Adversarial disentanglement by backpropagation with physics-informed variational autoencoder

Today's article comes from the journal of Data-Centric Engineering. The authors are Koune et al., from Delft University of Technology, in the Netherlands. In this paper they've developed an error-tracing system for physical models. It allows you to determine whether a discrepancy between data and prediction reflects a change in the environment, a change in the structure, or a failure of the physics itself.

DOI: 10.1017/dce.2025.10028

Book
Book

Members Only

You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.

Login to My Account Sign Up