Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
Abstract
:1. Introduction
2. Proposed HSS-LSTM Framework
2.1. Spatial Features with CNN-Based Model
2.2. Fusion Spatial-Spectral Feature
2.3. Hierarchical Spatial-Spectral Feature with LSTM-Based Model
3. Experimental Results and Analysis
3.1. Experimental Data
3.2. Analysis of Parameter Settings
3.3. Identification Results of the Nevada Dataset
3.4. Discussion
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Hunt, G.R. Spectral signatures of particulate minerals in the visible and near infrared. Geophysics 2012, 42, 501. [Google Scholar] [CrossRef] [Green Version]
- Porwal, A.K.; Kreuzer, O.P. Introduction to the special issue: Mineral prospectivity analysis and quantitative resource estimation. Ore Geol. Rev. 2010, 38, 121–127. [Google Scholar] [CrossRef]
- Landgrebe, D. Hyperspectral image data analysis. IEEE Signal Process. Mag. 2002, 19, 17–28. [Google Scholar] [CrossRef]
- Bioucas-Dias, J.M.; Plaza, A.; Camps-Valls, G.; Scheunders, P.; Nasrabadi, N.; Chanussot, J. Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci. Remote Sens. Lett. 2013, 1, 6–36. [Google Scholar] [CrossRef] [Green Version]
- Zhao, H.; Zhang, L.; Zhao, X.; Yang, H.; Yang, K.; Zhang, X.; Wang, S.; Sun, H. A new method of mineral absorption feature extraction from vegetation covered area. In Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10–15 July 2016; pp. 5437–5440. [Google Scholar]
- Ni, L.; Wu, H. Mineral Identification and Classification by Combining Use of Hyperspectral VNIR/SWIR and Multispectral TIR Remotely Sensed Data. In Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, Japan, 28 July 2019; pp. 3317–3320. [Google Scholar]
- Vignesh, K.M.; Kiran, Y. Comparative analysis of mineral mapping for hyperspectral and multispectral imagery. Arab. J. Geosci. 2020, 13, 1–12. [Google Scholar] [CrossRef]
- Vane, G.; Green, R.O.; Chrien, T.G.; Enmark, H.T.; Hansen, E.G.; Porter, W.M. The airborne visible/infrared imaging spectrometer (AVIRIS). Remote Sens. Environ. 1987, 44, 127–143. [Google Scholar] [CrossRef]
- Clark, R.N.; Swayze, G.A.; Livo, K.E.; Kokaly, R.F.; Sutley, S.J.; Dalton, J.B.; McDougal, R.R.; Gent, C.A. Imaging spectroscopy: Earth and planetary remote sensing with the USGS Tetracorder and expert systems. J. Geophys. Res. Planets 2003, 108, 5131. [Google Scholar] [CrossRef]
- Baugh, W.M.; Kruse, F.A.; Atkinson, W.W. Quantitative Geochemical Mapping of Ammonium Minerals in the Southern Cedar Mountains, Nevada, Using the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). Remote Sens. Environ. 1998, 65, 292–308. [Google Scholar] [CrossRef]
- Camps–Valls, G. Kernel spectral angle mapper. Electron. Lett. 2016, 52, 1218–1220. [Google Scholar] [CrossRef]
- De Carvalho, O.A.; de Carvalho, A.P.F.; Guimarães, R.F.; Lopes, R.A.S.; Guimaraes, P.A.; de Souza Martins, E.; Pedreño, J.N. Classification of hyperspectral image using SCM methods for geobotanical analysis in the Brazilian savanna region. In Proceedings of the 2003 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Toulouse, France, 21–25 July 2003; pp. 3754–3756. [Google Scholar]
- Balas, C.; Epitropou, G.; Tsapras, A.; Hadjinicolaou, N. Hyperspectral imaging and spectral classification for pigment identification and mapping in paintings by El Greco and his workshop. Multimedia Tools Appl. 2018, 77, 9737–9751. [Google Scholar] [CrossRef]
- Ren, Z.; Sun, L.; Zhai, Q.; Liu, X. Mineral Mapping with Hyperspectral Image Based on an Improved K–Means Clustering Algorithm. In Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, Japan, 28 July 2019; pp. 2989–2992. [Google Scholar]
