Articles
Semantic-Aware Privacy-Preserving Mobile Lithology Intelligence: A Deep Learning Framework for Rock Image Recognition, Geological Interpretation, and Secure Field Trajectory Analytics
Downloads
Keywords
lithology recognition
deep learning
mobile geology
semantic trajectory privacy
Article Usage Statistics
Live Metrics
Abstract Views
228
File Views
109
PDF
0
HTML
0
Other
109
Total
337
Article Usage Chart
Abstract
File Views
PDF
HTML
Other
Total
Abstract
Background: Contemporary geological intelligence is increasingly shaped by two technological trajectories that are usually discussed separately: deep learning–driven lithology recognition from rock images and privacy-preserving analytics for mobile location and trajectory data. The first trajectory has rapidly advanced through convolutional neural networks, transfer learning, lightweight mobile models, and image-based mineral recognition, enabling increasingly accurate identification of lithology from drill cores, thin sections, fresh rock surfaces, borehole images, and field photographs (Marmo et al., 2005; Chatterjee, 2013; Izadi et al., 2017; Liu et al., 2020; Alzubaidi et al., 2021; Zhang et al., 2024). The second trajectory has evolved through semantic trajectory mining, geo-indistinguishability, differential privacy, semantic-aware privacy preservation, and location privacy surveys, highlighting the vulnerability of mobile users to inference attacks when movement data reveal behavioral and spatial patterns (Andrés et al., 2013; Zheng, 2015; Primault et al., 2019; Jiang et al., 2021; Qiu et al., 2023). Yet the field deployment of mobile lithology systems inherently joins these domains, because rock image acquisition, drill-site inspection, field traverses, and smartphone-assisted recognition generate sensitive trajectory traces.
Objective: This article develops a unified research framework for privacy-preserving mobile lithology intelligence by integrating advances in geological image recognition and semantic trajectory privacy.
Methods: Through a structured synthesis of the provided references, the study constructs a multilayer conceptual architecture linking rock image acquisition, deep feature extraction, transfer learning, lightweight inference, semantic context modeling, and privacy-preserving trajectory management. The article analyzes the theoretical compatibility of convolutional image intelligence and location privacy mechanisms under field geology conditions.
Results: The analysis indicates that geological image recognition systems become operationally stronger when visual inference is combined with semantic context, but they also become privacy-riskier because contextualized field trajectories increase re-identification potential. A robust mobile lithology platform therefore requires joint optimization of classification accuracy, geological interpretability, computational portability, and behavioral-semantic privacy preservation. The proposed framework demonstrates how deep visual models, semantic fusion, and trajectory protection mechanisms can coexist without reducing geological usability to purely anonymous yet contextless data.
Conclusion: A next-generation geological field intelligence system should not treat lithology recognition and location privacy as separate engineering problems. It should instead operate as a secure semantic pipeline in which mobile rock recognition benefits from trajectory-aware context while trajectory exposure is limited through differentiated privacy controls. This integrated perspective provides a new direction for trustworthy
intelligent geoscience.
Downloads
Download data is not yet available.
References
1. Alzubaidi, F., Mostaghimi, P., Swietojanski, P., et al. (2021). Automated lithology classification from drill core images using convolutional neural networks. Journal of Petroleum Science and Engineering, 197, 107933.
2. Andrés, M. E., Bordenabe, N. E., Chatzikokolakis, K., et al. (2013). Geo-indistinguishability: Differential privacy for location-based systems. In Proceedings of the 2013 ACM SIGSAC Conference on Computer & Communications Security (pp. 901–914).
3. Bai, L., Yao, Y., Li, S., et al. (2018). Mineral composition analysis of rock images based on deep learning feature extraction. China Mining Magazine, 27(7), 178–182.
4. Chai, H., Li, N., Xiao, C., et al. (2009). Automatic discrimination of sedimentary facies and lithologies in reef-bank reservoirs using borehole image logs. Applied Geophysics, 6, 17–29.
5. Chatterjee, S. (2013). Vision-based rock-type classification of limestone using multi-class support vector machine. Applied Intelligence, 39, 14–27.
6. Chen, Y., Duan, J., Xu, G., et al. (2024). Geochemical characteristics and tectonic significance of Late Triassic lamprophyres in Beishan area, Gansu Province. Northwestern Geology, 57(6), 78–94.
7. Cheng, G., & Yin, J. (2015). Rock thin section image classification based on SVM. Technology Innovation and Application, 5(1), 38.
8. Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
9. Dai, X., Zhou, B., Li, X., et al. (2024). Geochronology, geochemistry and tectonic significance of Miocene quartz monzonite intrusions in the north of Qitaidaban, West Kunlun. Northwestern Geology, 57(4), 191–205.
10. Dai, Y., Shao, J., & Zhang, D. (2018). Personalized semantic trajectory privacy preservation through trajectory reconstruction. World Wide Web, 21(4), 875–914.
11. Dong, W., & Zhang, H. (2023). Lithology identification of cuttings based on transfer learning. Journal of University of Chinese Academy of Sciences, 40(6), 743–750.
12. Fan, G., Chen, F., Chen, D., et al. (2020a). Recognizing multiple types of rocks quickly and accurately based on lightweight CNNs model. IEEE Access, 8, 55269–55278.
13. Fan, G., Chen, F., Chen, D., et al. (2020b). A deep learning model for quick and accurate rock recognition with smartphones. Mobile Information Systems, 2020, 1–14.
14. Feng, Y., Gong, X., Xu, Y., et al. (2019). Lithology identification method based on fresh rock surface images and Siamese convolutional neural networks. Geography and Geo-Information Science, 35(5), 89–94.
