Radiance

Pierre Beaurepaire

Assistant professor

Institut Pascal - M3G - Uncertainty Quantification

Clermont-Ferrand, France

6 profile visits

Associate Professor at Clermont Auvergne INP specializing in uncertainty quantification for structural engineering, with increasing use of deep learning

My organisation

The Uncertainty Quantification (QI - Quantification des Incertitudes) team is a specialized research group within the M3G Department (Mechanics, Mechanical Engineering, Civil Engineering, Industrial Engineering) at the Institut Pascal (UMR 6602) in Clermont-Ferrand, France. The team’s work centers on ensuring structural safety and performance despite the inherent randomness in materials, manufacturing, and environments. Key research areas include: \-Stochastic Modeling & Statistical Inference: Developing probabilistic descriptions of system inputs and measurement errors. \- Uncertainty Propagation: Using methods like Monte-Carlo simulations and metamodeling (e.g., Kriging, Gaussian Processes) to see how input variations affect system outputs. \- Reliability Analysis: Evaluating the probability of failure for complex structures under static or dynamic loading. \- Optimization under Uncertainty (RBDO): Designing systems that are both efficient and robust against variability. \- AI & Machine Learning Integration: Leveraging Deep Learning and Physics-Informed Neural Networks (PINN) to accelerate simulations and improve predictive accuracy.
Read more

About me

I am a Maître de conférences (Associate Professor) at Clermont Auvergne INP and a researcher at the Institut Pascal (UMR6602). My work focuses on the development and application of numerical methods in structural mechanics, with a specialized emphasis on probabilistic methods such as uncertainty quantification, reliability analysis, and sensitivity analysis. I am currently expanding my research to integrate Deep Learning and Physics-Informed Neural Networks (PINN) into computational mechanics.

Skills

  • uncertainty quantification
  • Structural reliability
  • numerical simulation
  • Surrogate modeling
  • Structural Optimization
  • Bayesian inference
  • Machine Learning

Interests

  • neural networks
  • Physics-Informed Neural Networks (PINN)
  • Deep Learning for Partial Differential Equations

Marketplace (1)