- Amer, R.; Al Mezayen, A.; Hasanein, M. ASTER spectral analysis for alteration minerals associated with gold mineralization. Ore Geol. Rev. 2016, 75, 239–251. [Google Scholar] [CrossRef]
- Clark, R.N.; King, T.V.V.; Klejwa, M.; Swayze, G.A.; Vergo, N. High spectral resolution reflectance spectroscopy of minerals. J. Geophys. Res. Solid Earth 1990, 95, 12653–12680. [Google Scholar] [CrossRef] [Green Version]
- Zhao, H.; Zhao, X.; Cen, Y.; Yang, H. Research on the Impact of Absorption Feature Extraction on Spectral Difference between Similar Minerals. Spectrosc Spect. Anal. 2017, 37, 869–874. [Google Scholar]
- Zhao, H.; Zhang, L.; Zhang, X.; Liu, J.; Wu, T.; Wang, S. Hyperspectral feature extraction based on the reference spectral background removal method. Ieee, J. Sel. Top. Appl. Earth Obs. Remote Sens. 2015, 8, 2832–2844. [Google Scholar] [CrossRef]
- Hecker, C.; Ruitenbeek, F.J.A.V.; Werff, H.M.; Bakker, W.H.; Meer, F.D.V.D. Spectral absorption feature analysis for finding ore: A tutorial on using the method in geological remote sensing. IEEE Geosci. Remote Sens. Lett. 2019, 7, 51–71. [Google Scholar] [CrossRef]
- Wang, X.; Zhang, X.; Li, H.; Zhang, X.; Liu, H.; Dou, X.; Yu, Z. The minimum level for soil allocation using topsoil reflectance spectra: Genus or species? Catena 2019, 174, 36–47. [Google Scholar] [CrossRef]
- van Ruitenbeek, F.J.; Bakker, W.H.; van der Werff, H.M.; Zegers, T.E.; Oosthoek, J.H.; Omer, Z.A.; Marsh, S.H.; van der Meer, F.D. Mapping the wavelength position of deepest absorption features to explore mineral diversity in hyperspectral images. Planet. Space Sci. 2014, 101, 108–117. [Google Scholar] [CrossRef]
- Crowley, J.K.; Brickey, D.W.; Rowan, L.C. Airborne imaging spectrometer data of the Ruby Mountains, Montana: Mineral discrimination using relative absorption band–depth images. Remote Sens. Envion. 1989, 29, 121–134. [Google Scholar] [CrossRef]
- Okada, N.; Maekawa, Y.; Owada, N.; Haga, K.; Shibayama, A.; Kawamura, Y. Automated Identification of Mineral Types and Grain Size Using Hyperspectral Imaging and Deep Learning for Mineral Processing. Minerals 2020, 10, 809. [Google Scholar] [CrossRef]
- Chen, Y.; Jiang, H.; Li, C.; Jia, X.; Ghamisi, P. Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks. IEEE Trans. Geosci. Remote Sens. 2016, 54, 6232–6251. [Google Scholar] [CrossRef] [Green Version]
- Guo, H.; Liu, J.; Xiao, Z.; Xiao, L. Deep CNN–based hyperspectral image classification using discriminative multiple spatial–spectral feature fusion. Remote Sens. Lett. 2020, 11, 827–836. [Google Scholar] [CrossRef]
- Nogueira, K.; Penatti, O.A.B.; Santos, J.A.D. Towards better exploiting convolutional neural networks for remote sensing scene classification. Pattern Recognit. 2016, 61, 539–556. [Google Scholar] [CrossRef] [Green Version]
- Gong, Z.; Zhong, P.; Yu, Y.; Hu, W.; Li, S. A CNN With Multiscale Convolution and Diversified Metric for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2019, 57, 3599–3618. [Google Scholar] [CrossRef]
- Zhang, L.; Zhang, L.; Du, B. Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geosci. Remote Sens. Lett. 2016, 4, 22–40. [Google Scholar] [CrossRef]
- Gao, H.; Yang, Y.; Li, C.; Zhang, X.; Yao, D. Convolutional neural network for spectral–spatial classification of hyperspectral images. Neural. Comput. Appl. 2019, 31, 8997–9012. [Google Scholar] [CrossRef]
