Learned Design of a Compressive Hyperspectral Imager for Remote Sensing by a Physics-Constrained Autoencoder

Yaron Heiser, Adrian Stern

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Designing and optimizing systems by end-to-end deep learning is a recently emerging field. We present a novel physics-constrained autoencoder (PyCAE) for the design and optimization of a physically realizable sensing model. As a case study, we design a compressive hyperspectral imaging system for remote sensing based on this approach, which allows capturing hundreds of spectral bands with as few as four compressed measurements. We demonstrate our deep learning approach to design spectral compression with a spectral light modulator (SpLM) encoder and a reconstruction neural network decoder. The SpLM consists of a set of modified Fabry–Pérot resonator (mFPR) etalons that are designed to have a staircase-shaped geometry. Each stair occupies a few pixel columns of a push-broom-like spectral imager. The mFPR’s stairs can sample the earth terrain in along-track scanning from an airborne or spaceborne moving platform. The SpLM is jointly designed with an autoencoder by a data-driven approach, while spectra from remote sensing databases are used to train the system. The SpLM’s parameters are optimized by integrating its physically realizable sensing model in the encoder part of the PyCAE. The decoder part of the PyCAE implements the spectral reconstruction.

Original languageEnglish
Article number3766
JournalRemote Sensing
Issue number15
StatePublished - 1 Aug 2022


  • compressive hyperspectral imaging
  • deep learning
  • design learning
  • remote sensing

ASJC Scopus subject areas

  • Earth and Planetary Sciences (all)


Dive into the research topics of 'Learned Design of a Compressive Hyperspectral Imager for Remote Sensing by a Physics-Constrained Autoencoder'. Together they form a unique fingerprint.

Cite this