event_img

Séminaire

Bridging observation, theory and numerical simulation of the ocean using Machine Learning

This talk aims at showing some of the recent advancements in using Machine Learning for ocean modeling, it is also an opportunity to discuss the promising research avenues that can bring together ML researchers and ocean modelers.

       

Date début 25/05/2021 11:00
Date fin 25/05/2021
Organisateur LOCEAN
Lieu En ligne

Description

This talk aims at showing some of the recent advancements in using Machine Learning for ocean modeling, it is also an opportunity to discuss the promising research avenues that can bring together ML researchers and ocean modelers. Two applications are highlighted:

Clustering and Tracking Ocean Regimes using transparent machine learning: The North Atlantic ocean is key to climate through its role in heat transport and storage, but the response of the circulation’s drivers to a changing climate is poorly constrained. The transparent machine learning method Tracking global Heating with Ocean Regimes (THOR) identifies drivers of circulation with minimal input: depth, dynamic sea level and wind stress. Beyond a black box approach, THOR’s predictive skill is transparent. A dataset is created with features engineered and labeled by an explicitly interpretable equation transform and k-means application. A multilayer perceptron is then trained, explaining its skill using relevance maps and theory. THOR reveals a weakened circulation with abrupt CO2 quadrupling, due to a shift in deep water formation areas and locations of the Gulf Stream and Trans Atlantic Current transporting heat northward. If CO2 is increased 1% yearly, similar but transient patterns emerge. THOR could accelerate model analysis and facilitate process oriented intercomparisons.

History Matching for the tuning of oceanic models, a study case on the Lorenz96 model: Here I’ll present a tool from the Uncertainty Quantification community that started recently to draw attention in climate modeling: History Matching also referred to as « Iterative Refocussing ». The core idea of History Matching is to run several simulations with different set of parameters and then use observed data to rule-out any parameter settings which are « implausible ». Since climate simulation models are computationally heavy and do not allow testing every possible parameter setting, we employ an emulator that can be a cheap and accurate replacement. Here a machine learning algorithm, namely, Gaussian Process Regression is used for the emulating step. History Matching is then a good example where the recent advances in machine learning can be of high interest to climate modeling. I will show some results using History Matching on a toy model: the two-layer Lorenz96, and share some findings about the challenges and opportunities of using this technique.

Informations supplémentaires

Séminaire en ligne : https://global.gotomeeting.com/join/349269413

Au fil de la page


Spotlight

Sorbonnavirus

spotlight_img
Vingt-sept textes courts et percutants abordent l’épidémie, le virus, et la période actuelle à partir d’une grande variété de regards disciplinaires. Livre accessible au plus grand nombre, Sorbonnavirus rend compte de la crise sanitaire actuelle en tirant parti des forces d’une université dans laquelle la médecine côtoie les sciences et les humanités. Ce livre entre dans le virus, le traque, le suit, depuis ses origines jusqu’à ses effets, en remontant à ses ancêtres, épidémies antiques ou médiévales, en examinant sa gestion et ses effets, et en identifiant les chemins qu’il emprunte et qu’il ouvre, vers le ou les nouveaux mondes possibles. Avec une contribution de Cathy Clerbaux, chercheure au LATMOS-IPSL et de son équipe. Pierre-Marie Chauvin est vice-doyen Ressources humaines et moyens à la Faculté des Lettres. Maître de conférences en sociologie et chercheur au GEMASS (Groupe d’Etude des Méthodes de l’Analyse Sociologique de la Sorbonne), ses champs d’expertise sont la sociologie des réputations, la sociologie des temporalités et la sociologie visuelle. Annick Clement est vice-présidente Science, culture et société. Professeure de pédiatrie à la faculté de Médecine, elle est également chef du service de pneumologie pédiatrique de l’hôpital Trousseau. Visuel de couverture extrait de Profondeur bleue, par Julien Colombier.