Skip to main content
SpringerLink
Log in

Automatic lithology identification method based on efficient deep convolutional network

  • RESEARCH
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

A Correction to this article was published on 18 March 2023

This article has been updated

Abstract

Due to the complexity of the environment and the variability of rocks under natural conditions, it is difficult for geologists to obtain a rapid analysis and description of rocks. To this end, this study proposes a lithology identification method that is suitable for efficient computation and maintains good accuracy. The method uses deep learning and migration learning methods to build a lithology recognition model through PyTorch and YOLOv5 frameworks, and investigates the recognition of six types of rock data. The model achieves an accuracy of 90.30% on the validation set. The method was compared with five other commonly used methods which have the fewest network parameters and can recognise 176 rock images per second on a server (equipped with a Tesla T4 GPU).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20

Similar content being viewed by others

Data Availability

Data supporting the findings of this study can be obtained by contacting the authors or from the link https://github.com/2658450653/ROFMohsF.git.

Change history

References

  • Arya S (1994) An optimal algorithm for approximate nearest neighbor searching fixed dimensions. Society for Industrial and Applied Mathematics

  • Baraboshkin EE, Ismailova LS, Orlov DM, Zhukovskaya EA, Kalmykov GA, Khotylev OV, Baraboshkin EY, Koroteev DA (2020) Deep convolutions for in-depth automated rock typing. Comput Geosci 135:104330

    Article  Google Scholar 

  • Fan G, Chen F, Chen D, Li Y, Dong Y (2020) A Deep Learning Model for Quick and Accurate Rock Recognition with Smartphones. Mob Inf Syst 2020(2):1–14

    Google Scholar 

  • Goyal AA, Bochkovskiy J, Deng and V, Koltun (2021) "Non-deep Networks." ArXiv abs/2110.07641

  • He KX, Zhang S, Ren and Sun J (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 770–778

  • Hu J, Shen L, Sun G (2018) Squeeze-and-Excitation Networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2018:7132–7141

    Google Scholar 

  • LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324

    Article  Google Scholar 

  • Li N, Hao H, Gu Q, Wang D, Hu X (2017) A transfer learning method for automatic identification of sandstone microscopic images. Comput Geosci 103:111–121

    Article  Google Scholar 

  • Liu Z, Mao H,  Wu CY, Feichtenhofer C, Darrell T and Xie S (2022) A ConvNet for the 2020s. arXiv e-prints

  • Long XK, Deng G, Wang Y, Zhang Q, Dang Y, Gao H, Shen J, Ren S, Han E, Ding and Wen S (2020) PP-YOLO: An Effective and Efficient Implementation of Object Detector. ArXiv abs/2007.12099

  • Massonne HJ, Bernhardt HJ, Dettmar D, Kessler E, Medenbach O, Westphal T (1998) Simple identification and quantification of microdiamonds in rock thin-sections. Eur J Mineral 10:497–504

    Article  Google Scholar 

  • Młynarczuk M, Górszczyk A, Ślipek B (2013) The application of pattern recognition in the automatic classification of microscopic rock images. Comput Geosci 60:126–133

    Article  Google Scholar 

  • Prince CM and Chitale J (2008) Core Image Analysis: Reliable Pay Estimation in Thin-Bedded Reservoir Units. Soc. of Core Analysts Annual Meeting

  • Qi Z, WeiJun J, ChengDong L, YuanLong W (2010) On the classification of granitic rocks based on whole-rock Srand Yb concentrations III: Practice. Acta Petrologica Sinica 26(12):3431–3455

    Google Scholar 

  • Qi Z, WeiJun J, ChengDong L, YuanLong W (2011) Revisiting the new classification of granitic rocks based on whole-rock Sr and Yb contents. Acta Petrologica Sinica 26(4):1803–1833

    Google Scholar 

  • Reed FS, Mergner JL (1953) Preparation of rock thin sections. Am Miner 38:1184–1203

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning Representations by Back Propagating Errors. Nature 323(6088):533–536

    Article  Google Scholar 

  • Sandler M, Howard A, Zhu M, Zhmoginov A and Chen LC (2018) MobileNetV2: Inverted Residuals and Linear Bottlenecks. IEEE

