AI-enabled real-time dual-comb molecular fingerprint imaging

Abstract

Hyperspectral imaging provides spatially resolved spectral information. Utilizing dual-frequency combs as active illumination sources, hyperspectral imaging with ultra-high spectral resolution can be implemented in a scan-free manner when a detector array is used for heterodyne detection. Here, we show that dual-comb hyperspectral imaging can be performed with an uncooled near-to-mid-infrared detector by exploiting the detector array's high frame rate, achieving 10 Hz acquisition in 30 spectral channels across 16,384 pixels. Artificial intelligence (AI) enables real-time data reduction and imaging of gas concentration based on characteristic molecular absorption signatures. Owing to the detector array's sensitivity from 1 to 5 µm wavelength, this demonstration lays the foundation for real-time versatile imaging of molecular fingerprint signatures across the infrared wavelength regime with high temporal resolution.