Quantitative Analysis of Sulfur Elements in Mars-like Rocks Based on Multimodal Data
Abstract
1. Introduction
2. Materials
3. Methods
3.1. ViT Architecture and Modifications
3.2. MCNN Architecture
3.3. Feature Selection Methodology
4. Results
4.1. Performance Comparison Between Single-Modal and Multimodal Models
4.2. Experimental Results of MCNN Models with Different Feature Subsets
4.3. Ablation Study
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Mitra, K.; Catalano, J.G.; Bahl, Y.; Hurowitz, J.A. Iron sulfide weathering by oxyhalogen species: Implications for iron sulfate and (oxyhydr)oxides formation on Mars. Earth Planet. Sci. Lett. 2023, 624, 118464. [Google Scholar] [CrossRef]
- Hinman, N.W.; Hofmann, M.H.; Warren-Rhodes, K.; Phillips, M.S.; Noffke, N.; Cabrol, N.A.; Chong Diaz, G.; Demergasso, C.; Tebes-Cayo, C.; Cabestrero, O.; et al. Surface morphologies in a Mars-analog Ca-sulfate salar, high andes, northern chile. Front. Astron. Space Sci. 2022, 8, 797591. [Google Scholar] [CrossRef]
- King, P.L.; McLennan, S.M. Sulfur on Mars. Elements 2010, 6, 107–112. [Google Scholar] [CrossRef]
- Siljeström, S.; Czaja, A.D.; Corpolongo, A.; Berger, E.L.; Li, A.Y.; Cardarelli, E.; Abbey, W.; Asher, S.A.; Beegle, L.W.; Benison, K.C.; et al. Evidence of sulfate-rich fluid alteration in Jezero Crater Floor, Mars. J. Geophys. Res. Planets 2024, 129, e2023JE007989. [Google Scholar] [CrossRef]
- Zou, Y.; Zhu, Y.; Bai, Y.; Wang, L.; Jia, Y.; Shen, W.; Fan, Y.; Liu, Y.; Wang, C.; Zhang, A.; et al. Scientific objectives and payloads of Tianwen-1, China’s first Mars exploration mission. Adv. Space Res. 2021, 67, 812–823. [Google Scholar] [CrossRef]
- Wu, B.; Dong, J.; Wang, Y.; Rao, W.; Sun, Z.; Li, Z.; Tan, Z.; Chen, Z.; Wang, C.; Liu, W.; et al. Landing site selection and characterization of Tianwen-1 (Zhurong rover) on Mars. J. Geophys. Res. Planets 2022, 127, e2021JE007137. [Google Scholar] [CrossRef]
- Cui, Z.; Jia, L.; Li, L.; Liu, X.; Xu, W.; Shu, R.; Xu, X. A laser-induced breakdown spectroscopy experiment platform for high-degree simulation of MarSCoDe in situ detection on Mars. Remote. Sens. 2022, 14, 1954. [Google Scholar] [CrossRef]
- Rusak, D.A.; Rusak, D.A.; Castle, B.C.; Smith, B.W.; Winefordner, J.D. Fundamentals and applications of laser-induced breakdown spectroscopy. Crit. Rev. Anal. Chem. 1997, 27, 257–290. [Google Scholar] [CrossRef]
- Harmon, R.S.; Senesi, G.S. Laser-induced breakdown spectroscopy—A geochemical tool for the 21st century. Appl. Geochem. 2021, 128, 104929. [Google Scholar] [CrossRef]
- Wang, Z.; Afgan, M.S.; Gu, W.; Song, Y.; Wang, Y.; Hou, Z.; Song, W.; Li, Z. Recent advances in laser-induced breakdown spectroscopy quantification: From fundamental understanding to data processing. TrAC Trends Anal. Chem. 2021, 143, 116385. [Google Scholar] [CrossRef]
- Alrebdi, T.A.; Fayyaz, A.; Asghar, H.; Zaman, A.; Asghar, M.; Alkallas, F.H.; Hussain, A.; Iqbal, J.; Khan, W. Quantification of aluminum gallium arsenide (AlGaAs) wafer plasma using calibration-free laser-induced breakdown spectroscopy (CF-LIBS). Molecules 2022, 27, 3754. [Google Scholar] [CrossRef] [PubMed]
- Rao, A.P.; Jenkins, P.R.; Pinson, R.E.; Auxier II, J.D.; Shattan, M.B.; Patnaik, A.K. Machine learning in analytical spectroscopy for nuclear diagnostics [invited]. Appl. Opt. 2023, 62, A83–A109. [Google Scholar] [CrossRef] [PubMed]
- Yang, F.; Li, L.; Xu, W.; Liu, X.; Cui, Z.; Jia, L.; Liu, Y.; Xu, J.; Chen, Y.; Xu, X.; et al. Laser-induced breakdown spectroscopy combined with a convolutional neural network: A promising methodology for geochemical sample identification in Tianwen-1 Mars mission. Spectrochim. Acta Part B 2022, 192, 106417. [Google Scholar] [CrossRef]