  • Sifre L and Mallat S (2014) Rigid-Motion Scattering for Texture Classification. arXiv e-prints

  • Simonyan K and Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs/1409.1556

  • Singh N, Singh TN, Tiwary A, Sarkar KM (2009) Textural identification of basaltic rock mass using image processing and neural network. Comput Geosci 14(2):301–310

    Article  Google Scholar 

  • Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V and  Rabinovich A (2015) Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition

  • Szegedy C, Vanhoucke V, Ioffe S, Shlens J and Wojna Z (2016) Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 2818–2826

  • Tan M and Le QV (2019) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

  • Thomas A, Rider M, Curtis A and MacArthur A (2011) Automated lithology extraction from core photographs. first break 29(6)

  • Wieling IS (2013) Facies and permeability prediction based on analysis of core images

  • Xie S, Girshick RB, Dollár P, Tu Z and He K (2017) Aggregated Residual Transformations for Deep Neural Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR): 5987–5995

  • Ye Z, Mingchao LI, Shuai H (2018) Automatic identification and classification in lithology based on deep learning in rock images. Acta Petrologica Sinica 34(2):333–342

    Google Scholar 

  • Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? MIT Press

    Google Scholar 

  • Zagoruyko S and Komodakis N (2016) Wide Residual Networks. ArXiv abs/1605.07146

  • Zisserman A and Simonyan K (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition

Download references

Acknowledgements

This work was supported by several funds: 1. Open Fund of State Key Laboratory of Remote Sensing Science (Grant No. 6142A01210404); 2. Hubei Key Laboratory of Intelligent Geo-Information Processing (Grant No. KLIGIP-2022-B03); 3. Metallogenic patterns and mineralization predictions for the Daping gold deposit in Yuanyang County, Yunnan Province (Grant No. 2022026821); 4. Ministry of Education Industry-University Cooperation Collaborative Education Project - Remote Sensing Practical Education and Science Popularization Base Construction (Grant No. 20221008). In addition, the authors thank the Yifu Museum of the China University of Geosciences for providing the rock sample data.

Funding

This work was supported by several funds: 1. Open Fund of State Key Laboratory of Remote Sensing Science (Grant No. 6142A01210404); 2. Hubei Key Laboratory of Intelligent Geo-Information Processing(Grant No. KLIGIP-2022-B03); 3. Metallogenic patterns and mineralization predictions for the Daping gold deposit in Yuanyang County, Yunnan Province (Grant No. 2022026821); 4. Ministry of Education Industry-University Cooperation Collaborative Education Project - Remote Sensing Practical Education and Science Popularization Base Construction (Grant No. 20221008).

Author information

Authors and Affiliations

  1. School of Computer Science, China University of Geosciences (Wuhan), Wuhan, 430074, Hubei, China

    Yan Guo, Zhuowu Li, Ji Zhou & Shixiang Feng

  2. School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan, 430074, Hubei, China

    Weihua Lin, Luyu Zhang & Fujiang Liu

Authors
  1. Yan Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhuowu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weihua Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ji Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shixiang Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Luyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Fujiang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: Yan Guo; Data collection: Zhuowu Li and Luyu Zhang; Formal analysis and investigation: Zhuowu Li; Methodology: Yan Guo and Zhuowu Li; Resources: Weihua Lin; Software: Shixiang Feng and Ji Zhou; Writing – original draft: Zhuowu Li; Writing – review & editing: Yan Guo; Validation: Zhuowu Li; Funding acquisition: Fujiang Liu; Supervision: Fujiang Liu and Weihua Lin.

Corresponding author

Correspondence to Fujiang Liu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Conflict of Interest

The authors declare no competing interests.

Additional information

Communicated by: H. Babaie

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original online version of this article was revised incorrect funding grant number.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guo, Y., Li, Z., Lin, W. et al. Automatic lithology identification method based on efficient deep convolutional network. Earth Sci Inform 16, 1359–1372 (2023). https://doi.org/10.1007/s12145-023-00962-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-023-00962-4

Keywords

Search

Navigation