Abstract:  Solving parametric partial differential equations (PDEs) and associated PDE-based, inverse problems is a central task in engineering and physics, yet existing neural operator methods struggle with high-dimensional, discontinuous inputs and require large amounts of {\em labeled} training… [weiterlesen]

Optimizing parameters of physics-based simulators is crucial in the design process of engineering and scientific systems. This becomes particularly challenging when the simulator is stochastic, computationally expensive, black-box and when a high-dimensional vector of parameters needs to be… [weiterlesen]

Highlights • PSP-GEN integrates the entire PSP chain into one deep model, addressing complexities. • It employs a two-part latent space: one for microstructures and one for processing links. • Discrete-valued design is reformulated as continuous for gradient-based optimization. • PSP-GEN… [weiterlesen]

Highlights • Novel Bayesian method using ML and physics to solve model-based, inverse problems. • Uses weighted residuals as virtual observables, avoiding a classical forward model. • Solving inverse problems for ill-posed (insufficient bound. cond.) forward problems. • Demonstrations in… [weiterlesen]

[weiterlesen]

Highlights: • We propose a novel probabilistic framework for training physics-informed surrogates for high dimensional, parametric PDEs as those encountered in (random) heterogeneous materials. • It is trained exclusively by sub-sampling weighted residuals, • In the core of its architecture lies… [weiterlesen]

We solve optimization problems involving a real-world physics-based, stochastic, bck-box, multi-modal, and high dimensional simulators. More details here: https://hal.science/hal-04659802 [weiterlesen]

A framework for the stochastic inversion of Process-Structure-Property chain in the design of heterogeneous materials. More details: https://arxiv.org/abs/2408.01114 [weiterlesen]

We solve model-based Bayesian inverse problems without a forward model.We explore applications in elastography with the ultimate goal of enabling model-based diagnosis on hand-held devices by non-experts. More details here: https://arxiv.org/abs/2407.20697 [weiterlesen]

Abstract: The goal of inverse molecular design is the discovery of novel molecular structures that fulfill a set of target properties. In this project we explore the application of generative models and molecular graph representations for the development of solutions to the inverse molecular design… [weiterlesen]