CNRS-MITI “Sciences pour l’IA, l’IA pour les sciences” SIDEREAL 2022-2023

CNRS-MITI 80Prime SIDEREAL 2023

Summary

This multidisciplinary project will develop new deep learning techniques to finely characterise the morphology of galaxies from large datasets of deep optical imaging. The astrophysics community faces a deluge of images that cannot be fully exploited by traditional manual and semi-automated analysis. We will address this situation by developing fully automated and high precision visual analysis algorithms. They will identify the diffuse tidal stellar features that surround galaxies and that bring a testimony on past galaxy collisions. Because of their low surface brightness and the presence of multiple contaminants, they are particularly difficult to isolate with classical IA techniques. New algorithms will be designed to address the specific challenges of these astrophysics data by integrating prior physics knowledge into the design of deep neural networks.

In a previous study, we adapted the architecture of a neural network to improve its sensitivity to both short and large scale oriented textures, in order to locate dust clouds contaminants that are overlaid with the imaged galaxies. This integration of knowledge on the structure of contaminants into the design of neural networks has improved their ability to differentiate the clouds’ filamentary structures from tidal features of the background galaxies.

In this project, we will push this architecture adaptation principle further. We will continue the development of our neural network to jointly classifying galactic stellar structures type and estimating morphology parameters, in order to obtain a detailed characterisation of galaxies and their collisional debris. This new framework will account for our prior knowledge on the structure of the problem and on the interactions and interdependencies between the morphology types and parameters. This interdisciplinary work will bring together experts in data science and deep learning, and in galaxy imaging and evolution.

Partner: Observatoire de Strasbourg and MATLAS

Funding body: CNRS-MITI

Role in the project: Principal Investigator

Preliminary study: PhD co-supervision: Classification and segmentation of galactic structures in large multi-spectral images, Felix Richards, 2017-2022