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

Abstract

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 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 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.

Keywords

Hyperspectral imaging / Underground space / Geological analysis / Mineral mapping / Hyperspectral noise reduction / Hyperspectral unmixing

References

[1] Akgül, M. A., & Ural, S. (2024). The study of mineral distribution using hyperspectral Hyperion data along the shores of Lake Salda/Türkiye. Environmental Earth Sciences, 83(7), 219.

[2] Akgün, H., Muratlı, S., & Koçkar, M. K. (2014). Geotechnical investigations and preliminary support design for the Geçilmez tunnel: A case study along the Black Sea coastal highway, Giresun, northern Turkey. Tunnelling and Underground Space Technology, 40, 277-299.

[3] Ali, A., Chiang, Y. W., & Santos, R. M. (2022). X-ray diffraction techniques for mineral characterization: A review for engineers of the fundamentals, applications, and research directions. Minerals, 12(2), 205.

[4] Baik, H., Son, Y. S., & Kim, K. E. (2023). A tunnel coaxial 3D hyperspectral scanning system for underground mine investigation. Scientific Reports, 13(1), 10417.

[5] Bhargava, A., Sachdeva, A., Sharma, K., Alsharif, M. H., Uthansakul, P., & Uthansakul, M. (2024). Hyperspectral imaging and its applications: A review. Heliyon, 10(12), e33208.

[6] Bhasin, R., Barton, N., Grimstad, E., & Chryssanthakis, P. (1995). Engineering geological characterization of low strength anisotropic rocks in the Himalayan region for assessment of tunnel support. Engineering Geology, 40(3-4), 169-193.

[7] Bodrito, T., Zouaoui, A., Chanussot, J., & Mairal, J. (2021). A trainable spectral-spatial sparse coding model for hyperspectral image restoration. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS’21) (pp. 5340-5442).

[8] Bu, Y. Y., Zhao, Y. Q., Xue, J. Z., Kong, S. G., Yao, J. X., Chan, J. C. W., Liu, P., & Zhang, X. (2025). Transductive gradient injection for improved hyperspectral image denoising. Engineering Applications of Artificial Intelligence, 143, 109973.

[9] Chang, Y., Yan, L. X., & Zhong, S. (2017). Hyper-laplacian regularized unidirectional low-rank tensor recovery for multispectral image denoising. In Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5901-5909).

[10] Chen, C. W., Yang, H. Q., Song, K. L., Liang, D., Zhang, Y. H., & Ni, J. H. (2023). Dissolution feature differences of carbonate rock within hydro-fluctuation belt located in the Three Gorges Reservoir Area. Engineering Geology, 327, 107362.

[11] Chen, T. T., Leng, C. C., Pei, Z., Peng, J. Y., & Basu, A. (2024). Multimanifold bistructured low rank representation of hyperspectral images. Infrared Physics & Technology, 136, 105039.

[12] Deng, F., Pu, J., Huang, Y., & Han, Q. D. (2023). 3D geological suitability evaluation for underground space based on the AHP-cloud model. Underground Space, 8, 109-122.

[13] Ducasse, E., Adeline, K., Hohmann, A., Achard, V., Bourguignon, A., Grandjean, G., & Briottet, X. (2024). Mapping of clay montmorillonite abundance in agricultural fields using unmixing methods at centimeter scale hyperspectral images. Remote Sensing, 16(17), 3211.

[14] George, E. B., Ternikar, C. R., Ghosh, R., Nagesh Kumar, D., Gomez, C., Ahmad, T., Sahadevan, A. S., Gupta, P. K., & Misra, A. (2024). Assessment of spectral reduction techniques for endmember extraction in unmixing of hyperspectral images. Advances in Space Research, 73(2), 1237-1251.

[15] Ghosh, P., Roy, S. K., Koirala, B., Rasti, B., & Scheunders, P. (2022). Hyperspectral unmixing using transformer network. IEEE Transactions on Geoscience and Remote Sensing, 60, 5535116.

[16] Govil, H., Gill, N., Rajendran, S., Santosh, M., & Kumar, S. (2018). Identification of new base metal mineralization in Kumaon Himalaya, India, using hyperspectral remote sensing and hydrothermal alteration. Ore Geology Reviews, 92, 271-283.

[17] Guo, Y. J., Lyu, S., Xiao, H. R., Liu, Y., Chen, R. F., Zhang, X. Q., Xiao, S., & Wu, G. N. (2025). Evaluation of the hygrothermal aging state of composite insulators based on hyperspectral imaging technology and the IDBO-BiGRU model. Measurement, 253, 117446.

[18] He, J. P., Riley, D. N., & Barton, I. (2024). Is endmember extraction a critical step in the analysis of hyperspectral images in mining environments? Remote Sensing, 16(12), 2137.

[19] He, W., Yao, Q. M., Li, C., Yokoya, N., Zhao, Q. B., Zhang, H. Y., & Zhang, L. P. (2020). Non-local meets global: An integrated paradigm for hyperspectral image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4), 2089-2107.

