ORIGINAL ARTICLE
Optimized 3D-2D CNN for automatic mineral classification in hyperspectral images
1
Coding and Security of Information Laboratory (LACOSI), Department of Electronics, Faculty of Electrical Engineering, University of Science and Technology of Oran Mohamed-Boudiaf (USTOMB), 31000, Oran, Algeria
A - Research concept and design; B - Collection and/or assembly of data; C - Data analysis and interpretation; D - Writing the article; E - Critical revision of the article; F - Final approval of article
Submission date: 2024-04-19
Final revision date: 2024-10-01
Acceptance date: 2024-10-03
Publication date: 2024-11-06
Corresponding author
Youcef Attallah
Coding and Security of Information Laboratory (LACOSI), Department of Electronics, Faculty of Electrical Engineering, University of Science and Technology of Oran Mohamed-Boudiaf (USTOMB), 31000, Oran, Algeria
Coding and Security of Information Laboratory (LACOSI), Department of Electronics, Faculty of Electrical Engineering, University of Science and Technology of Oran Mohamed-Boudiaf (USTOMB), 31000, Oran, Algeria
Reports on Geodesy and Geoinformatics 2024;118:82-91
KEYWORDS
hyperspectral imagingmineral identificationOptimized 3D-2D CNNdiagnostic absorption bandfeature extraction
TOPICS
Image processing and machine learningSpaceborne, airborne and terrestrial platformsApplied Remote Sensing
ABSTRACT
Mineral classification using hyperspectral imaging represents an essential field of research improving the understanding of geological compositions. This study presents an advanced methodology that uses an optimized 3D-2D CNN model 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 SAM at 83.31 %. Beyond the precise identification of specific minerals, our methodology proves its versatility for broader applications in hyperspectral image analysis. The optimized 3D-2D CNN model excels in terms of mineral identification and sets a new standard for robust feature extraction and classification.
REFERENCES (39)
1.
Beiswenger Toya N, Gallagher Neal B, Myers Tanya L, Szecsody James E, Tonkyn Russell G, Su Yin-Fong, Sweet Lucas E, Lewallen Tricia A, Johnson Timothy 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.
2.
Bhatt Dulari, Patel Chirag, Talsania Hardik, Patel Jigar, Vaghela Rasmika, P, ya Sharnil, Modi Kirit, Ghayvat Hemant. (2021). CNN variants for computer vision: History, architecture, application, challenges and future scope. Electronics. 10 (20): 2470-2470. doi:10.3390/electronics10202470.
3.
Chakraborty Rupsa, Kereszturi Gabor, Pullanagari Reddy, Durance Patricia, Ashraf Salman, Anderson Chris. (2022). Mineral prospecting from biogeochemical and geological information using hyperspectral remote sensing – Feasibility and challenges. Journal of Geochemical Exploration. 232: 106900-106900. doi:10.1016/j.gexplo.2021.106900.
4.
Chang Chein-I. (1999). Spectral information divergence for hyperspectral image analysis. IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No. 99CH36293). 509-511. IEEE. doi:10.1109/IGARSS.1999.773549.
5.
De Carvalho O Abilio, Meneses Paulo Roberto. (2000). Spectral correlation mapper (SCM): An improvement on the spectral angle mapper (SAM). Summaries of the 9th JPL Airborne Earth Science Workshop, JPL Publication 00-18. 2-2. JPL publication Pasadena, CA, USA.
6.
Deng Kewang, Zhao Huijie, Li Na, Wei Wei. (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.
7.
Dennison Philip E, Halligan Kerry Q, Roberts Dar 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.
8.
El Rahman Sahar A. (2016). Hyperspectral image classification using unsupervised algorithms. International Journal of Advanced Computer Science and Applications. 7 (4).
9.
Farhadi Zari, Bevrani Hossein, Feizi-Derakhshi Mohammad-Reza. (2022). Combining regularization and dropout techniques for deep convolutional neural network. 2022 global energy conference (GEC). 335-339. IEEE. doi:10.1109/GEC55014.2022.9986657.
10.
Firat Hüseyin, Asker Mehmet Emin, Hanbay Davut. (2022). Classification of hyperspectral remote sensing images using different dimension reduction methods with 3D/2D CNN. Remote Sensing Applications: Society and Environment. 25: 100694-100694. doi:10.1016/j.rsase.2022.100694.
11.
Ghaderizadeh Saeed, Abbasi-Moghadam Dariush, Sharifi Alireza, Zhao Na, Tariq Aqil. (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.
12.
Gu Jiuxiang, Wang Zhenhua, Kuen Jason, Ma Lianyang, Shahroudy Amir, Shuai Bing, Liu Ting, Wang Xingxing, Wang Gang, Cai Jianfei, Chen T. (2018). Recent advances in convolutional neural networks. Pattern recognition. 77: 354-377. doi:10.1016/j.patcog.2017.10.013.
13.
Hecker Christoph, van Ruitenbeek Frank JA, van der Werff Harald MA, Bakker Wim H, Hewson Robert D, van der Meer Freek D. (2019). Spectral absorption feature analysis for finding ore: A tutorial on using the method in geological remote sensing. IEEE geoscience and remote sensing magazine. 7 (2): 51-71. doi:10.1109/MGRS.2019.2899193.
14.
Ige Ayokunle Olalekan, Sibiya Malusi. (2024). State-of-the-art in 1D Convolutional Neural Networks: A Survey. IEEE Access. : 144082-144105. doi:10.1109/ACCESS.2024.3433513.
