">link</a>. Open PhD and postdoc positions will be published soon. Do not hesitate to contact me for additional information.</p>Ronan Fabletronan.fablet[at]imt-atlantique.frWe just received very good news from ANR. Our AI chair proposal Oceanix (Physics-Informed AI for Observation-driven Ocean AnalytiX) has been selected by the ANR. More details from this link. Open PhD and postdoc positions will be published soon. Do not hesitate to contact me for additional information.New MSc/Eng. internship positions2019-10-31T00:00:00-07:002019-10-31T00:00:00-07:00https://rfablet.github.io/posts/2019/10/blog-post-1<p>Two MSc/Enng. internship positions are currently open in our group on data science, machine learning, oceanography and ocean remote sensing. Additional information can be found from the following links:</p>
<ul>
<li><a href="http://www.madics.fr/event/1571394504-2649/?instance_id=1228">Deep learning and stochastic transport in upper ocean dynamics</a></li>
<li><a href="http://www.madics.fr/event/1572432911-4572/?instance_id=1231">Learning multimodal invertible representations from ocean remote sensing data</a></li>
</ul>
<p>Do not hesisate to contact me for additionnal information at ronan.fablet AT imt-atlantique.fr</p>
<hr />Ronan Fabletronan.fablet[at]imt-atlantique.frTwo MSc/Enng. internship positions are currently open in our group on data science, machine learning, oceanography and ocean remote sensing. Additional information can be found from the following links: Deep learning and stochastic transport in upper ocean dynamics Learning multimodal invertible representations from ocean remote sensing dataWorkshop on AI4OAC, January 20202019-10-31T00:00:00-07:002019-10-31T00:00:00-07:00https://rfablet.github.io/posts/2019/31/blog-post-5<p>Announcement of the <strong>workskop AI4OAC (Artificial Intelligence for Ocean, Atmosphere and Climate)</strong>. This workshop is by invitation only. It will he held in Brest January 20-23, 2020. More details at <a href="https://ai4oac.sciencesconf.org/">ai4oac.sciencesconf.org</a>.</p>Ronan Fabletronan.fablet[at]imt-atlantique.frAnnouncement of the workskop AI4OAC (Artificial Intelligence for Ocean, Atmosphere and Climate). This workshop is by invitation only. It will he held in Brest January 20-23, 2020. More details at ai4oac.sciencesconf.org.New ANR project on Deep learning for Geophysical Fluid Dynamics2019-10-01T00:00:00-07:002019-10-01T00:00:00-07:00https://rfablet.github.io/posts/2019/10/blog-post-2<p>Good news from the ANR with the newly-funded project Melody
(Bridging geophysics and MachinE Learning for the modeling, simulation and reconstruction of Ocean DYnamics), 2019-2023.
Look at this <a href="https://rfablet.github.io/projects/2019-melody">link</a> for more information. We will open
PhD and postdoc positions within the framework of this project. Do not hesitate to contact me (ronan.fablet AT imt-atlantique.fr).</p>Ronan Fabletronan.fablet[at]imt-atlantique.frGood news from the ANR with the newly-funded project Melody (Bridging geophysics and MachinE Learning for the modeling, simulation and reconstruction of Ocean DYnamics), 2019-2023. Look at this link for more information. We will open PhD and postdoc positions within the framework of this project. Do not hesitate to contact me (ronan.fablet AT imt-atlantique.fr).Doctoral course on Data Science for Geoscience2019-09-15T00:00:00-07:002019-09-15T00:00:00-07:00https://rfablet.github.io/posts/2019/09/blog-post-3<p>We are glad to announce the third edition of the “Data Science for Geosciences” course.
It will be held in Toulouse from Monday 27 to Friday 31 January 2020. It aims to provide trainees with the basic concepts
underlying data science and statistical learning along with their implementation through dedicated libraries in the field of geosciences.
It will be located in the National Institute of Electrical engineering, Electronics, Computer science, Fluid mechanics &
Telecommunications and Networks (ENSEEIHT) in the center of Toulouse. More information at <a href="https://dsg2020.wordpress.com"> DSG’2020</a>.</p>Ronan Fabletronan.fablet[at]imt-atlantique.frWe are glad to announce the third edition of the “Data Science for Geosciences” course. It will be held in Toulouse from Monday 27 to Friday 31 January 2020. It aims to provide trainees with the basic concepts underlying data science and statistical learning along with their implementation through dedicated libraries in the field of geosciences. It will be located in the National Institute of Electrical engineering, Electronics, Computer science, Fluid mechanics & Telecommunications and Networks (ENSEEIHT) in the center of Toulouse. More information at DSG’2020.