Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments
Laser-induced breakdown spectroscopy (LIBS) coupled with chemometrics is an efficient method for rock identification and classification, which has considerable potential in planetary geology. A great challenge facing the LIBS community is the difficulty to accurately discriminate rocks with close ch...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5343 |
| _version_ | 1797466632237350912 |
|---|---|
| author | Fan Yang Weiming Xu Zhicheng Cui Xiangfeng Liu Xuesen Xu Liangchen Jia Yuwei Chen Rong Shu Luning Li |
| author_facet | Fan Yang Weiming Xu Zhicheng Cui Xiangfeng Liu Xuesen Xu Liangchen Jia Yuwei Chen Rong Shu Luning Li |
| author_sort | Fan Yang |
| collection | DOAJ |
| description | Laser-induced breakdown spectroscopy (LIBS) coupled with chemometrics is an efficient method for rock identification and classification, which has considerable potential in planetary geology. A great challenge facing the LIBS community is the difficulty to accurately discriminate rocks with close chemical compositions. A convolutional neural network (CNN) model has been designed in this study to identify twelve types of rock, among which some rocks have similar compositions. Both the training set and the testing set are constructed based on the LIBS spectra acquired by Mars Surface Composition Detector (MarSCoDe) for China’s Tianwen-1 Mars exploration mission. All the spectra were collected from dedicated rock pellet samples, which were placed in a simulated Martian atmospheric environment. The classification performance of the CNN has been compared with that of three alternative machine learning algorithms, i.e., logistic regression (LR), support vector machine (SVM), and linear discriminant analysis (LDA). Among the four methods, it is on the CNN model that the highest classification correct rate has been obtained, as assessed by precision score, recall score, and the harmonic mean of precision and recall. Furthermore, the classification accuracy is inspected more quantitatively via Brier score, and the CNN is still the best performing model. The results demonstrate that the CNN-based chemometrics are an efficient tool for rock identification with LIBS spectra collected in a simulated Martian environment. Despite the relatively small sample set, this study implies that CNN-supported LIBS classification is a promising analytical technique for Tianwen-1 Mars mission and more planetary explorations in the future. |
| first_indexed | 2024-03-09T18:42:26Z |
| format | Article |
| id | doaj.art-cd2e3e4a4ae04ccaa32fd01b3fb4fcd0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:42:26Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-cd2e3e4a4ae04ccaa32fd01b3fb4fcd02023-11-24T06:37:29ZengMDPI AGRemote Sensing2072-42922022-10-011421534310.3390/rs14215343Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight ExperimentsFan Yang0Weiming Xu1Zhicheng Cui2Xiangfeng Liu3Xuesen Xu4Liangchen Jia5Yuwei Chen6Rong Shu7Luning Li8Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaSchool of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, ChinaDepartment of Remote Sensing and Photogrammetry, Finnish Geospatial Research Institute, 02430 Kirkkonummi, FinlandKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaKey Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, ChinaLaser-induced breakdown spectroscopy (LIBS) coupled with chemometrics is an efficient method for rock identification and classification, which has considerable potential in planetary geology. A great challenge facing the LIBS community is the difficulty to accurately discriminate rocks with close chemical compositions. A convolutional neural network (CNN) model has been designed in this study to identify twelve types of rock, among which some rocks have similar compositions. Both the training set and the testing set are constructed based on the LIBS spectra acquired by Mars Surface Composition Detector (MarSCoDe) for China’s Tianwen-1 Mars exploration mission. All the spectra were collected from dedicated rock pellet samples, which were placed in a simulated Martian atmospheric environment. The classification performance of the CNN has been compared with that of three alternative machine learning algorithms, i.e., logistic regression (LR), support vector machine (SVM), and linear discriminant analysis (LDA). Among the four methods, it is on the CNN model that the highest classification correct rate has been obtained, as assessed by precision score, recall score, and the harmonic mean of precision and recall. Furthermore, the classification accuracy is inspected more quantitatively via Brier score, and the CNN is still the best performing model. The results demonstrate that the CNN-based chemometrics are an efficient tool for rock identification with LIBS spectra collected in a simulated Martian environment. Despite the relatively small sample set, this study implies that CNN-supported LIBS classification is a promising analytical technique for Tianwen-1 Mars mission and more planetary explorations in the future.https://www.mdpi.com/2072-4292/14/21/5343Mars explorationTianwen-1 missionMarSCoDelaser-induced breakdown spectroscopy (LIBS)convolutional neural network (CNN) |
| spellingShingle | Fan Yang Weiming Xu Zhicheng Cui Xiangfeng Liu Xuesen Xu Liangchen Jia Yuwei Chen Rong Shu Luning Li Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments Remote Sensing Mars exploration Tianwen-1 mission MarSCoDe laser-induced breakdown spectroscopy (LIBS) convolutional neural network (CNN) |
| title | Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments |
| title_full | Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments |
| title_fullStr | Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments |
| title_full_unstemmed | Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments |
| title_short | Convolutional Neural Network Chemometrics for Rock Identification Based on Laser-Induced Breakdown Spectroscopy Data in Tianwen-1 Pre-Flight Experiments |
| title_sort | convolutional neural network chemometrics for rock identification based on laser induced breakdown spectroscopy data in tianwen 1 pre flight experiments |
| topic | Mars exploration Tianwen-1 mission MarSCoDe laser-induced breakdown spectroscopy (LIBS) convolutional neural network (CNN) |
| url | https://www.mdpi.com/2072-4292/14/21/5343 |
| work_keys_str_mv | AT fanyang convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT weimingxu convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT zhichengcui convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT xiangfengliu convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT xuesenxu convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT liangchenjia convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT yuweichen convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT rongshu convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments AT luningli convolutionalneuralnetworkchemometricsforrockidentificationbasedonlaserinducedbreakdownspectroscopydataintianwen1preflightexperiments |