PhD in Multi-Fidelity Physics-Informed Neural Network

We are offering a PhD position by a joint research project between the Division of Marine Technology and the Division of Fluid Dynamics with the aim to develop multi-fidelity physics-informed Neural Networks (PINN) architectures for fast CFD simulations.

Information about the research project
Most of the engineering mechanics problems can be described by different kinds of Partial Differential Equations (PDEs), such as fluid dynamics and ocean wave evolution. Current CFD methods for high-fidelity solutions of PDEs in fluid dynamics require large meshes with fine resolution and short time steps. The solutions of the stochastic PDEs that describe the dynamics of ocean wave evolution strongly depend on the resolution of the spatial and temporal discretization of the ocean environment. Both these sets of PDEs are normally solved by either numerical or empirical methods with multiple approximations and different levels of fidelity/resolution. The fast development of various Machine Learning algorithms provides opportunities to build explicit/black-box models in terms of pre-defined boundary and initial conditions.

This project will assess and implement the current state of the Physics-Informed Neural Networks (PINN) technology for solving general non-linear PDEs with application in fluid dynamics and wave equations. The main aim of this project is to exploit the recent developments in machine learning and multi-fidelity deep learning algorithms to accelerate and improve the efficiency of PINN algorithms. The current study will answer the research question of how to efficiently and accurately solve PDEs that describe fluid dynamics and wave evolutions by combining PINN and multi-fidelity algorithms. More detailed description of this project can be accessed here.


The Division of Marine Technology and Division of Fluid Dynamics
The division of Marine Technology conducts research and education centred primarily around the professional understanding and technical development of a ship's operational performance models. The Division of Fluid Dynamics conducts research covering turbulent flow, aero-acoustics and turbomachines. The mission is to gain fundamental knowledge about turbulent incompressible and compressible flows through numerical and experimental research, and develop new and improved computational and experimental techniques for the study of such flows in both fundamental and real-world environments.

Major responsibilities
Within this project, you will develop an efficient multi-fidelity physics-informed neural networks framework and algorithms for fast simulation of CFD solutions and ocean wave evolutions. Such algorithms require low-fidelity calculations that are computationally cheap, yet accurate enough to adequately capture the low-rank physical structures and expensive high-fidelity simulations that represent the physics more accurately. In addition, your responsibility as a PhD student also includes taking doctoral courses, developing your own scientific concepts, and communicating the results of your research verbally and in writing. The position generally also includes teaching corresponding to a maximum 10 percent of the working hours. You are encouraged to learn Swedish, to be able to contribute to courses taught in Swedish and to integrate better with the Swedish society.

Qualifications
To qualify as a PhD student in this project, you must have a Master of Science (Swedish: civilingenjör) in applied mechanics, engineering mechanics, ocean engineering, engineering physics, or similar with an emphasis on computational fluid dynamics and/or mathematical mechanics modeling.

It is meritorious to have experience in big data analysis, machine learning techniques, mathematical analytics, and interdisciplinary cooperation. As for all graduate studies, genuine interest and curiosity in the subject matter and excellent analytical and communication skills, orally as well as literally, are needed. Since research work normally involves developing and testing analytical techniques, you should have good skills in CFD simulation, and/or programming skills, such as in Python or Matlab. This PhD project will involve researchers from different disciplines. It is important that you are a motivated person that enjoys solving complex mathematical/mechanics problems individually as well as in collaboration with other researchers.

This position requires oral and written communication skills in English. Swedish is not required, but you will be encouraged to learn Swedish during employment, Chalmers offers Swedish courses.

Contract terms
The position is full-time temporary employment with a time limit to a maximum of 4.5 years. You will be employed by Chalmers and will receive a salary according to current salary agreements.

We offer
Chalmers offers a cultivating and inspiring working environment in the coastal city of Gothenburg. 
Read more about working at Chalmers and our benefits for employees.

Chalmers aims to actively improve our gender balance. We work broadly with equality projects, for example, the GENIE Initiative on gender equality for excellence. Equality and diversity are substantial foundations in all activities at Chalmers.

Learn more and apply on Chalmers website: https://www.chalmers.se/en/about-chalmers/Working-at-Chalmers/Vacancies/Pages/default.aspx?rmpage=job&rmjob=10605&rmlang=UK

Application deadline: August 14, 2022


*** Chalmers declines to consider all offers of further announcement publishing or other types of support for the recruiting process in connection with this position. *** 
   



Chalmers University of Technology conducts research and education in engineering sciences, architecture, technology-related mathematical sciences, natural and nautical sciences, working in close collaboration with industry and society. The strategy for scientific excellence focuses on our six Areas of Advance; Energy, Health Engineering, Information and Communication Technology, Materials Science, Production and Transport. The aim is to make an active contribution to a sustainable future using the basic sciences as a foundation and innovation and entrepreneurship as the central driving forces. Chalmers has around 11,000 students and 3,000 employees. New knowledge and improved technology have characterised Chalmers since its foundation in 1829, completely in accordance with the will of William Chalmers and his motto: Avancez!