ZHU Ling,LI Ming,QIN Kai.Small sample data augmentation and abundances inversion of minerals hyperspectral[J].Optics and Precision Engineering,2023,31(11):1684-1690.
ZHU Ling,LI Ming,QIN Kai.Small sample data augmentation and abundances inversion of minerals hyperspectral[J].Optics and Precision Engineering,2023,31(11):1684-1690. DOI: 10.37188/OPE.20233111.1684.
Small sample data augmentation and abundances inversion of minerals hyperspectral
Using deep learning methods to retrieve mineral abundance requires numerous labeled hyperspectral data samples. Thus, a method based on the Hapke mixed model with filling factor is proposed for data augmentation of small mineral samples, to generate a large number of labeled datasets. First, five kinds of common mineral powders were mixed by multiple elements in the laboratory according to the weight mixing ratio, and the spectra of mixed minerals were measured. Subsequently, mixing spectra were simulated considering the corresponding weight proportion of the five mixing models, including the linear mixing model. The simulated spectra of the augmented data using the original Hapke and the Hapke mixing model with filling factors of 0.1, 0.2, and 0.3 were compared with the measured spectra. Finally, based on the sum to one abundance matrix randomly generated by the Monte Carlo method, forty thousand simulated spectra were generated using the five mixing models. The abundance information on real spectral data was obtained by treating the simulated spectra as the training dataset of the stack autoencoder network. The results showed that the simulation results obtained using the original Hapke model and the model with filling factors were better in accuracy than those of the linear mixed model. When the filling factors of the Hapke model were set to 0.1 and 0.2, the mean SAM error was 0.053 5 and 0.053 7, respectively, and the RMSE error of mineral abundance inversion of hyperspectral data was 0.124 8, demonstrating the superiority of the Hapke model with filling factors over the other four methods. The simulated mineral spectrum was closer to the measured spectrum and better than that without any filling factors with a simulation error of 0.074 8, and the spectra associated with the simulated data were closer to the real spectrum, thereby providing support for mineral abundance inversion research based on deep learning.
DING W Q , DING L . Hyperspectral remote sensing of rock and mineral and its application prospects on the Tibetan Plateau [J]. Chinese Journal of Geology , 2022 , 57 ( 3 ): 924 - 944 . (in Chinese) . doi: 10.12017/dzkx.2022.053 http://dx.doi.org/10.12017/dzkx.2022.053
ZHANG CH Y , QIN Q M , CHEN L , et al . Research and development of mineral identification utilizing hyperspectral remote sensing [J]. Opt. Precision Engi. , 2015 , 23 ( 8 ): 2407 - 2418 . (in Chinese) . doi: 10.3788/ope.20152308.2407 http://dx.doi.org/10.3788/ope.20152308.2407
DONG X F , GAN F P , LI N , et al . Fine mineral identification of GF-5 hyperspectral image [J]. Journal of Remote Sensing , 2020 , 24 ( 4 ): 454 - 464 . (in Chinese)
YE ZH , BAI L , HE M Y . Review of spatial-spectral feature extraction for hyperspectral image [J]. Journal of Image and Graphics , 2021 , 26 ( 8 ): 1737 - 1763 . (in Chinese) . doi: 10.11834/jig.210198 http://dx.doi.org/10.11834/jig.210198
OZKAN S , KAYA B , AKAR G B . EndNet: sparse AutoEncoder network for endmember extraction and hyperspectral unmixing [J]. IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 1 ): 482 - 496 . doi: 10.1109/tgrs.2018.2856929 http://dx.doi.org/10.1109/tgrs.2018.2856929
ZHANG X R , SUN Y J , ZHANG J Y , et al . Hyperspectral unmixing via deep convolutional neural networks [J]. IEEE Geoscience and Remote Sensing Letters , 2018 , 15 ( 11 ): 1755 - 1759 . doi: 10.1109/lgrs.2018.2857804 http://dx.doi.org/10.1109/lgrs.2018.2857804
SU Y C , LI J , PLAZA A , et al . DAEN: deep autoencoder networks for hyperspectral unmixing [J]. IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 7 ): 4309 - 4321 . doi: 10.1109/tgrs.2018.2890633 http://dx.doi.org/10.1109/tgrs.2018.2890633
HAN ZH , GAO L R , ZHANG B , et al . Nonlinear unmixing of hyperspectral image self-coding network with high score No.5 [J]. National Remote Sensing Bulletin , 2020 , 24 ( 4 ): 388 - 400 . (in Chinese) . doi: 10.11834/jrs.20209188 http://dx.doi.org/10.11834/jrs.20209188
MU X D , BAI K , YOU X A , et al . Remote sensing image feature extraction and classification based on contrastive learning method [J]. Opt. Precision Eng. , 2021 , 29 ( 9 ): 2222 - 2234 . doi: 10.37188/OPE.20212909.2222 http://dx.doi.org/10.37188/OPE.20212909.2222
WANG ZH L , HE M , YE ZH , et al . For hyperspectral compressed sensing method on linear mixed spectrum model [J]. Journal of Remote Sensing , 2020 , 24 ( 3 ): 277 - 289 . (in Chinese)
WANG ZH , ZHAO ZH , YAN B K , et al . Simulation of bi-directional reflectance on mixed minerals based on Hapke photometric model [J]. Remote Sensing for Land & Resources , 2017 , 29 ( 1 ): 186 - 191 . (in Chinese)
QIN K , GE F Y , ZHAO Y J , et al . Hapke data augmentation for deep learning-based hyperspectral data analysis with limited samples [J]. IEEE Geoscience and Remote Sensing Letters , 2021 , 18 ( 5 ): 886 - 890 . doi: 10.1109/lgrs.2020.2989796 http://dx.doi.org/10.1109/lgrs.2020.2989796
WANG L , LIU D , WANG Q , et al . Spectral unmixing model based on least squares support vector machine with unmixing residue constraints [J]. Geoscience and Remote Sensing Letters , 2013 , 10 ( 6 ): 1592 - 1596 . doi: 10.1109/lgrs.2013.2262371 http://dx.doi.org/10.1109/lgrs.2013.2262371