Optimized 3D-2D CNN for automatic mineral classification in hyperspectral images

Attallah, Youcef; Zigh, Ehlem; Adda, Ali Pacha

doi:10.2478/rgg-2024-0017

Abstract

Mineral classification using hyperspectral imaging represents an essential field of research improving the understanding of geological compositions. This study presents an advancedmethodology that uses an optimized 3D-2D CNNmodel for automatic mineral identification and classification. Our approach includes such crucial steps as using the Diagnostic Absorption Band (DAB) selection technique to selectively extract bands that contain the absorption features of minerals for classification in the Cuprite zone. Focusing on the Cuprite dataset, our study successfully identified the following minerals: alunite, calcite, chalcedony, halloysite, kaolinite,montmorillonite,muscovite, and nontronite. The Cuprite dataset results with an overall accuracy rate of 95.73%underscore the effectiveness of our approach and a significant improvement over the benchmarks established by related studies. Specifically, ASMLP achieved a 94.67%accuracy rate, followed by 3D CNN at 93.86%, SAI-MLP at 91.03%, RNN at 89.09%, SPE-MLP at 85.53%, and SAMat 83.31 %. Beyond the precise identification of specific minerals, ourmethodology proves its versatility for broader applications in hyperspectral image analysis. The optimized 3D-2D CNNmodel excels in terms of mineral identification and sets a new standard for robust feature extraction and classification.

