Internship Master or Engineering degree
AI for Science: Physics Based Deep Learning for Modeling Complex Dynamics. Application to Climate
More information at: https://mlia.lip6.fr/available-positions/
Contact : patrick.gallinari@sorbonne-universite.fr
Where : Machine Learning and Information Access team – MLIA – https://mlia.lip6.fr, Sorbonne University, Paris, Fr
Dates and duration : 6 months starting in spring 2022
Candidate profile: Master or engineering degree in computer science or applied mathematics. The candidate should have a strong scientific background with good technical skills in programming.
Stipend : classical French academic internship gratification around 550 E/ mois
Research project summary
AI for science is concerned with the exploration of machine learning for scientific computing in domains traditionally dominated by physics models (first principles) like earth science, climate science, biological science, etc. It is particularly promising in problems involving processes that are not completely understood, or computationally too complex to solve by running the physics inspired model. The global objective for the internship is the development of new models integrating physics prior knowledge and deep learning (DL) for spatio-temporal dynamics characterizing physical phenomena such as those underlying climate observations. The classical modeling tools for such dynamics in physics rely on partial differential equations (PDE). We will then consider situations where the physical prior background is provided by PDEs. Two main directions will be explored: : (i) Interfacing Deep neural Networks and PDEs and (ii) Domain generalization for deep learning as dynamical model. The application will target the modeling of the dynamics of ocean circulation.