- Yue, J.; Zhao, W.; Mao, S.; Liu, H. Spectral-spatial classification of hyperspectral images using deep convolutional neural networks. Remote Sens. Lett. 2015, 6, 468–477. [Google Scholar] [CrossRef]
- Cao, X.; Zhou, F.; Xu, L.; Meng, D.; Xu, Z.; Paisley, J. Hyperspectral Image Classification with Markov Random Fields and a Convolutional Neural Network. IEEE Trans. Image Process. 2018, 27, 2354–2367. [Google Scholar] [CrossRef] [Green Version]
- Mei, S.; Ji, J.; Bi, Q.; Hou, J.; Du, Q. Integrating spectral and spatial information into deep convolutional neural network for hyperspectral classification. In Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10–15 July 2016; pp. 5067–5070. [Google Scholar]
- Zhao, W.; Du, S. Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach. IEEE Trans. Geosci. Remote Sens. 2016, 54, 4544–4554. [Google Scholar] [CrossRef]
- Zhang, X.; Sun, Y.; Jiang, K.; Li, C.; Jiao, L.; Zhou, H. Spatial Sequential Recurrent Neural Network for Hyperspectral Image Classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018, 11, 4141–4155. [Google Scholar] [CrossRef] [Green Version]
- Hu, W.; Li, H.; Pan, L.; Li, W.; Tao, R.; Du, Q. Spatial–Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2020, 58, 4237–4250. [Google Scholar] [CrossRef]
- Xu, Y.; Zhang, L.; Du, B.; Zhang, F. Spectral–Spatial Unified Networks for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2018, 56, 5893–5909. [Google Scholar] [CrossRef]
- Li, S.; Zhu, X.; Bao, J. Hierarchical multi-scale convolutional neural networks for hyperspectral image classification. Sensors 2019, 19, 1714. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Krizhevsky, A.; Sutskever, I.; Hinton, G. ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM 2017, 60, 84–90. [Google Scholar] [CrossRef]
- Sellami, A.; Farah, M.; Farah, I.R.; Solaiman, B. Hyperspectral imagery classification based on semi-supervised 3-d deep neural network and adaptive band selection. Expert Syst. Appl. 2019, 129, 246–259. [Google Scholar] [CrossRef]
- Chen, Y.; Lin, Z.; Zhao, X.; Wang, G.; Gu, Y. Deep learning-based classification of hyperspectral data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2014, 7, 2094–2107. [Google Scholar] [CrossRef]
- Keshava, N.; Mustard, J.F. Spectral unmixing. IEEE Signal. Process. Mag. 2002, 19, 44–57. [Google Scholar] [CrossRef]
- Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [Green Version]
- Mou, L.; Ghamisi, P.; Zhu, X.X. Deep Recurrent Neural Networks for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens. 2017, 55, 3639–3655. [Google Scholar] [CrossRef] [Green Version]
- Liu, Q.; Zhou, F.; Hang, R.; Yuan, X. Bidirectional-Convolutional LSTM Based Spectral–Spatial Feature Learning for Hyperspectral Image Classification. Remote Sens. 2017, 9, 1330. [Google Scholar]
- Reddi, J.S.; Kale, S.; Kumar, S. On the Convergence of Adam and Beyond. In Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 30 April–3 May 2018. [Google Scholar]
- Chen, X.; Warner, T.A.; Campagna, D.J. Integrating visible, near-infrared and short-wave infrared hyperspectral and multispectral thermal imagery for geological mapping at Cuprite, Nevada. Remote Sens. Environ. 2007, 110, 344–356. [Google Scholar] [CrossRef] [Green Version]
- 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.; et al. Mapping Advanced Argillic Alteration at Cuprite, Nevada, Using Imaging Spectroscopy. Econ. Geol. 2014, 109, 1179–1221. [Google Scholar] [CrossRef]
- Hirai, A. Mineral discrimination by combination of multispectral image and surrounding hyperspectral image. J. Appl. Remote Sens. 2019, 13, 024517. [Google Scholar] [CrossRef]
