PhD in Physics-Informed Learning for Acoustic Inverse Problems

This PhD project focuses on creating a robust mathematical and algorithmic framework for solving acoustic inverse problems in complex environments. By integrating the wave equation directly into artificial intelligence architectures, the research aims to enhance acoustic field reconstruction from partial measurements. The work involves developing methods for localizing mobile sources and conducting quantitative detectability analysis. Candidates will work at the intersection of partial differential equation modeling, constrained optimization, and hybrid deep learning. The project has practical applications in distributed acoustic sensing and the detection of mobile platforms.

• Develop and implement physics-informed AI architectures for acoustic field reconstruction.
• Formulate and solve acoustic inverse problems using partial differential equation modeling.
• Design algorithms for the localization and tracking of mobile acoustic sources.
• Perform quantitative analysis of source detectability in complex environments.
• Integrate constrained optimization techniques into deep learning workflows.
• Contribute to the development of distributed acoustic sensing systems.