Physics-Informed Spectral Modeling for Hyperspectral Imaging
Abstract
We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. PhISM outperforms previous methods on several classification and regression benchmarks, requires limited labeled data, and provides additional insights thanks to its interpretable latent representation.
Fields of Study & Subjects
Generative Adversarial Networks and Image Synthesis
Machine Learning in Materials Science
Stochastic Gradient Optimization Techniques
Publication details
- Journal / source
- IEEE Geoscience and Remote Sensing Letters
- Publisher
- Institute of Electrical and Electronics Engineers (IEEE)
- Volume
- 23
- Pages
- 1–5
- Publication date
- 1 January 2026
- Language
- EN