Abstract
The development and distribution of interlayers in sandstones can lead to increased heterogeneity in the formation within the reservoir, which further affects the movement of fluids in the formation. Therefore, it is essential to accurately evaluate the interlayers in sandstones, as the precise evaluation of interlayers in sandstones is of great importance for identifying the distribution of underground fluid systems. The logging data of interlayers are inadequate for traditional Machine Learning training due to their low measurement proportion compared to the conventional layers. In logging data, the amount of data in interlayers is significantly smaller than that of conventional reservoirs. Traditional machine learning models are mostly based on samples with balanced distribution. By contrast, semi-supervised learning requires a small number of labeled samples for learning, and then combines a large number of unlabeled samples for modeling. To verify the feasibility of semi-supervised learning in the identification of interlayers, the Donghe sandstone section of the H oilfield was taken as an example. First, the core analysis results were used to label the logging data; then, to uncover more response information that can characterize the interlayers on the logging curve, multiple features were extracted to construct cross features. Finally, an improved model based on autoencoders—probabilistic autoencoder (PAE)—is proposed to address the issue of interlayer recognition for imbalanced samples. The PAE model can calculate the probability of belonging to a different class for unlabeled samples, and classify new samples according to the maximum probability. Experimental results show that, compared with traditional machine learning methods and ensemble learning methods, PAE achieves higher recognition accuracy and better generalization performance by updating the algorithm, and can be used as a simple and fast method for interlayer recognition. The results of the algorithm demonstrate that the semi-supervised method is of great significance for exploring and developing complex heterogeneous oil reservoirs. The research results are of great importance for exploring and developing complex heterogeneous oil reservoirs.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Deng Y, Guo R, Tian Z, Tan W, Yi Y, Xu Z, Xiao C, Cao X, Chen L (2016) Geological characteristics and genesis of intercalation layer of carbonate reservoirs: taking the west gulna oilfield in iraq a case of the cretaceous mishrif group. Pet Explor Dev 43(01):136–144
Fu XF, Lan X, Meng LD et al (2016) Characteristics of fault zones and their control on remaining oil distribution at the fault edge: a case study from the northern Xingshugang Anticline in the Daqing Oilfield, China. Pet Sci 13(3):418–433
Guo C, Ni L, Chen J (2020) Characteristics and distribution of interlayer in gravel-bearing sandstone segment in Tazhong area. Sci Technol Eng 20(7):2625–2633
Guo J, Wang W, Tan J et al (2019) Fine Characterization Method for Interlayers in Complex Meander River Sandstone Reservoir: A Case Study of Um7 Sand of C Oilfield in Bohai Bay Area. Int J Geosci 10(04):405
Han R, Liu Q, Jiang T, Xu H, Xu Z, Zho L, Lei C, Zhang P (2014) Feature, origin and distribution of calcareous interlayers: a case of Carboniferous Donghe sandstone in Hade Oil Field, Tarim Basin, NW China. Pet Explor Dev 41(4):475–484
Hu W (2008) On the necessity and feasibility of implementing secondary development projects in old oilfields. Pet Explor Dev 01:1–5
Li F, Xinmin S, Rui G, Lifeng L, Shiqi S (2021) Characteristics and genesis of interlayers in thick bioclastic limestone reservoirs: a case study of Cretaceous Mishrif Formation of the M oilfield in the Middle East. Acta Petrolei Sinica 42(7):853–864
Li H, Xinran W, Shanbin C, Xilin L, Qianping Z (2018) Effect of intra-formational bed on the remaining oil distribution in offshore polymer-flooding reservoir. Special Oil & Gas Reservoirs 25(5):135–140
Liu YM, Hou JG, Cai MJ et al (2009) Method of detailed reservoir description in secondary development of old oilfield. Sci Technol Rev 4:46–49
Liu YM, Hou JG, Song BQ et al (2011) Characterization of interlayers within braided-river thick sandstones: A case study on the Lamadian oilfield in Daqing. Acta Petrolei Sinica 32(5):836–841
Lun Z, Jincai W, Li C et al (2014) Influences of sandstone superimposed structure and architecture on waterflooding mechanisms: A case study of Kumkol Oilfield in South Turgay Basin, Kazakhstan. Pet Explor Dev 41(1):96–104
Lun Z, Jincai W, Li C et al (2017) Influences of delta sandstone architecture on waterflooding sweep characteristics: A case study of layer J-II of Kumkol South oilfield in South Turgay Basin, Kazakstan. Pet Explor Dev 44(3):437–445
Miyaji M, Danno M, Kawanaka H, Oguri K (2008) Driver’s cognitive distraction detection using AdaBoost on pattern recognition basis. In: 2008 IEEE International Conference on Vehicular Electronics and Safety, Columbus, USA, pp 51–56
Ng A (2011) Sparse autoencoder. CS294A Lecture notes, 72(2011):1–1
Qu H, Xue D, Sun D, Huang Y, Zhang S (2019) Oil control model of interlayer in thick reservoir of Taizhou Formation in Chen 3 fault block at high water cut stage. Complex Hydrocarbon Reservoirs 12(2):41–45
Saritha M, Joseph KP, Mathew AT (2013) Classification of MRI brain images using combined wavelet entropy based spider web plots and probabilistic neural network. Pattern Recogn Lett 34(16):2151–2156
Suk HI, Lee SW, Shen D et al (2015) Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Struct Funct 220(2):841–859
Sun T, Mu L, Zhao G (2014) Types and characterization methods of sand-like braided river reservoir interlayers: A case study of Hegli oilfield in Sultan’s Muglate Basin. Pet Explor Dev 41(01):112–120
Wang J, Liu HQ, Hong C, Kang AH, Geng CH (2016) Investigation on formation and distribution of remaining oil and sensitivity analysis in fracture-vuggy media. Energy Sources Part A-Recovery Utilization And Environmental Effects 38(2):214–226
Yu N, Yu Z, Pan Y (2017) A deep learning method for lincRNA detection using auto-encoder algorithm. BMC Bioinformatics 18(15):511
Zhang J, Shan S, Kan M, Chen X (2014) Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8690. Springer, Cham
Zhang Y, Zhang E, Chen W (2016) Deep neural network for halftone image classification based on sparse auto-encoder. Eng Appl Artif Intell 50:245–255
Zhou X, Ding W, Chang L, Niu Y, Yin S, Zhang M, Sun Y (2017) Identification of the shoreline sandstone reservoir interlayer by the “three-ended staffing” method: taking the donghe sandstone of the hudson oilfield in the tarim basin as example. Geosci Front 24(05):328–338
Acknowledgements
This work is supported by the CNPC-SWPU Innovation Alliance(2020CX010204). We also thank the Research Institute of Exploration and Development of Southwest Oil & Gas field Company, PetroChina for providing samples and data.
Funding
This work is supported by the CNPC-SWPU Innovation Alliance(2020CX010204).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study’s conception and design. Shixiang Jiao, Jun Zhao, and Yufei He wrote the main manuscript. Shixuan Zhao and Zhenguan Wu analyzed the data. Tianyi Zeng and Rui Zhang prepared figures.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflict 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 H. Babaie
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
Jiao, S., Zhao, J., He, Y. et al. Semi-supervised interlayer intelligent recognition method. Earth Sci Inform 16, 2187–2197 (2023). https://doi.org/10.1007/s12145-023-01021-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01021-8