convolutional neural networks; deep learning; hyperspectral imaging; Mineral classification; Convolutional neural network; Deep learning; Environmental Monitoring; Exploration and exploitation; HyperSpectral; Hyperspectral imaging systems; Industrial processs; Monitoring process; Short wave infrared; Electronic, Optical and Magnetic Materials; Condensed Matter Physics; Computer Science Applications; Applied Mathematics; Electrical and Electronic Engineering
Abstract :
[en] The correct identification of minerals is crucial task for the exploration and exploitation of mineral resources, environmental monitoring, and industrial processes. In this article, we propose a hyperspectral imaging system and classification model to identify nine types of minerals. To accomplish this, we employed a hyperspectral shortwave infrared (SWIR) camera to capture hyperspectral images. We then introduce a convolutional neural network (CNN) architecture that considers only spectral data, complemented by a fully connected network for classification. To prevent overfitting, we implemented the dropout technique, which enables random deactivation of neurons during the backpropagation process. This results in improved performance during the training phase and a better generalization capacity. Training was optimized to minimize the categorical cross-entropy objective function, and the model was evaluated during training using an accuracy metric. Finally, we evaluated the results with the test data using accuracy, recall, and precision metrics, and achieved 98.52%, 98.25%, and 98.68%, respectively. Our source code is available at https://github.com/jcifuenr/Spec-CNN.
Disciplines :
Geological, petroleum & mining engineering
Author, co-author :
Cifuentes, José I.; University of Concepción, Concepción, Chile ; Center for Ocean Technology and Instrumentation, Concepción, Chile
Arias, Luis E.; University of Concepción, Concepción, Chile
Pirard, Eric ; Université de Liège - ULiège > Département ArGEnCo > Géoressources minérales & Imagerie géologique
Castillo, Fernando; University of Concepción, Concepción, Chile
Language :
English
Title :
Mineral Classification using Convolutional Neural Networks and SWIR Hyperspectral Imaging
Publication date :
2024
Event name :
AI and Optical Data Sciences V
Event place :
San Francisco, Usa
Event date :
29-01-2024 => 01-02-2024
Main work title :
AI and Optical Data Sciences V
Editor :
Kitayama, Ken-ichi
Publisher :
International Society for Optical Engineering (SPIE)
ISBN/EAN :
978-1-5106-7066-2
Peer review/Selection committee :
Editorial reviewed
Funders :
SPIE - Society of Photo-Optical Instrumentation Engineers
Funding text :
I am pleased to acknowledge that this work was financially supported by FONDECYT 1211184.
Rajan Girija, R. and Mayappan, S., “Mapping of mineral resources and lithological units: A review of remote sensing techniques,” International Journal of Image and Data Fusion 10(2), 79–106 (2019).
Tusa, L., Andreani, L., Khodadadzadeh, M., Contreras, C., Ivascanu, P., Gloaguen, R., and Gutzmer, J., “Mineral mapping and vein detection in hyperspectral drill-core scans: Application to porphyry-type mineralization,” Minerals 9(2), 122 (2019).
Long, T., Zhou, Z., Hancke, G., Bai, Y., and Gao, Q., “A review of artificial intelligence technologies in mineral identification: classification and visualization,” Journal of Sensor and Actuator Networks 11(3), 50 (2022).
Chen, Z., Liu, X., Yang, J., Little, E., and Zhou, Y., “Deep learning-based method for sem image segmentation in mineral characterization, an example from duvernay shale samples in western canada sedimentary basin,” Computers & Geosciences 138, 104450 (2020).
Liu, Y., Zhang, Z., Liu, X., Lei, W., and Xia, X., “Deep learning based mineral image classification combined with visual attention mechanism,” IEEE Access 9, 98091–98109 (2021).
Wang, W., Liu, L., Zhang, T., Shen, J., Wang, J., and Li, J., “Hyper-es2t: efficient spatial–spectral transformer for the classification of hyperspectral remote sensing images,” International Journal of Applied Earth Observation and Geoinformation 113, 103005 (2022).
Sun, Y., Liu, B., Yu, X., Yu, A., Zhang, P., and Xue, Z., “Exploiting discriminative advantage of spectrum for hyperspectral image classification: Spectralformer enhanced by spectrum motion feature,” IEEE Geoscience and Remote Sensing Letters 20, 1–5 (2022).
Tanaka, S., Tsuru, H., Someno, K., and Yamaguchi, Y., “Identification of alteration minerals from unstable reflectance spectra using a deep learning method,” Geosciences 9(5), 195 (2019).
Yang, N., Zhang, Z., Yang, J., and Hong, Z., “Applications of data augmentation in mineral prospectivity prediction based on convolutional neural networks,” Computers & geosciences 161, 105075 (2022).
Sang, X., Zhou, R.-g., Li, Y., and Xiong, S., “One-dimensional deep convolutional neural network for mineral classification from raman spectroscopy,” Neural Processing Letters , 1–14 (2022).
Xu, Y. and Zuo, R., “Geochemical survey data cube: A useful tool for lithological classification and geochemical anomaly identification,” Geochemistry , 125959 (2023).
Dougherty, E. R., [Digital image processing methods], CRC Press (2020).
Becker, B., Vaccari, M., Prescott, M., and Grobler, T., “Cnn architecture comparison for radio galaxy classification,” Monthly Notices of the Royal Astronomical Society 503(2), 1828–1846 (2021).
Loshchilov, I. and Hutter, F., “Decoupled weight decay regularization,” arXiv preprint arXiv:1711.05101 (2017).
Chen, T. and Guestrin, C., “Xgboost: A scalable tree boosting system,” in [Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining], 785–794 (2016).
Bishop, C. M. and Nasrabadi, N. M., [Pattern recognition and machine learning], vol. 4, Springer (2006).
