提升地震相边缘和不规则体识别效果的半监督识别方法
A Semi-Supervised Recognition Method to Improve the Recognition of Earthquake Phase Boundaries and Irregular Bodies
DOI: 10.12677/CSA.2023.139168, PDF,    科研立项经费支持
作者: 李晓玲, 硕良勋*, 赵虹阳：河北地质大学信息工程学院，河北 石家庄；柴变芳：河北地质大学信息工程学院，河北 石家庄;河北省智能传感物联网技术工程研究中心，河北 石家庄
关键词: 半监督学习；语义分割；地震相识别；有效通道注意力机制；双注意力机制；Semi-Supervised Learning； Semantic Segmentation； Seismic Facies Identification； Effective Channel Attention Mechanism； Dual Attention Mechanism
摘要: 近年来随着深度学习的快速发展和地震相识别智能化研究深入，国内外提出了多种基于深度学习的地震相识别方法。但深度学习方法需要大量标注信息学习网络参数，实际上地震数据标注成本高，困难大。鉴于此，提出半监督地震相识别方法。利用少部分标注数据训练基于语义分割网络的地震相识别模型，并用模型对未标注的数据进行类别推断。该方法可扩展训练数据集规模，降低标注成本，提高模型的准确性和泛化能力。相较于仅用有限标注数据的模型性能有显著提升。该模型采用Deeplabv3+网络，在复杂深层相带存在边缘不清晰以及类内预测不一致问题，针对该问题，提出提升地震相边缘和不规则体识别效果的半监督识别方法。该方法在Deeplabv3+编码部分引入双注意力机制改善同类预测不一致现象，同时解码部分加入了有效通道注意力模块，结合低层特征进一步改善预测目标边界不清晰问题。改进后的Deeplabv3+网络有效改善存在的问题。
Abstract: In recent years, with the rapid development of deep learning and indepth research on seismic phase recognition intelligence, various deep learning-based seismic phase recognition methods have been proposed both domestically and internationally. However, deep learning methods require a large amount of labeled information to learn network parameters, and in fact, the cost of seismic data labeling is high and difficult. In view of this, a semi-supervised seismic phase recognition method is proposed. The seismic phase recognition model based on a semantic segmentation network is trained using a small number of labeled data, and the model is used to infer categories for unlabeled data. This method can expand the training dataset scale, reduce the labeling cost, and improve the accuracy and generalization ability of the model. Compared with models that use only limited labeled data, the performance of this method has significant improvements. This model uses the Deeplabv3+ network, which has problems such as unclear edges in complex deep phase bands and inconsistent predictions within classes. To address these issues, a semi-supervised recognition method for improving the edge detection and irregular body recognition effect of seis-mic phases is proposed. This method introduces a double attention mechanism into the Deeplabv3+ encoding part to improve the problem of inconsistent predictions among similar classes, while adding an effective channel attention module to the decoding part to further improve the problem of unclear prediction targets by combining low-level features. The improved Deeplabv3+ network effectively improves the problem.
文章引用：李晓玲, 柴变芳, 硕良勋, 赵虹阳. 提升地震相边缘和不规则体识别效果的半监督识别方法[J]. 计算机科学与应用, 2023, 13(9): 1704-1712. https://doi.org/10.12677/CSA.2023.139168

参考文献

[1] 蒋沛凡, 邓飞, 严星. 基于Swin Transformer特征提取的微地震初至拾取方法[J]. 地球物理学进展, 2023, 38(3): 1132-1142.
[2] Wu, X.M., Liang, L.M., Shi, Y.Z. and Fomel, S. (2019) FaultSeg3D: Using Synthetic Data Sets to Train an End-to-End Convolutional Neural Network for 3D Seismic Fault Segmentation. Geophysics, 84, IM35-IM45. [Google Scholar] [CrossRef] 
[3] 韩卫雪, 周亚同, 池越. 基于深度学习卷积神经网络的地震数据随机噪声去除[J]. 石油物探, 2018, 57(6): 862-869, 877.
[4] Chevitarese, D.S., Szwarcman, D., Silva, R.M.G. and Brazil, E.V. (2018) Deep Learning Applied to Seismic Facies Classification: A Methodology for Training. Saint Petersburg, 2018, 1-5. [Google Scholar] [CrossRef] 
[5] Zhao, T. (2018) Seismic Facies Classification Using Different Deep Convo-lutional Neural Networks. 2018 SEG International Exposition and Annual Meeting, Anaheim, 14-19 October 2018. [Google Scholar] [CrossRef] 
[6] Zhang, H.R., Chen, T.S., Liu, Y., Zhang, Y.X. and Liu, J. (2021) Automatic Seismic Facies Interpretation Using Supervised Deep Learning. Geophysics, 86, IM15-IM33. [Google Scholar] [CrossRef] 
[7] Wu, X.M., Shi, Y.Z., Fomel, S., et al. (2018) Convolutional Neural Networks for Fault Interpretation in Seismic Images. Society of Exploration Geophysicists, Houston. [Google Scholar] [CrossRef] 
[8] 闫星宇, 顾汉明, 罗红梅, 闫有平. 基于改进深度学习方法的地震相智能识别[J]. 石油地球物理勘探, 2020, 55(6): 1169-1177, 1159.
[9] He, M.S., Song, H.Z., Zhang, K.M., et al. (2022) Incremental Semi-Supervised Learning for Intelligent Seismic Facies Identification. Applied Geophysics, 19, 41-52. [Google Scholar] [CrossRef] 
[10] Liu, M.L., Li, W.C., Jervis, M. and Nivlet, P. (2020) Seismic Facies Classifica-tion Using Supervised Convolutional Neural Networks and Semisupervised Generative Adversarial Networks. Geophysics, 85, 1JA-Z18. [Google Scholar] [CrossRef] 
[11] ColéOu, T., Poupon, M. and Azbel, K. (2003) Unsupervised Seismic Facies Classi-fication: A Review and Comparison of Techniques and Implementation. Leading Edge, 22, 942-953. [Google Scholar] [CrossRef] 
[12] 张, 郑晓东, 李劲松, 等. 基于SOM和PSO的非监督地震相分析技术[J]. 地球物理学报, 2015, 58(9): 3412-3423. [Google Scholar] [CrossRef] 
[13] Yang, L., Zhuo, W., Qi, L., Shi, Y.H. and Gao, Y. (2022) ST++: Make Self-Training Work Better for Semi-Supervised Semantic Segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, 18-24 June 2022, 4258-4267. [Google Scholar] [CrossRef] 
[14] 刘文祥, 舒远仲, 唐小敏, 等. 采用双注意力机制Deeplabv3+算法的遥感影像语义分割[J]. 热带地理, 2020, 40(2): 303-313.
[15] Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2014) Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. arXiv: 1412.7062.
[16] Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2017) Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848. [Google Scholar] [CrossRef] 
[17] Chen, L.C., Papandreou, G., Schroff, F., et al. (2017) Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv: 1706.05587.
[18] 韩红. 基于深度卷积神经网络的地震相识别[D]: [硕士学位论文]. 石家庄: 河北地质大学, 2022.