- Wang, X.; Liu, C.; Liu, P.; Ling, Z. A new method for cross-calibration between LIBS systems based on a domain adaptive fully connected network. J. Anal. At. Spectrom. 2024, 39, 558–572. [Google Scholar] [CrossRef]
- Weritz, F.; Ryahi, S.; Schaurich, D.; Taffe, A.; Wilsch, G. Quantitative determination of sulfur content in concrete with laser-induced breakdown spectroscopy. Spectrochim. Acta Part B 2005, 60, 1121–1131. [Google Scholar] [CrossRef]
- Fang, X.; Yu, H.; Huang, Q.; Jiang, Z.; Pan, D.; Gui, W. Full-spectrum LIBS quantitative analysis based on heterogeneous ensemble learning model. Chemom. Intell. Lab. Syst. 2025, 257, 105321. [Google Scholar] [CrossRef]
- Duponchel, L.; Bousquet, B.; Pelascini, C.; Motto-Ros, V. Should we prefer inverse models in quantitative LIBS analysis? J. Anal. At. Spectrom. 2020, 35, 794–803. [Google Scholar] [CrossRef]
- Zeng, J.; Xu, H.; Gong, G.; Xu, C.; Tian, C.; Lu, T. Hackem-LIBS: An heterogeneous stacking ensemble model for laser-induced breakdown spectroscopy elemental quantitative analysis. IEEE Access 2020, 8, 136141–136150. [Google Scholar] [CrossRef]
- Gu, Y.; Chen, Z.; Chen, H.; Nian, F. Quantitative analysis of steel alloy elements based on LIBS and deep learning of multi-perspective features. Electronics 2023, 12, 2566. [Google Scholar] [CrossRef]
- Naser, H.J.; Hamad, T.K. Quantitative analysis of heavy metals in gallstone using LIBS. J. Phys. Conf. Ser. 2021, 1963, 012089. [Google Scholar] [CrossRef]
- Sui, M.; Fan, Y.; Jiang, L.; Xue, T.; Zhou, J.; Zhong, S. Online ultrasonic nebulizer assisted laser induced breakdown spectroscopy (OUN-LIBS): An online metal elements sensor for marine water analysis. Spectrochim. Acta Part B 2021, 180, 106201. [Google Scholar] [CrossRef]
- Zhao, R.; Li, W.; Xu, J.; Chen, L.; Wei, X.; Kong, X. A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification. Anal. Methods 2025, 17, 1090–1100. [Google Scholar] [CrossRef] [PubMed]
- Yi, M.; Chen, W.; Liu, J. Total partial least square regression and its application in infrared spectra quantitative analysis. Measurement 2025, 247, 116794. [Google Scholar] [CrossRef]
- Kadam, P.S.; Godse, S. Exploring different feature selection techniques for high risk disease prediction using machine learning. In Proceedings of the 2024 MIT Art, Design and Technology School of Computing International Conference (MITADTSoCiCon), Pune, India, 25–27 April 2024; pp. 1–6. [Google Scholar] [CrossRef]
- Boucher, T.F.; Ozanne, M.V.; Carmosino, M.L.; Dyar, M.D.; Mahadevan, S.; Breves, E.A.; Lepore, K.H.; Clegg, S.M. A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy. Spectrochim. Acta Part B 2015, 107, 1–10. [Google Scholar] [CrossRef]
- Yang, Y.; Wang, X.; Zhao, X.; Huang, M.; Zhu, Q. M3GPSpectra: A novel approach integrating variable selection/construction and MLR modeling for quantitative spectral analysis. Anal. Chim. Acta 2021, 1160, 338453. [Google Scholar] [CrossRef]
- Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; Gelly, S.; et al. An image is worth 16 × 16 words: Transformers for image recognition at scale. In Proceedings of the 9th International Conference on Learning Representations, Virtual, 3–7 May 2021. [Google Scholar]
- Ma, J.; Chen, Y.; Luo, X.; Chen, D.; Cai, Y.; Xue, W.; Wang, L. Identification of industrial gas by sparse infrared absorption spectrum characteristics and support vector machine. In Proceedings of the Global Intelligent Industry Conference 2020, Guangzhou, China, 18 March 2021; Volume 11780. [Google Scholar] [CrossRef]
- Sun, T.; Shao, C.; Liao, H.; Ding, S.; Xu, X. Research on adaptive local feature enhancement in convolutional neural networks. IET Image Process. 2020, 14, 4306–4315. [Google Scholar] [CrossRef]
- Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D. Going deeper with convolutions. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 1–9. [Google Scholar] [CrossRef]
- Yuan, K.; Guo, S.; Liu, Z.; Zhou, A.; Yu, F.; Wu, W. Incorporating convolution designs into visual transformers. In Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 10–17 October 2021; pp. 559–568. [Google Scholar] [CrossRef]
- Li, Y.; Zhang, K.; Cao, J.; Timofte, R.; Magno, M.; Benini, L. LocalViT: Analyzing locality to vision transformers. In Proceedings of the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 1–5 October 2023; pp. 9598–9605. [Google Scholar] [CrossRef]
- Behmanesh, M.; Adibi, P.; Chanussot, J.; Jutten, C.; Ehsani, S.M.S. Geometric multimodal learning based on local signal expansion for joint diagonalization. IEEE Trans. Signal Process. 2021, 69, 1271–1286. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar] [CrossRef]
- Luarte, D.; Myakalwar, A.K.; Velásquez, M.; Álvarez, J.; Sandoval, C.; Fuentes, R.; Yañez, J.; Sbarbaro, D. Combining prior knowledge with input selection algorithms for quantitative analysis using neural networks in laser induced breakdown spectroscopy. Anal. Methods 2021, 13, 1181–1190. [Google Scholar] [CrossRef]
Rock Matrix | Sulfate |
---|---|
Basalt GBW07105 | CaSO4 |
CaSO4·1/2H2O | |
CaSO4·2H2O | |
K2SO4 | |
Andesite GBW07104 | MgSO4 |
FeSO4 | |
CaSO4·2H2O |
Component | Basalt GBW07105 | Andesite GBW07104 |
---|---|---|
SiO2 | 44.64 ± 0.11 | 60.62 ± 0.14 |
Al2O3 | 13.83 ± 0.13 | 16.17 ± 0.12 |
CaO | 8.81 ± 0.09 | 5.20 ± 0.07 |
H2O+ | 2.86 ± 0.13 | (1.5) |
S | 0.01 | 0.0192 ± 0.0021 |
Model | Accuracy |
---|---|
SVM | 0.93 |
RF | 0.90 |
KNN | 0.83 |
Layer Name | Kernel Size | Channels | Dropout Rate |
---|---|---|---|
Conv1 | 1 × 3 | 4 | |
Conv2 | 1 × 3 | 64 | |
Conv3 | 1 × 5 | 128 | 0.2 |
Conv4 | 1 × 5 | 64 | |
Conv5 | 1 × 3 | 64 |
Layer Name | Kernel Size | Num_Heads | Channels |
---|---|---|---|
Multi-Head Attention | 4 | ||
Conv1 | 1 × 3 | 8 | |
Multi-Head Attention | 4 | ||
Conv2 | 1 × 5 | 32 | |
Multi-Head Attention | 4 | ||
Conv3 | 1 × 3 | 64 |
Modal | RMSEP | R2 |
---|---|---|
SVR | 2.28 | 0.670 |
Inception-v2 | 2.91 | 0.466 |
BPNN | 1.44 | 0.506 |
Multimodal (low content) | 0.04 | 0.981 |
Multimodal (high content) | 0.11 | 0.932 |
Low Content | High Content | |||||
---|---|---|---|---|---|---|
RF | CARS | XGBoost | RF | CARS | XGBoost | |
RMSEP | 0.02 | 0.0687 | 0.02 | 0.15 | 0.093 | 0.06 |
R2 | 0.986 | 0.964 | 0.989 | 0.899 | 0.936 | 0.962 |
RMSEP | R2 | |
---|---|---|
No classification | 0.61 | 0.956 |
Connection fusion | 3.42 | 0.748 |
Only LIBS | 0.34 | 0.964 |
Only IR | 1.34 | 0.900 |
Model | RMSEP | R2 |
---|---|---|
BPNN | 2.73 | 0.691 |
Inception-v2 | 3.42 | 0.748 |
SVR | 1.29 | 0.827 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 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 (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Dong, Y.; Shi, Z.; Yao, J.; Zhang, L.; Chen, Y.; Jia, J. Quantitative Analysis of Sulfur Elements in Mars-like Rocks Based on Multimodal Data. Sensors 2025, 25, 4388. https://doi.org/10.3390/s25144388
Dong Y, Shi Z, Yao J, Zhang L, Chen Y, Jia J. Quantitative Analysis of Sulfur Elements in Mars-like Rocks Based on Multimodal Data. Sensors. 2025; 25(14):4388. https://doi.org/10.3390/s25144388
Chicago/Turabian StyleDong, Yuhang, Zhengfeng Shi, Junsheng Yao, Li Zhang, Yongkang Chen, and Junyan Jia. 2025. "Quantitative Analysis of Sulfur Elements in Mars-like Rocks Based on Multimodal Data" Sensors 25, no. 14: 4388. https://doi.org/10.3390/s25144388
APA StyleDong, Y., Shi, Z., Yao, J., Zhang, L., Chen, Y., & Jia, J. (2025). Quantitative Analysis of Sulfur Elements in Mars-like Rocks Based on Multimodal Data. Sensors, 25(14), 4388. https://doi.org/10.3390/s25144388