15.
Jung Wonkyung, Jung Daejin, Kim Byeongho, Lee Sunjung, Rhee Wonjong, Ahn Jung Ho. (2019). Restructuring batch normalization to accelerate CNN training. Proceedings of Machine Learning and Systems. 1: 14-26.
16.
Kong Fanqiang, Hu Kedi, Li Yunsong, Li Dan, Liu Xin, Durrani Tariq S. (2022). A spectral-spatial feature extraction method 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.
17.
Kozoderov Vladimir, Kondranin Timofei, Dmitriev Egor, Kamentsev Vladimir. (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.
18.
Kumar Suresh, Gautam Ghosh, Saha SK. (2015). Hyperspectral remote sensing data derived spectral indices in characterizing salt-affected soils: A case study of Indo-Gangetic plains of India. Environmental Earth Sciences. 73: 3299-3308. doi:10.1007/s12665-014-3613-y.
19.
Langley Pat, Iba Wayne, Thompson Kevin. (1992). An analysis of Bayesian classifiers. Proceedings of the Tenth National Conference of Artificial Intelligence. 223-228.
20.
Laukamp Carsten, Rodger Andrew, LeGras Monica, Lampinen Heta, Lau Ian C, Pejcic Bobby, Stromberg Jessica, Francis Neil, Ramanaidou Erick. (2021). Mineral physicochemistry underlying feature-based extraction of mineral abundance and composition from shortwave, mid and thermal infrared reflectance spectra. Minerals. 11 (4): 347-347. doi:10.3390/min11040347.
21.
Li Qingbo, Niu Chunyang. (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.
22.
Li Ying, Zhang Haokui, Shen Qiang. (2017). Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing. 9 (1): 67-67. doi:10.3390/rs9010067.
23.
Ma Xiaotong, Man Qixia, Yang Xinming, Dong Pinliang, Yang Zelong, Wu Jingru, Liu Chunhui. (2023). Urban feature extraction within a complex urban area with an improved 3D-CNN using airborne hyperspectral data. Remote Sensing. 15 (4): 992-992. doi:10.3390/rs15040992.
24.
Mahlein A-K, Rumpf T, Welke P, Dehne H-W, Plümer L, Steiner U, 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.
25.
McHugh Mary L. (2012). Interrater reliability: The kappa statistic. Biochemia medica. 22 (3): 276-282.
26.
Mou Lichao, Ghamisi Pedram, Zhu Xiao Xiang. (2017). Deep recurrent neural networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing. 55 (7): 3639-3655. doi:10.1109/TGRS.2016.2636241.
27.
Ozdemir Akin, Polat Kemal. (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.
28.
Peyghambari Sima, Zhang Yun. (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.
29.
Ranjan Sameer, Nayak Deepak Ranjan, Kumar Kallepalli Satish, Dash Ratnakar, Majhi Banshidhar. (2017). Hyperspectral image classification: A k-means clustering based approach. 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS). 1-7. IEEE. doi:10.1109/ICACCS.2017.8014707.
30.
Rao Mengbin, Tang Ping, Zhang Zheng. (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.
31.
Roy Swalpa Kumar, Krishna Gopal, Dubey Shiv Ram, Chaudhuri Bidyut 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.
32.
Story Michael, Congalton Russell G. (1986). Accuracy assessment: A user’s perspective. Photogrammetric Engineering and remote sensing. 52 (3): 397-399.
33.
Swayze Gregg A, Clark Roger N, Goetz Alex, er FH, Livo K Eric, Breit George N, Kruse Fred A, Sutley Stephen J, Snee Lawrence W, Lowers Heather A, Post James L, Stoffregen Roger E., Ashley Roger 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.
34.
Tripathi Mahesh Kumar, Govil H. (2019). Evaluation of AVIRIS-NG hyperspectral images for mineral identification and mapping. Heliyon. 5 (11). doi:10.1016/j.heliyon.2019.e02931.
35.
Van der Meer Freek D, Van der Werff Harald MA, Van Ruitenbeek Frank JA, Hecker Chris A, Bakker Wim H, Noomen Marleen F, Van Der Meijde Mark, Carranza E John M, De Smeth J Boudewijn, Woldai Tsehaie. (2012). Multi-and 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.
36.
Wu Haibing, Gu Xiaodong. (2015). Towards dropout training for convolutional neural networks. Neural Networks. 71: 1-10. doi:10.1016/j.neunet.2015.07.007.
37.
Xing Yukun, Gomez Richard B. (2001). Hyperspectral image analysis using ENVI (environment for visualizing images). Geo-Spatial Image and Data Exploitation II. 79-86. SPIE. doi:10.1117/12.428244.
38.
Yuhas Roberta H, Goetz Alex, er FH, Boardman Joe W. (1992). Discrimination among semi-arid landscape endmembers using the spectral angle mapper (SAM) algorithm. JPL, Summaries of the Third Annual JPL Airborne Geoscience Workshop. Volume 1: AVIRIS Workshop.
39.
Zhang Chuan, Yi Min, Ye Fawang, Xu Qingjun, Li Xinchun, Gan Qingqing. (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): 5122-5122. doi:10.3390/rs14205122.
| eISSN: | 2391-8152 |
| ISSN: | 2391-8365 |
© 2006-2024 Journal hosting platform by Bentus
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