- Liu, B.; Yu, X.; Zhang, P.; Tan, X.; Wang, R.; Zhi, L. Spectral–spatial classification of hyperspectral image using three–dimensional convolution network. J. Appl. Remote Sens. 2018, 12, 016005. [Google Scholar]
- Tan, Y.; Lu, L.; Bruzzone, L.; Guan, R.; Chang, Z.; Yang, C. Hyperspectral Band Selection for Lithologic Discrimination and Geological Mapping. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2020, 13, 471–486. [Google Scholar] [CrossRef]
- Liu, C.; Li, M.; Zhang, Y.; Han, S.; Zhu, Y. An enhanced rock mineral recognition method integrating a deep learning model and clustering algorithm. Minerals 2019, 9, 516. [Google Scholar] [CrossRef] [Green Version]
- Zuo, R.; Xiong, Y.; Wang, J.; Carranza, E.J.M. Deep learning and its application in geochemical mapping. Earth Sci. Rev. 2019, 192, 1–14. [Google Scholar] [CrossRef]
Class Name | Training Samples | Testing Samples |
---|---|---|
Muscovite | 100 | 400 |
Halloysite | 100 | 240 |
Calcite | 100 | 240 |
Kaolinite | 100 | 400 |
Montmorillonite | 100 | 400 |
Alunite | 100 | 400 |
Chalcedony | 100 | 240 |
Total | 700 | 2320 |
Parameter Combinations ID | f | l | h | OA (%) |
---|---|---|---|---|
1 | 20 | 5 | 40 | 91.12 |
2 | 20 | 5 | 50 | 91.25 |
3 | 20 | 5 | 60 | 91.59 |
4 | 20 | 10 | 40 | 91.59 |
5 | 20 | 10 | 50 | 91.90 |
6 | 20 | 10 | 60 | 92.16 |
7 | 30 | 5 | 40 | 91.55 |
8 | 30 | 5 | 50 | 92.36 |
9 | 30 | 5 | 60 | 92.76 |
10 | 30 | 10 | 40 | 92.58 |
11 | 30 | 10 | 50 | 92.97 |
12 | 30 | 10 | 60 | 93.36 |
13 | 40 | 5 | 40 | 93.62 |
14 | 40 | 5 | 50 | 94.05 |
15 | 40 | 5 | 60 | 94.09 |
16 | 40 | 10 | 40 | 93.36 |
17 | 40 | 10 | 50 | 94.70 |
18 | 40 | 10 | 60 | 94.52 |
HSS-LSTM | SAM | LSTM | 3D-CNN | |||||
---|---|---|---|---|---|---|---|---|
UA (%) | PA (%) | UA (%) | PA (%) | UA (%) | PA (%) | UA (%) | PA (%) | |
Muscovite | 98.47 | 96.50 | 93.90 | 100.00 | 93.90 | 100.00 | 100.00 | 100.00 |
Halloysite | 83.40 | 87.92 | 57.78 | 91.25 | 68.20 | 92.92 | 60.17 | 88.75 |
Calcite | 100.00 | 100.00 | 100.00 | 92.50 | 100.00 | 78.33 | 100.00 | 100.00 |
Kaolinite | 82.87 | 89.50 | 91.57 | 57.00 | 89.67 | 73.75 | 90.72 | 66.00 |
Montmorillonite | 100.00 | 100.00 | 96.62 | 100.00 | 91.53 | 100.00 | 99.26 | 100.00 |
Alunite | 99.73 | 91.75 | 100.00 | 99.50 | 99.49 | 97.25 | 100.00 | 100.00 |
Chalcedony | 100.00 | 97.92 | 96.98 | 93.75 | 100.00 | 92.50 | 100.00 | 96.67 |
AA (%) | 94.80 | 90.57 | 90.68 | 93.06 | ||||
OA (%) | 94.70 | 90.17 | 91.25 | 92.63 |
Method | Kaolinite/ Kaolinite | Halloysite/ Kaolinite | Kaolinite/ Halloysite | Halloysite/ Halloysite | OA (%) |
---|---|---|---|---|---|
HSS-LSTM | 211 | 29 | 41 | 359 | 89.06 |
SAM | 219 | 20 | 151 | 228 | 69.84 |
LSTM | 216 | 23 | 56 | 331 | 85.47 |
3D-CNN | 213 | 27 | 136 | 264 | 74.53 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhao, H.; Deng, K.; Li, N.; Wang, Z.; Wei, W. Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery. Sensors 2020, 20, 6854. https://doi.org/10.3390/s20236854
Zhao H, Deng K, Li N, Wang Z, Wei W. Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery. Sensors. 2020; 20(23):6854. https://doi.org/10.3390/s20236854
Chicago/Turabian StyleZhao, Huijie, Kewang Deng, Na Li, Ziwei Wang, and Wei Wei. 2020. "Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery" Sensors 20, no. 23: 6854. https://doi.org/10.3390/s20236854
APA StyleZhao, H., Deng, K., Li, N., Wang, Z., & Wei, W. (2020). Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery. Sensors, 20(23), 6854. https://doi.org/10.3390/s20236854