A Deep Learning-Based Seismic Horizon Tracking Method With Uncertainty Encoding and Vertical Constraint

被引:1
|
作者
Liao, Zhiying [1 ]
Zhu, Peimin [1 ]
Zhang, Hao [1 ]
Li, Zewei [2 ]
Li, Zi'ang [1 ]
Ali, Muhammad [1 ]
机构
[1] China Univ Geosci, Sch Geophys & Geomat, Wuhan 430074, Peoples R China
[2] CNPC, BGP Inc, Geophys Res Inst, Zhuozhou 072750, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2024年 / 62卷
基金
中国国家自然科学基金;
关键词
Uncertainty; Training; Deep learning; Encoding; Task analysis; Target tracking; Three-dimensional displays; horizon interpretation; uncertain label; vertical constraint; NEURAL-NETWORKS;
D O I
10.1109/TGRS.2024.3424467
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Deep learning-based seismic horizon tracking methods have been extensively researched in the past few years. However, the predicted results of previous methods are currently unstable and require additional processing to obtain reasonable interpretations, limiting their applications to field seismic data. There are two potential reasons for this: 1) the training labels may not consider the uncertainty in horizon interpretation and 2) the characteristics of the seismic data used for training may differ from those for prediction (domain shift). In addition, the previous deep learning methods are mostly based on point-by-point cost functions, which are not well-suitable for horizon tracking problems. To address these issues, we proposed a method that mimics the process of manual horizon interpretation to avoid the domain shift problem and regard horizon identification and tracking as a problem of conditional probability density estimation using deep learning. In the North Sea F3 seismic data experiments, our proposed method can predict horizons accurately and stably when we select only 1.6% of the seismic sections to create labels. Taking mean absolute error (MAE) and accuracy as evaluation indices, the MAE for single-horizon prediction is as low as 2.0 ms, and the accuracy reaches 98.1%. A surprising finding revealed by the experiments is that the predicted results could provide a perspective of underground structures, such as faults and salt domes, demonstrating the feasibility of our method in interpreting complex field seismic data.
引用
收藏
页码:1 / 1
页数:13
相关论文
共 50 条
  • [31] Ensemble Deep Learning-Based Porosity Inversion From Seismic Attributes
    Song, Jianguo
    Ntibahanana, Munezero
    Luemba, Moise
    Tondozi, Keto
    Imani, Gloire
    IEEE ACCESS, 2023, 11 : 8761 - 8772
  • [32] Considering Uncertainty Improves Deep Learning-based Lung Cancer Subtyping
    Lee, Yongeun
    Kwak, Tae-Yeong
    Kim, Sun Woo
    Chang, Hyeyoon
    MODERN PATHOLOGY, 2022, 35 (SUPPL 2) : 1314 - 1315
  • [33] Explainable uncertainty quantifications for deep learning-based molecular property prediction
    Yang, Chu-, I
    Li, Yi-Pei
    JOURNAL OF CHEMINFORMATICS, 2023, 15 (01)
  • [34] Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra
    Patel, Kanil
    Beluch, William
    Rambach, Kilian
    Cozma, Adriana-Eliza
    Pfeiffer, Michael
    Yang, Bin
    2021 IEEE RADAR CONFERENCE (RADARCONF21): RADAR ON THE MOVE, 2021,
  • [35] Uncertainty Qualification for Deep Learning-Based Elementary Reaction Property Prediction
    Liu, Yan
    Mo, Yiming
    Cheng, Youwei
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2024, 64 (21) : 8131 - 8141
  • [36] Considering Uncertainty Improves Deep Learning-based Lung Cancer Subtyping
    Lee, Yongeun
    Kwak, Tae-Yeong
    Kim, Sun Woo
    Chang, Hyeyoon
    LABORATORY INVESTIGATION, 2022, 102 (SUPPL 1) : 1314 - 1315
  • [37] Deep learning-based stochastic modelling and uncertainty analysis of fault networks
    Han, Shuai
    Li, Heng
    Li, Mingchao
    Zhang, Jiawen
    Guo, Runhao
    Ma, Jie
    Zhao, Wenchao
    BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT, 2022, 81 (06)
  • [38] Uncertainty Quantification of Deep Learning-Based Statistical Downscaling of Climatic Parameters
    Nourani, Vahid
    Khodkar, Kasra
    Baghanam, Aida Hosseini
    Kantoush, Sameh Ahmed
    Demird, Ibrahim
    JOURNAL OF APPLIED METEOROLOGY AND CLIMATOLOGY, 2023, 62 (09) : 1223 - 1242
  • [39] Explainable uncertainty quantifications for deep learning-based molecular property prediction
    Chu-I Yang
    Yi-Pei Li
    Journal of Cheminformatics, 15
  • [40] DEEP LEARNING-BASED CLASSIFICATION OF SEISMIC EVENTS USING WAVEFORM DATA
    Vasti, Manka
    Dev, Amita
    ADVANCES AND APPLICATIONS IN DISCRETE MATHEMATICS, 2025, 42 (01): : 17 - 45