Abstract
Traditional machine learning models have mainly been used to study geological logging data of a single sample point, ignoring the fact that logging data has a strong spatial correlation. In this study, we use convolutional neural network to extract single-point features, structural features, and multidimensional features from logging data and compare the identification effects of lithology identification models based on the three features. The identification model based on the multidimensional feature extraction achieves 77.94% correctness in the test set, which is the best result among the identification models based on CNN and the three machine learning models. Based on this feature extraction model, the feature fusion modules in U-net and feature pyramid are added respectively to build two feature fusion models to combine the features extracted from different convolutional layers and improve the effectiveness of the model. The model also introduces attention mechanism to improve the role of useful features in the model training process. The identification accuracy of the two feature fusion models, U-CNN and P-CNN, reached 79.67% and 80.02% on the test set, respectively, which verified the effectiveness of the feature fusion models for lithology identification in the study area.
Similar content being viewed by others
Data availability
Data not available due to legal restrictions. Due to relevant laws and regulations of this research, The provider of data did not agree for their data to be shared publicly, so supporting data is not available.
References
An P (2019) Research on reservoir parameter prediction method based on deep learning. Dissertation, China University of Petroleum (Qingdao)
Chen Y, Li G, Yang Z et al (2020) Identification of Lithology and Lithofacies of Chang 7 Reservoir in Heshui Area by KNN Algorithm. Well Logging Technol 44(02):182–185
Chen Y (2021) Study on Sedimentary System QuanTou Formation - YaoJia Formation in Southwestern of Songliao Basin. Dissertation, Northwest University (Xian)
Dev V, Eden M (2019) Gradient boosted decision trees for lithology classification. 9th International Conference on the Foundations of Computer Aided Process Design (FOCAPD) 47:113–118
Feng R (2020) Lithofacies classification based on a hybrid system of artificial neural networks and hidden Markov models. Geophys J Int 221(3):1484–1498
Ge R (2011) Synrift Structural Evolution and Crustal Extention in the Central Songliao Basin. Dissertation, Nanjing University (Nanjing)
He M, Gu H, Wan H (2020) Log interpretation for lithology and fluid identification using deep neural network combined with MAHAKIL in a tight sandstone reservoir. J Petrol Sci Eng 194:107498
Hu J, Shen L, Sun G et al (2020) Squeeze-and-Excitation Networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023
Hu Y (2021) Deep Learning for Recognition of Sedimentary Microfacies with Logging Data. Dissertation, University of Electronic Science and Technology of China (Chengdu)
Imamverdiyev Y, Sukhostat L (2019) Lithological facies classification using deep convolutional neural network. J Petrol Sci Eng 174:216–228
Li C, Cheng Y, Wang T et al (2020) The Controlling effect of Cenozoic Tectonic Evolution on the Mineralization of Sandstone-type uranium deposits in the Songliao Basin: Evidence from apatite fission tracks. Acta Geol Sin 94(10):2856–2873
Lin T, Dollar P, Girshick R, et al (2017) Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 936–944
Liu Y, Liu S, Ma Q et al (2019) Application of BP neural network method to identification of shale lithofacies of Luchaogou Formation in Santanghu Basin. Lithologic Reserv 31(04):101–111
Lu S (2022) Analysis Sedimentary Characteristics and Uranium Mineralization Conditions of the Second and Third Members of Qingshankou Fm in Songliao Basin. Uranium Min Metall 41(01):12–20
Puskarczyk E (2019) Artificial neural networks as a tool for pattern recognition and electrofacies analysis in Polish palaeozoic shale gas formations. Acta Geophys 67(6):1991–2003
Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 9351:234-241
Saporetti C, Goliatt L, Pereira E (2021) Neural network boosted with differential evolution for lithology identification based on well logs information. Earth Sci Inf 14(1):133–140
Sun Z, Jiang B, Li X et al (2020) A Data-Driven Approach for Lithology Identification Based on Parameter-Optimized Ensemble Learning. Energies 13(15):3903
Wan T (2019) Geological characteristics of Upper Cretaceous oil shale in the southern Songliao Basin and optimization of in situ development target area. Dissertation, Jilin University (Jilin)
Wang X, Yang S, Zhao Y et al (2018) Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field, Jiyang depression. J Petrol Sci Eng 166:157–174
Wang Q, Zhang X, Tang B et al (2021) Lithology identification technology using BP neural network based on XRF. Acta Geophys 69(6):2231–2240
Woo S, Park J, Lee J, et al (2018) CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV) 3–19.
Xiang M, Qin P, Zhang F (2020) Research and application of logging lithology identification for igneous reservoirs based on deep learning. J Appl Geophys 173:103929
Zeng L, Ren W, Shan L (2020) Attention-based bidirectional gated recurrent unit neural networks for well logs prediction and lithology identification. Neurocomputing 414:153–171
Zhang L (2012) Application of common mathematical physics methods in logging interpretation. Dissertation, Yangtze University (Jingzhou)
Zhang R, Li W, Mo T (2018a) Review of Deep Learning. Inf Control 47(04):385–397
Zhang G, Wang Z, Chen Y (2018b) Deep learning for seismic lithology prediction. Geophys J Int 215(2):1368–1387
Zhang C, Guo Y, Li M (2021) Review of Development and Application of Artificial Neural Network Models. Comput Eng Appl 57(11):57–69
Zhao Z, Wan X, Xi D et al (2010) Identification of Lake Bay Environment in Eastern Songliao Basin and Its Signification. Glocal Geol 29(02):262–270
Zhou K, Zhang J, Ren Y et al (2020) A gradient boosting decision tree algorithm combining synthetic minority oversampling technique for lithology identification. Geophysics 85(4):147–158
Funding
This work was supported by: Guizhou Provincial Science and Technology Plan Project "Promotion of digital exploration and development technology for mineral resources" QianKeHeChengGuo [2022] ZD 003); Guizhou Provincial Science and Technology Plan Project "Research and demonstration on metallogenic law of phosphorus, manganese and aluminum advantageous resources and rapid, efficient and intelligent exploration technology in Guizhou " QianKeHeZhanLue [2022] ZD 003); The central government guided the local science and Technology Development Fund Project "Research and development base of deep prediction and exploration technology of manganese resources" QiankeZhongyingdi[2021]4027; Guizhou high-level Innovative Talents Project QianKeHePingTingRenCai [2020]6019); China national uranium Co. Ltd project “Digital uranium exploration system”.
Author information
Authors and Affiliations
Contributions
Zhang XiaLin writing original draft and experiment Validation.Sun Qing completed data curation and formal analysis.Wang ZhenJiang, Zhang LuYi and Liang Peng carried out visualization.Wen JinJun completed conceptualization, methodology design and writing review & editing.All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflicts of interest
This manuscript has not been published or presented elsewhere in part or entirety and is not under consideration by another journal. There are no conflicts of interest to declare.
Additional information
Communicated by: Xiang Que
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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.
About this article
Cite this article
Zhang, X., Wen, J., Sun, Q. et al. Lithology identification technology of logging data based on deep learning model. Earth Sci Inform 16, 2545–2557 (2023). https://doi.org/10.1007/s12145-023-01051-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01051-2