15. He, K. M., Zhang, X. Y., Ren, S. Q., et al. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
16. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507.
17. Izadi, H., Sadri, J., & Bayati, M. (2017). An intelligent system for mineral identification in thin sections based on a cascade approach. Computers & Geosciences, 99, 37–49.
18. Jiang, H., Li, J., Zhao, P., et al. (2021). Location privacy-preserving mechanisms in location-based services: A comprehensive survey. ACM Computing Surveys, 54(1), 1–36.
19. Jin, X., Zhang, R., Chen, Y., et al. (2016). Dpsense: Differentially private crowdsourced spectrum sensing. In Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), Vienna, Austria (pp. 296–307).
20. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90.
21. Li, Y. (2020). Rock image recognition based on deep learning. Beijing: Beijing Forestry University.
22. Liu, H., Cui, J., Jin, W., et al. (2024). Geochemical characteristics and geological significance of granites in the eastern Songliao Basin. Northwestern Geology, 57(2), 46–58.
23. Liu, X., Wang, H., Jing, H., et al. (2020). Research on intelligent identification of rock types based on Faster R-CNN method. IEEE Access, 8, 21804–21812.
24. Marmo, R., Amodio, S., Tagllaferri, R., et al. (2005). Textural identification of carbonate rocks by image processing and neural network: Methodology proposal and examples. Computers & Geosciences, 31(5), 649–659.
25. Meng, W., Zhang, Z., Gao, Y., et al. (2024). Mineral composition and geological significance of the newly discovered Wangzhuang gold deposit in Southern Qinling. Northwestern Geology, 57(4), 157–169.
26. Phan, N., Wang, Y., Wu, X., et al. (2016). Differential privacy preservation for deep auto-encoders: An application of human behavior prediction. In Proceedings of the 30th AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA (pp. 1309–1316).
27. Primault, V., Boutet, A., Mokhtar, S. B., et al. (2019). The long road to computational location privacy: A survey. IEEE Communications Surveys & Tutorials, 21(3), 2772–2793.
28. Qiu, G., Guo, D., Shen, Y., et al. (2020). Mobile semantic-aware trajectory for personalized location privacy preservation. IEEE Internet of Things Journal, 8(21), 16165–16180.
29. Qiu, G., Tang, G., Li, C., et al. (2023). Differentiated location privacy protection in mobile communication services: A survey from the semantic perception perspective. ACM Computing Surveys, 56(3), 1–36.
30. Qiu, G., Tang, G., Li, C., et al. (2024). Behavioral-semantic privacy protection for continual social mobility in mobile internet services. IEEE Internet of Things Journal, 11(1), 462–477.
31. Ran, X., Xue, L., Zhang, Y., et al. (2019). Rock classification from field image patches analyzed using a deep convolutional neural network. Mathematics, 7, 755.
32. Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv.
33. Song, C., & Raghunathan, A. (2020). Information leakage in embedding models. In Proceedings of the 27th ACM SIGSAC Conference on Computer and Communications Security (CCS), Gather.town, virtual platform (pp. 377–390).
34. Szegedy, C., Vanhoucke, V., Ioffe, S., et al. (2016). Rethinking the Inception architecture for computer vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
35. Tan, Y., Tian, M., Xu, D., et al. (2022). Research on rock image classification and recognition based on Xception network. Geography and Geo-Information Science, 38(3), 17–22.
36. Wang, C., Li, Y., Fan, G., et al. (2018). Quick recognition of rock images for mobile applications. Journal of Engineering Science and Technology Review, 11(4), 111–117.
37. Wu, L., Zhai, X., Wang, E., et al. (2025). Geochemical characteristics and formation environment of Jijitaizi ophiolite in Beishan area. Northwestern Geology, 58(1), 27–42.
38. Xu, Z., Ma, W., Lin, P., et al. (2021). Intelligent lithology identification based on transfer learning of rock images. Journal of Basic Science and Engineering, 29(5), 1075–1092.
39. Yang, C., Sun, M., Zhao, W. X., et al. (2017). A neural network approach to jointly modeling social networks and mobile trajectories. IEEE Transactions on Information Systems, 35(4), 1–28.
40. Yuan, H. (2023). Research on intelligent lithology identification method based on rock image feature learning.
41. Zhang, F., Liu, J., Lu, X., et al. (2023). Spatial weighted graph-driven fault diagnosis of complex process industry considering technological process flow. Measurement Science and Technology, 34(12), 125143.
42. Zhang, J., Li, C., & Wang, B. (2022). A performance tunable CPIR-based privacy protection method for location based service. Information Sciences, 589, 440–458.
43. Zhang, Y., Li, M., & Han, S. (2018). Automatic identification and classification method of lithology based on deep learning of rock images. Acta Petrologica Sinica, 34(2), 333–342.
44. Zhang, Y., Ye, Y. L., Guo, D. J., et al. (2024). PCA-VGG16 model for classification of rock types. Earth Science Informatics, 17(2), 1553–1567.
45. Zhang, Z., Tang, J., Fan, B., et al. (2024). An intelligent lithology recognition system for continental shale by using digital coring images and convolutional neural networks. Geoenergy Science and Engineering, 239, 212909.
46. Zhao, W., Zhou, N., Zhang, W., et al. (2016). A probabilistic lifestyle-based trajectory model for social strength inference from human trajectory data. IEEE Transactions on Information Systems, 35(1), 1–28.
47. Zheng, Y. (2015). Trajectory data mining: An overview. ACM Transactions on Intelligent Systems and Technology, 6(3), 1–41.