ML4Oceans 2024 - 2nd edition!

The use of artificial intelligence is now crucial for environmental and climate issues, including oceanography. In this context, SCAI, ISCD and the Institut de l'Océan of Sorbonne Université joined their forces, together with the support of EUR-IPSL, to offer a transdisciplinary school for PhD candidates and post-doctoral researchers. 20 candidates will be selected according to their academic background, their research subject & their motivation to participate in this school.

The objective: to acquire knowledge and skills in AI applied to oceanography (marine biology - omics, biogeochemistry, acoustics, imagery).

Practical information

The school will take place in the seminar room of SCAI, the Sorbonne Center for Artificial Intelligence. It is located on the Pierre and Marie Curie Campus of Sorbonne University, 4 place Jussieu (métro Jussieu), 75005 Paris, France. Lectures will be given in English.

To join the seminar room of SCAI, you have to enter on the Jussieu campus through security, and then turn right and walk to the « Esclangon » building. Enter the Esclangon building and then take the exit on the left to take the stairs outside on the right. SCAI is just at the top of the stairs

Important: Do not forget to bring your own laptop.

Programme

The school will be from 9h to 17h or 18h, from Monday to Friday. Each day, you will have two classes of 1h30 each in the morning, by experts in their field: one on an oceanography topic and one on a machine learning topic. In the afternoon, you will have a tutored practical lab, in a dedicated computing environment, to apply a machine learning algorithm on real oceanic data. This direct application of the morning class will encompass coding, training, and applying a model.

Detailed programme:

The ML4Oceans school will be from 9h to 17h or 18h, from Monday to Friday.


Monday 7th October 2024: Introductions to the school, the programming language (Python and PyTorch) and the coding environment.
-------------------------------------------------------------------
From 8h30 to 9h00: Arrival of the participants
9h00-9h20: Presentation of the summer school (Sakina-Dorothée Ayata, LOCEAN) and presentations of SCAI (Andrea Pinna) and of the IPSL-SAMA (Soulivanh Thao)
9h20-10h30: Round table/presentation of each participant (about 2-3 min each)
10h30-11h00: break
11h00-11h45: Presentation of the computing environment and connexion tests (Christophe Bouder, SCAI)
11h45-12h30: Introduction to Python - Part I (Jean-Olivier Irisson, LOV)
(on-site lunch)
14h00-15h30:  Introduction to Python - Part II (Jean-Olivier Irisson)
15h30-16h00: break
16h00-17h:  Introduction to Python - Part III (Jean-Olivier Irisson)

From 17h30: Social event: Pétanque tournament at the Arènes de Lutèce, a park nearby the campus. TBC depending on the weather...!


Tuesday 8th October 2024: Linking biology and marine environment
---------------------------------------------------------------
9h00-10h30: Lecture on Marine genomics (Lucie Bittner, ISYEB)
10h30-11h00: break
11h00-12h30: Lecture on Machine Learning for Distribution models, including Tree based models (Jean-Olivier Irisson, LOV)
(lunch)
14h00-15h30: Practical lab on Predicting carbon concentration genomic potential using multivariate gradient boosted trees - part I (Lucie Bittner & Jean-Olivier Irisson)
15h30-16h00: break
16h00-17h00: Practical lab on Predicting carbon concentration genomic potential using multivariate gradient boosted trees - part II (Lucie Bittner & Jean-Olivier Irisson)
17h00-17h30: Example of machine learning applications by the company Fotonower (Victor Reutenauer, https://www.fotonower.com/)


Wednesday 9th October 2024: Derivation of poorly observed variables
------------------------------------------------------------------
9h-10h30: Lecture on Biogeochemical Argo floats (Hervé Claustre, LOV)
10h30-11h00: break
11h30-12h30: Lecture on Multilayer Perceptron and its use for biogeochemical Argo float data (Raphaëlle Sauzède, LOV; Anastase Charantonis, INRIA)
(lunch)
14h00-15h30: Practical lab on Deriving scarcely observed biogeochemical variables from profiles of common Argo ones using an MLP - part I (Raphaëlle Sauzède & Anastase Charantonis)
15h30-16h00: break
16h00-17h00: Practical lab on Deriving scarcely observed biogeochemical variables from profiles of common Argo ones using an MLP - part II (Raphaëlle Sauzède & Anastase Charantonis)
17h00-17h30: Example of machine learning applications for ocean data by the company Amphitrite (TBC, Alexandre Stegner & Evangelos Moschos, LMD/Amphitrite, https://www.amphitrite.fr/)


Thursday 11th October 2024: Classifying Passive acoustics data
---------------------------------------------------------------
9h-10h30: Lecture on Convolutional neural networks (CNN) with weak labeling (Dorian Cazau, Lab-SICC/ENSTA)
10h30-11h00: break
11h00-12h30: Lecture on using Passive acoustics data to study marine mammals and marine seascape (Olivier Adam, IJLRDA)
(lunch)
14h00-15h30: Practical lab Classifying marine mammals sounds using CNNs - part I (Dorian Cazau & Gabriel Dubus, IJLRDA)
15h30-16h00: break
16h00-17h30: Practical lab on Classifying marine mammals sounds using CNNs - part II (Dorian Cazau & Gabriel Dubus)


Friday 11th October 2024: Segmenting marine imaging data
--------------------------------------------------------
9h-10h30: Lecture on Plankton imaging (Sakina-Dorothée Ayata, LOCEAN)
10h30-10h30: break
11h00-12h30: Lecture on CNNs for object detection and segmentation (Jérémy Fix, LORIA-CentraleSupélec)
(lunch)
14h00-15h30: Practical lab on Instance segmentation of planktonic organisms from images using CNNs - part I (Jérémy Fix & Enza Labourdette, LOV/LPSM)
15h30-16h00: break
16h00-17h00: Practical lab on Instance segmentation of planktonic organisms from images using CNNs - part II (Jérémy Fix & Enza Labourdette, LOV/LPSM)
17h-17h15: Conclusion of the summer school

Application procedure

Please apply online before the 27th of June 2024:

LINK TO THE REGISTRATION FORM

Candidates will be selected using the following criteria: adequation between the school’s thematics and the candidate’s research project, minimum skill requirement, motivation for the ML4Oceans school. Candidates from different backgrounds are encouraged to apply.

The outcome of the selection procedure will be communicated to the candidates mid-July.

Speakers

Olivier Adam, IJLRDA, SU
Sakina-Dorothée Ayata, LOCEAN, SU
Lucie Bittner, ISYEB, SU
Dorian Cazau, LabSTICC, ENSTA Bretagne
Anastase Charantonis, LaMME/LOCEAN, ENSIIE/INRIA
Hervé Claustre, LOV, SU/CNRS
Gabriel Dubus, IJLRDA
Jean-Olivier Irisson, LOV, SU
Jérémy Fix, CentraleSupélec, LORIA
Enza Labourdette, LOV/LPSM, SU
Raphaëlle Sauzède, LOV-IMEV, SU

Organising committee

Sakina-Dorothée Ayata, LOCEAN, SU
Lucie Bittner, ISYEB, SU
Anastase Charantonis, LaMME/LOCEAN, ENSIIE/INRIA
Jean-Olivier Irisson, LOV, SU

Please contact sakina-dorothee.ayata@locean.ipsl.fr for any questions.