References

Beiswenger, T. N., Gallagher, N. B., Myers, T. L., Szecsody, J. E., Tonkyn, R. G., Su, Y.-F., Sweet, L. E., Lewallen, T. A., and Johnson, T. J. (2018). Identification of uranium minerals in natural U-bearing rocks using infrared reflectance spectroscopy. Applied Spectroscopy, 72(2):209–224, doi:10.1177/000370281774326.
Search in Google Scholar Back to article
Bhatt, D., Patel, C., Talsania, H., Patel, J., Vaghela, R., Pandya, S., Modi, K., and Ghayvat, H. (2021). CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics, 10(20):2470, doi:10.3390/electronics10202470.
Search in Google Scholar Back to article
Chakraborty, R., Kereszturi, G., Pullanagari, R., Durance, P., Ashraf, S., and Anderson, C. (2022). Mineral prospecting frombiogeochemical and geological information using hyperspectral remote sensing – Feasibility and challenges. Journal of Geochemical Exploration, 232:106900, doi:10.1016/j.gexplo.2021.106900.
Search in Google Scholar Back to article
Chang, C.-I. (1999). Spectral information divergence for hyperspectral image analysis. In IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS’99 (Cat. No. 99CH36293), volume 1, pages 509–511. IEEE, doi:10.1109/IGARSS.1999.773549.
Search in Google Scholar Back to article
De Carvalho, O. A. andMeneses, P. R. (2000). Spectral correlation mapper (SCM): An improvement on the spectral angle mapper (SAM). In Summaries of the 9th JPL Airborne Earth ScienceWorkshop, JPL Publication 00-18, volume 9, page 2. JPL publication Pasadena, CA, USA.
Search in Google Scholar Back to article
Deng, K., Zhao, H., Li, N., and Wei, W. (2021). Identification of minerals in hyperspectral imagery based on the attenuation spectral absorption index vector using a multilayer perceptron. Remote Sensing Letters, 12(5):449–458, doi:10.1080/2150704X.2021.1903612.
Search in Google Scholar Back to article
Dennison, P. E., Halligan, K. Q., and Roberts, D. A. (2004). A comparison of error metrics and constraints for multiple endmember spectral mixture analysis and spectral angle mapper. Remote Sensing of Environment, 93(3):359–367, doi:10.1016/j.rse.2004.07.013.
Search in Google Scholar Back to article
El Rahman, S. A. (2016). Hyperspectral image classification using unsupervised algorithms. International Journal of Advanced Computer Science and Applications, 7(4).
Search in Google Scholar Back to article
Farhadi, Z., Bevrani, H., and Feizi-Derakhshi,M.-R. (2022). Combining regularization and dropout techniques for deep convolutional neural network. In 2022 global energy conference (GEC), pages 335–339. IEEE, doi:10.1109/GEC55014.2022.9986657.
Search in Google Scholar Back to article
Fırat, H., Asker, M. E., and Hanbay, D. (2022). Classification of hyperspectral remote sensing images using different dimension reduction methods with 3D/2D CNN. Remote Sensing Applications: Society and Environment, 25:100694, doi:10.1016/j.rsase.2022.100694.
Search in Google Scholar Back to article
Ghaderizadeh, S., Abbasi-Moghadam, D., Sharifi, A., Zhao, N., and Tariq, A. (2021). Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14:7570–7588, doi:10.1109/JSTARS.2021.3099118.
Search in Google Scholar Back to article
Gu, J.,Wang, Z., Kuen, J.,Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X.,Wang, G., Cai, J., and Chen, T. (2018). Recent advances in convolutional neural networks. Pattern recognition, 77:354–377, doi:10.1016/j.patcog.2017.10.013.
Search in Google Scholar Back to article
Hecker, C., van Ruitenbeek, F. J., van derWerff, H.M., Bakker,W. H., Hewson, R.D., and van derMeer, F.D. (2019). Spectral absorption feature analysis for finding ore: A tutorial on using themethod in geological remote sensing. IEEE geoscience and remote sensing magazine, 7(2):51–71, doi:10.1109/MGRS.2019.2899193.
Search in Google Scholar Back to article
Ige, A. O. and Sibiya, M. (2024). State-of-the-art in 1D Convolutional Neural Networks: A survey. IEEE Access, pages 144082–144105, doi:10.1109/ACCESS.2024.3433513.
Search in Google Scholar Back to article
Jung,W., Jung, D., Kim, B., Lee, S., Rhee,W., and Ahn, J. H. (2019). Restructuring batch normalization to accelerate CNN training. Proceedings ofMachine Learning and Systems, 1:14–26.
Search in Google Scholar Back to article
Kong, F., Hu, K., Li, Y., Li, D., Liu, X., and Durrani, T. S. (2022). A spectral-spatial feature extractionmethod with polydirectional CNN for multispectral image compression. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15:2745–2758, doi:10.1109/JSTARS.2022.3158281.
Search in Google Scholar Back to article
Kozoderov, V., Kondranin, T., Dmitriev, E., and Kamentsev, V. (2015). Bayesian classifier applications of airborne hyperspectral imagery processing for forested areas. Advances in Space Research, 55(11):2657–2667, doi:10.1016/j.asr.2015.02.015.
Search in Google Scholar Back to article
Kumar, S., Gautam, G., and Saha, S. (2015). Hyperspectral remote sensing data derived spectral indices in characterizing saltaffected soils: A case study of Indo-Gangetic plains of India. Environmental Earth Sciences, 73:3299–3308, doi:10.1007/s12665-014-3613-y.
Search in Google Scholar Back to article
Langley, P., Iba, W., and Thompson, K. (1992). An analysis of Bayesian classifiers. In Proceedings of the Tenth National Conference of Artificial Intelligence, volume 90, pages 223–228.
Search in Google Scholar Back to article
