Yaohua Zang

Yaohua Zang is a Professor at the Technical University of Munich, affiliated with the Department of Data-driven Materials Modeling. Their research bridges computational materials science, machine learning, and mathematical modeling, focusing on advanced methods for solving partial differential equations (PDEs), inverse problems, and optimal control in complex systems.

Research Interests include:

• Physics-informed neural operators for PDEs
• Stochastic generative modeling for materials design
• Optimal control in robotics and dynamic systems
• Bayesian inference and uncertainty quantification
• High-dimensional numerical analysis
• Adversarial and weak formulation-based neural networks

Recent work highlights physics-aware neural operators (DGenNO), weak adversarial networks for inverse problems, and applications in elastography and robotic assembly. Their scientific contributions span PDEs, materials science, and computational control.

Labs & Teams: Part of the Chair of Data-driven Materials Modeling, located in Garching b. München, Germany.