UC Davis Develops Silicon Spectrometer-On-A-Chip With AI

Researchers at the University of California, Davis have developed a compact spectrometer-on-a-chip designed to enhance hyperspectral sensing while dramatically reducing device size. The work focuses on shrinking a lab-grade spectrometer to a footprint small enough for integration into portable and embedded systems.

As described by the research team, and recently reported in Advanced Photonics, the project “aimed to shrink a lab-grade spectrometer down to the size of a grain of sand, a tiny spectrometer-on-a-chip that can be integrated into portable devices.”

“We wanted to take the power of a spectrometer out of the lab and put it in your pocket,” commented Ahasan Ahamed of UC Davis.

Efforts to miniaturize infrared sensing devices have been the subject of extensive research, often relying on modified photodetectors with enhanced optical properties. Previous work in this area includes projects incorporating colloidal quantum dots into sensors for both consumer electronics and specialized space applications.

The UC Davis device exploits photon-trapping surface textures (PTST), surface modifications that enhance the light absorption capabilities of silicon photodiodes in the near-infrared (NIR) by coupling incident light into guided modes that effectively increase the optical path length.

“The enhanced light absorption capabilities of PTST improve the efficiency and sensitivity of the photodiodes, which in turn boost the efficacy of the spectrometer-on-a-chip at NIR wavelengths,” noted the project in its paper.

The chip integrates 16 distinct silicon detectors, with PTST extending performance at near-IR wavelengths where silicon absorption is typically low. A neural network then reconstructs spectral information from the measured photocurrents, enabling accurate spectral analysis with minimal hardware.

According to UC Davis, integrating deep learning into the system represents a key step toward AI-augmented spectral sensing. Neural networks allow compact hardware to achieve spectral fidelity traditionally associated only with bulky laboratory spectrometers.

In proof-of-concept trials, the research team fabricated a sensor with a footprint of just 0.4 mm² and evaluated its performance in hyperspectral imaging scenarios. The results demonstrated high accuracy and fidelity, with AI-based spectral reconstruction enabling reliable hyperspectral data extraction despite limited detector hardware.

The device also maintained signal clarity in the presence of significant electrical interference, outperforming conventional spectrometer designs. This characteristic could be particularly valuable in portable and low-cost electronic systems, where noise immunity is often a limiting factor.

By extending silicon sensing into the near-infrared and combining photonic design with machine learning, the technology establishes a pathway for integrated, real-time hyperspectral sensing across applications ranging from medical diagnostics to environmental monitoring.

“We are paving the way for a future where your watch or phone doesn’t just take pictures, but analyzes the chemistry of the world around you,” said project leader Saif Islam of UC Davis.

About the University of California, Davis (UC Davis)

The University of California, Davis is a public research university recognized for interdisciplinary research across engineering, photonics, materials science, and applied sensing technologies. UC Davis researchers conduct work spanning optical devices, semiconductor systems, and data-driven methods supporting scientific, industrial, and environmental applications. For more information, please click here.

Source/Photo Credit: UC Davis

---

(Editor’s Note: All trademarks mentioned in this article, including company names, product names, and logos, are the property of their respective owners. Use of these trademarks is for informational purposes only and does not imply any endorsement.)