[20] Huang, H. W., Wang, C. S., Zhou, M. L., & Qu, L. Q. (2024). Compressive strength detection of tunnel lining using hyperspectral images and machine learning. Tunnelling and Underground Space Technology, 153, 105979.

[21] Jia, J. X., Wang, Y. M., Cheng, X. Y., Yuan, L. Y., Zhao, D., Ye, Q., Zhuang, X. Q., Shu, R., & Wang, J. Y. (2019). Destriping algorithms based on statistics and spatial filtering for visible-to-thermal infrared pushbroom hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 57(6), 4077-4091.

[22] Klose, C. D., Loew, S., Giese, R., & Borm, G. (2007). Spatial predictions of geological rock mass properties based on in-situ interpretations of multi-dimensional seismic data. Engineering Geology, 93(3-4), 99-116.

[23] Kurz, T. H., Miguel, G. S., Dubucq, D., Kenter, J., Miegebielle, V., & Buckley, S. J. (2022). Quantitative mapping of dolomitization using close-range hyperspectral imaging: Kimmeridgian carbonate ramp, Alacón, NE Spain. Geosphere, 18(2), 780-799.

[24] Liu, B., Yu, X. C., Yu, A. Z., Zhang, P. Q., & Wan, G. (2018). Spectral-spatial classification of hyperspectral imagery based on recurrent neural networks. Remote Sensing Letters, 9(12), 1118-1127.

[25] Liu, F. M., Lin, P., Xu, Z. H., Shao, R. Q., & Han, T. (2023). Extraction and imaging of indicator elements for non-destructive, in-situ, fast identification of adverse geology in tunnels. International Journal of Mining Science and Technology, 33(12), 1437-1449.

[26] Liu, T. X., Zhang, C. P., Li, W., Tu, S. Q., Wang, L. B., & Jin, Z. X. (2025). Face failure mechanism of fault tunnels under high-temperature and high-pressure conditions using the discrete element method. Computers and Geotechnics, 179, 107059.

[27] Lobo, A., Garcia, E., Barroso, G., Martí, D., Fernandez-Turiel, J. L., & Ibáñez-Insa, J. (2021). Machine learning for mineral identification and ore estimation from hyperspectral imagery in tin-tungsten deposits: Simulation under indoor conditions. Remote Sensing, 13(16), 3258.

[28] Lu, M., Zhang, J., Lyu, Q., & Zhang, L. L. (2023). Assessing the annual probability of rainfall-induced slope failure based on intensity-duration-frequency (IDF) curves. Natural Hazards, 117(1), 763-778.

[29] McCormick, C. A., Corlett, H., Stacey, J., Hollis, C., Feng, J. L., Rivard, B., & Omma, J. E. (2021). Shortwave infrared hyperspectral imaging as a novel method to elucidate multi-phase dolomitization, recrystallization, and cementation in carbonate sedimentary rocks. Scientific Reports, 11(1), 21732.

[30] McElderry, J. D. P., Zhu, P. Z., Mroue, K. H., Xu, J. D., Pavan, B., Fang, M., Zhao, G. S., McNerny, E., Kohn, D. H., Franceschi, R. T., Holl, M. M. B., Tecklenburg, M. M. J., Ramamoorthy, A., & Morris, M. D. (2013). Crystallinity and compositional changes in carbonated apatites: Evidence from 31P solid-state NMR, Raman, and AFM analysis. Journal of Solid State Chemistry, 206, 192-198.

[31] Meng, Y., Li, G. Y., & Huang, W. (2024). Adaptive shadow compensation method in hyperspectral images via multi-exposure fusion and edge fusion. Applied Sciences, 14(9), 3890.

[32] Okada, N., Maekawa, Y., Owada, N., Haga, K., Shibayama, A., & Kawamura, Y. (2020). Automated identification of mineral types and grain size using hyperspectral imaging and deep learning for mineral processing. Minerals, 10(9), 809.

[33] Peng, X., Wang, P. T., Zhou, K., Yan, Z. P., Zhong, X. G., & Zhao, C. (2025). Bridge defect detection using small sample data with deep learning and hyperspectral imaging. Automation in Construction, 170, 105900.

[34] Shah, D., Trivedi, Y., Bhattacharya, B., Thakkar, P., & Srivastava, P. (2025). Hyperspectral endmember extraction using convexity based purity index. Advances in Space Research, 75(1), 465-480.

[35] Son, Y. S., Noh, S. G., Bang, E. S., Kim, K. E., Cho, S. J., & Baik, H. (2022). Ground-based visible-near infrared hyperspectral imaging for monitoring cliff weathering of a volcanic island in Dokdo, South Korea. Engineering Geology, 309, 106854.

[36] Tao, X. W., Paoletti, M. E., Wu, Z. Y., Haut, J. M., Ren, P., & Plaza, A. (2024). An abundance-guided attention network for hyperspectral unmixing. IEEE Transactions on Geoscience and Remote Sensing, 62, 5505414.

