OceaniX members organize different courses and training sessions on deep learning, data science, ocean remote sensing. We provide below more information on the following courses:

  • Introductory course on Deep Learning for Ocean and Atmosphere Science link
  • Doctoral course on Deep Leearning and Geophysical Dynamics link

Doctoral course on Deep Learning for Ocean and Atmosphere Sciences

This doctoral course co-organized between Grenoble (Pr. Emmanuel Cosme and Dr. Bruno Deremble) and Brest (Pr. Ronan Fablet, Pr. Carlos Granero Belincho, Pr. Lucas Drumetz and Pr. Pierre Tandeo) is an introductory course to deep learning for ocean, atmosphere and climate scientists. Supported by LEFE/MANU action, it will cover generic theoretical concepts in data science and machine learning as well as various approaches and problems. Besides labsession using python, it also involves a group project to apply these concepts to a specific issue from the formulation of the problem to the interpretation of numerical experiments. The targeted attendance primarily include PhD students and early-career scientists but we also welcome the particpation of research scientists, engineers,…

The course will be held in person both in Brest and Grenoble on June 26-30 2023 (up to 20 attendees in each location). The remote attendance will be possible for the lecture sessions (morning sessions). The detailed program of the course is available here.

Pre-requisite: Participants shall have some basic knowledge in applied math. and/or machine learning and some practice in Python programming. Previous knowledge in deep learning and pytorch is not a pre-requisite.

Contact person: ronan.fablet AT imt-atlantique.fr

Registration deadline: June 2, 2023

Registration form: link

Advanced Course on Deep Learning and Geophysical Dynamics

We will organize this year the second edition of the advanced course on Deep Learning and Geophysical Dynamics. The general objective of the course will be to cover theoretical aspects of deep learning and its application to geophysical dynamics, especially regarding the exploitation of physical priors.

The course will take place on tuesdays four consecutive weeks from November 15 to December 6 with the following four different lectures:

Co-working sessions: In addition to the lectures, co-working sessions will be organized in the afternoons to have the additional opportunity to meet and discuss with the lecturers and oceanix chair members as well as to share experience on deep learning packages (e.g., lightning, hydra,…). Interested attendees will have the opportunity to present ongoing research topics for discussion.

Pre-requisite: Participants shall have some basic knowledge in applied math. and/or machine learning and some practice in Python programming. Previous knowledge in deep learning and pytorch is not a pre-requisite. We will provide some links prior to the course to online tutorials for Pytorch, so that all participants could gain at a first basic practice before the course.

Online resources to prepare the course For those who have no or very little knowledge on deep learning and pytorch, below some resources:

  • Introductory course from Stanford Univ. on deep learning video
  • Reference book on deep learning link
  • Introduction to pytorch framework link
  • 60-minute blitz for pytorch link

Organization: The lectures will be given in-person in Brest at IMT Atlantique on Nov.15 and at the “Pôle Numérique Brest Iroise” for the other dates. It will also be possible to attend to the lectures and co-working sessions remotely (zoom conference).

  • Session on Nov.15: IMT Atlantique, Brest campus, room B1-010
  • Session on Nov.22, 29 and Dec.6: PNBI, Technopôle Brest Iroise, room “TD Iroise” (1st floor)

Registration deadline: November 8, 2022. There are no registration fees. For organizational aspects, we request the interested people to register through the following link: registration form