In situ, non-destructive and rapid mineral mapping in tunnels with hyperspectral imaging

• An in-situ, non-destructive and rapid method for mineral mapping in tunnels is proposed. • Noise reduction of tunnel hyperspectral image is achieved via the integrated Spatial-Spectral Recurrent Transformer model. • A Dirichlet distribution-based mixed-pixel simulation approach is developed to replicate spectral mixing phenomena in tunnel settings. • Quantitative mineral abundance inversion is accomplished via integration of N-FINDR and fully constrained least squares (FCLS) algorithms. Hyperspectral imaging provides a novel approach for intelligent geological perception in tunnelling and underground engineering due to its high spectral resolution, nondestructive nature, and combined spectral-spatial information. However, in confined underground spaces, noise is often introduced by short exposure times, low illumination, and dust, and limited spatial resolution can cause mixed pixel effects, complicating data processing. This study presents an underground hyperspectral imaging-based mineral mapping method that achieves wall-rock visualization and semi-quantitative mineral mapping through image denoising and spectral unmixing. A spatial-spectral recurrent transformer U-Net (SSRT-UNet) is developed to reduce noise by leveraging spectral band correlations and nonlocal spatial-texture dependencies. A Dirichlet-based mixed pixel simulation is used to address spectral mixing, with the N-FINDR algorithm identifying endmember minerals, and the fully constrained least squares (FCLS) method to estimate mineral abundances. When applied to a water diversion tunnel in Shanxi, the method generates spatial distribution maps of dolomite and calcite. The experimental results confirm its effectiveness for intelligent geological logging and subsurface geological feature analysis.