Data-driven discovery of thermal illusions through latent-space geometry
Liyou Luo, Pengfei Zhao, Jensen Li

TL;DR
This paper introduces a data-driven method using a variational autoencoder to discover thermal illusions and cloaking by analyzing the geometry of high-dimensional thermal data in a latent space, enabling inverse design without complex models.
Contribution
It presents a novel latent-space geometric approach for thermal illusion and cloaking, leveraging deep learning to bypass traditional model constraints.
Findings
Achieved robust thermal illusion and cloaking with positive conductivities.
Demonstrated the method on a cylindrical shell with anisotropic conductivities.
Provided a new perspective for inverse design in wave systems.
Abstract
Illusion effects-where one object appears as another-arise from the non-uniqueness of physical systems, in which different material configurations yield identical external responses. Conventional approaches, such as coordinate transformation, map equivalent configurations but provide only specific solutions, while analytical or numerical optimization methods extend these designs by minimizing scattering yet remain constrained by model assumptions and computational cost. Here, we exploit this non-uniqueness through a data-driven framework that uses a variational autoencoder to compress high-dimensional thermal-field data into a compact latent space capturing geometrical relations between configurations and observations. In this latent space, thermal illusion corresponds to finding configurations that minimize geometric distance to a target configuration, with thermal cloaking as a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
