Spectral kernel machines with electrically tunable photodetectors
Spectral machine vision collects spectral and spatial information as three-dimensional hypercubes and digitally processes them, which causes a data bottleneck, limiting power efficiency, frame rate, and spectral-spatial resolution. This work introduces spectral kernel machines (SKMs) to overcome these bottlenecks. SKM directly compresses spectral analysis through the output photocurrent and learns from example objects to identify and classify new samples in a "sniff-and-seek" mode. We experimentally demonstrated SKMs with electrically tunable bipolar black phosphorus-molybdenum disulfide (bP-MoS<sub>2</sub>) photodiodes in the near- and mid-infrared band and silicon photoconductors in the visible band, performing versatile intelligent tasks from chemometrics to semiconductor metrology. This architecture consumed substantially less power and was more than an order of magnitude faster than existing solutions for hyperspectral image analysis, defining an intelligent imaging and sensing paradigm with intriguing possibilities.
Authors
- Dehui Zhang (ORCID: https://orcid.org/0000-0002-7077-0639)
- Aydogan Özcan (ORCID: https://orcid.org/0000-0002-0717-683X)
- Ali Javey (ORCID: https://orcid.org/0000-0001-7214-7931)
- Hyong Min Kim (ORCID: https://orcid.org/0000-0002-0094-4189)
- Naoki Higashitarumizu (ORCID: https://orcid.org/0000-0003-3996-6753)
- I. K. M. Reaz Rahman (ORCID: https://orcid.org/0000-0003-3911-4681)
- Theodorus Jonathan Wijaya (ORCID: https://orcid.org/0000-0003-3947-0029)
- Shifan Wang (ORCID: https://orcid.org/0000-0002-9866-1434)
- Inha Kim (ORCID: https://orcid.org/0009-0002-7870-7682)
- James Bullock (ORCID: https://orcid.org/0000-0001-7903-9642)
- Jamie Geng (ORCID: https://orcid.org/0009-0003-8707-6533)
- Yuhang Li (ORCID: https://orcid.org/0000-0002-9364-4125)
- Marco Ma (ORCID: https://orcid.org/0009-0004-7584-0917)
- Dorottya Urmossy
Institutions
- California NanoSystems Institute (US)
- Tokyo University of Information Sciences (JP)
- Lawrence Berkeley National Laboratory (US)
- University of California, Los Angeles (US)
- The University of Melbourne (AU)
- Kavli Energy NanoScience Institute (US)
- The University of Tokyo (JP)
- University of California, Berkeley (US)
Publication Details
- Journal
- Science
- Published
- 2025-11-27
- DOI
- https://doi.org/10.1126/science.ady6571
- Citations
- 1
- Primary Topic
- Transition Metal Oxide Nanomaterials
- Type
- article
- Field-Weighted Citation Impact
- 0.61