[37] Wang, L. G., Liu, D. F., & Wang, Q. M. (2013). Geometric method of fully constrained least squares linear spectral mixture analysis. IEEE Transactions on Geoscience and Remote Sensing, 51(6), 3558-3566.

[38] Wang, X. F., Wei, Y. Y., Jiang, T., Hao, F. X., & Xu, H. F. (2024a). Elastic-plastic criterion solution of deep roadway surrounding rock based on intermediate principal stress and Drucker-Prager criterion. Energy Science & Engineering, 12(6), 2472-2492.

[39] Wang, Y. X., Liu, B., Wang, J. W., Meng, Q. Y., & Liu, Z. Y. (2024b). Analysis of quartz content in muck based on artificial intelligence algorithms and laser-induced breakdown spectroscopy in TBM tunneling. Bulletin of Engineering Geology and the Environment, 83(8), 314.

[40] Wang, Y. Z., Cao, H. J., Chen, J., Liu, C. Q., Lu, X. J., Yin, C. X., Fu, X. H., Qiao, L., Zhang, G., Liu, C. B., Zhang, P., & Ling, Z. C. (2025). New maps of mafic mineral abundances in global mare units on the Moon. ISPRS Journal of Photogrammetry and Remote Sensing, 224, 348-360.

[41] Wu, C. C., Chen, H. M., & Chang, C. I. (2012). Real-time N-finder processing algorithms for hyperspectral imagery. Journal of Real-Time Image Processing, 7(2), 105-129.

[42] Xiong, F. C., Zhou, J., Zhao, Q. L., Lu, J. F., & Qian, Y. T. (2022). MAC-Net: Model-aided nonlocal neural network for hyperspectral image denoising. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-14.

[43] Xu, Z. H., Li, S., Lin, P., & Li, Q. J. (2025a). Non-destructive, fast and intelligent identification of coal and gangue via spatial-spectral fusion of hyperspectral images. International Journal of Rock Mechanics and Mining Sciences, 194, 106187.

[44] Xu, Z. H., Li, S., Lin, P., Shi, H., & Lou, Y. F. (2025b). Partition feature extraction of hyperspectral images for in situ intelligent lithology identification. Journal of Rock Mechanics and Geotechnical Engineering, 17(12), 7736-7752.

[45] Xu, Z. H., Yu, T. F., Lin, P., & Li, S. C. (2023). Adverse geology identification through mineral anomaly analysis during tunneling: Methodology and case study. Engineering, 27, 150-160.

[46] Xu, Z. H., Yu, T. F., Lin, P., Wang, W. Y., & Shao, R. Q. (2022). Integrated geochemical, mineralogical, and microstructural identification of faults in tunnels and its application to TBM jamming analysis. Tunnelling and Underground Space Technology, 128, 104650.

[47] Yang, L., Yang, D., Zhang, M. Y., Meng, S. W., Wang, S. L., Su, Y. T., & Xu, L. (2024). Application of nano-scratch technology to identify continental shale mineral composition and distribution length of bedding interfacial transition zone-A case study of Cretaceous Qingshankou formation in Gulong Depression, Songliao Basin, NE China. Geoenergy Science and Engineering, 234, 212674.

[48] Zahiri, Z., Laefer, D. F., Kurz, T., Buckley, S., & Gowen, A. (2022). A comparison of ground-based hyperspectral imaging and red-edge multispectral imaging for façade material classification. Automation in Construction, 136, 104164.

[49] Zhang, H. M., Li, X. J., Liu, J. F., Wang, Y. P., Guo, L., Wu, Z. Y., & Tian, Y. F. (2025a). A fractal characteristics analysis of the pore throat structure in low-permeability sandstone reservoirs: A case study of the Yanchang formation, Southeast Ordos Basin. Fractal and Fractional, 9(4), 224.

[50] Zhang, J., Sun, Y., Hu, J. Z., & Huang, H. W. (2023). Assessing site investigation program for design of shield tunnels. Underground Space, 9, 31-42.

[51] Zhang, T. H., Zhao, J. L., Fang, S., Li, Z., Zhang, Q., & Gong, M. G. (2025b). Hyperspectral image restoration via the collaboration of low-rank tensor denoising and completion. Pattern Recognition, 165, 111629.

[52] Zhao, L. L., Hong, H. L., Liu, J. C., Fang, Q., Yao, Y. Z., Tan, W., Yin, K., Wang, C. W., Chen, M., & Algeo, T. J. (2018). Assessing the utility of visible-to-shortwave infrared reflectance spectroscopy for analysis of soil weathering intensity and paleoclimate reconstruction. Palaeogeography, Palaeoclimatology, Palaeoecology, 512, 80-94.

[53] Zhou, H., Zhang, C. Q., Li, Z., Hu, D. W., & Hou, J. (2014). Analysis of mechanical behavior of soft rocks and stability control in deep tunnels. Journal of Rock Mechanics and Geotechnical Engineering, 6(3), 219-226.