Laukamp, C., Rodger, A., LeGras,M., Lampinen, H., Lau, I. C., Pejcic, B., Stromberg, J., Francis, N., and Ramanaidou, E. (2021). Mineral physicochemistry underlying feature-based extraction of mineral abundance and composition from shortwave, mid and thermal infrared reflectance spectra. Minerals, 11(4):347, doi:10.3390/min11040347.
Search in Google Scholar Back to article
Li, Q. and Niu, C. (2015). Feature-enhanced spectral similarity measure for the analysis of hyperspectral imagery. Journal of Applied Remote Sensing, 9(1):096008–096008, doi:10.1117/1.JRS.9.096008.
Search in Google Scholar Back to article
Li, Y., Zhang, H., and Shen, Q. (2017). Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing, 9(1):67, doi:10.3390/rs9010067.
Search in Google Scholar Back to article
Ma, X., Man, Q., Yang, X., Dong, P., Yang, Z., Wu, J., and Liu, C. (2023). Urban feature extraction within a complex urban area with an improved 3D-CNN using airborne hyperspectral data. Remote Sensing, 15(4):992, doi:10.3390/rs15040992.
Search in Google Scholar Back to article
Mahlein, A.-K., Rumpf, T., Welke, P., Dehne, H.-W., Plümer, L., Steiner, U., and Oerke, E.-C. (2013). Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment, 128:21–30, doi:10.1016/j.rse.2012.09.019.
Search in Google Scholar Back to article
McHugh, M. L. (2012). Interrater reliability: The kappa statistic. Biochemiamedica, 22(3):276–282.
Search in Google Scholar Back to article
Mou, L., Ghamisi, P., and Zhu, X. X. (2017). Deep recurrent neural networks for hyperspectral image classification. IEEE Transactions onGeoscience andRemote Sensing, 55(7):3639–3655, doi:10.1109/TGRS.2016.2636241.
Search in Google Scholar Back to article
Ozdemir, A. and Polat, K. (2020). Deep learning applications for hyperspectral imaging: A systematic review. Journal of the Institute of Electronics and Computer, 2(1):39–56, doi:10.33969/JIEC.2020.21004.
Search in Google Scholar Back to article
Peyghambari, S. and Zhang, Y. (2021). Hyperspectral remote sensing in lithological mapping, mineral exploration, and environmental geology: An updated review. Journal of Applied Remote Sensing, 15(3):031501–031501, doi:10.1117/1.JRS.15.031501.
Search in Google Scholar Back to article
Ranjan, S., Nayak, D. R., Kumar, K. S., Dash, R., andMajhi, B. (2017). Hyperspectral image classification: A k-means clustering based approach. In 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS), pages 1–7. IEEE, doi:10.1109/ICACCS.2017.8014707.
Search in Google Scholar Back to article
Rao, M., Tang, P., and Zhang, Z. (2019). Spatial-spectral relation network for hyperspectral image classification with limited training samples. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12):5086–5100, doi:10.1109/JSTARS.2019.2957047.
Search in Google Scholar Back to article
Roy, S. K., Krishna, G., Dubey, S. R., and Chaudhuri, B. B. (2019). HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 17(2):277–281, doi:10.1109/LGRS.2019.2918719.
Search in Google Scholar Back to article
Story, M. and Congalton, R. G. (1986). Accuracy assessment: A user’s perspective. PhotogrammetricEngineeringandremote sensing, 52(3):397–399.
Search in Google Scholar Back to article
Swayze, G. A., Clark, R.N., Goetz, A. F., Livo, K. E., Breit, G.N., Kruse, F. A., Sutley, S. J., Snee, L.W., Lowers, H. A., Post, J. L., Stoffregen, R. E., and Ashley, R. P. (2014). Mapping advanced argillic alteration at Cuprite, Nevada, using imaging spectroscopy. Economic geology, 109(5):1179–1221, doi:10.2113/econgeo.109.5.1179.
Search in Google Scholar Back to article
Tripathi,M.K. andGovil,H. (2019). Evaluation ofAVIRIS-NG hyperspectral images for mineral identification and mapping. Heliyon, 5(11), doi:10.1016/j.heliyon.2019.e02931.
Search in Google Scholar Back to article
Van der Meer, F. D., Van der Werff, H. M., Van Ruitenbeek, F. J., Hecker, C. A., Bakker,W. H., Noomen,M. F., Van DerMeijde,M., Carranza, E. J.M., De Smeth, J. B., andWoldai, T. (2012). Multiand hyperspectral geologic remote sensing: A review. International journal of applied Earth observation and geoinformation, 14(1):112–128, doi:10.1016/j.jag.2011.08.002.
Search in Google Scholar Back to article
Wu, H. and Gu, X. (2015). Towards dropout training for convolutional neural networks. Neural Networks, 71:1–10, doi:10.1016/j.neunet.2015.07.007.
Search in Google Scholar Back to article
Xing, Y. and Gomez, R. B. (2001). Hyperspectral image analysis using ENVI (environment for visualizing images). In Geo-Spatial Image and Data Exploitation II, volume 4383, pages 79–86. SPIE, doi:10.1117/12.428244.
Search in Google Scholar Back to article
Yuhas, R. H., Goetz, A. F., and Boardman, J.W. (1992). Discriminationamong semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm. In JPL, Summaries of the Third Annual JPL Airborne GeoscienceWorkshop. Volume 1: AVIRISWorkshop.
Search in Google Scholar Back to article
Zhang, C., Yi, M., Ye, F., Xu, Q., Li, X., and Gan, Q. (2022). Application and evaluation of deep neural networks for airborne hyperspectral remote sensing mineral mapping: A case study of the Baiyanghe uranium deposit in northwestern Xinjiang, China. Remote Sensing, 14(20):5122, doi:10.3390/rs14205122.
Search in Google Scholar Back to article

Optimized 3D-2D CNN for automatic mineral classification in hyperspectral images

Abstract

Paradigm

My account