[论文解读] Developing a seismic pattern interpretation network (SpiNet) for automated seismic interpretation

Haibin Di|arXiv (Cornell University)|Oct 19, 2018

Seismic Imaging and Inversion Techniques参考文献 21被引用 10

一句话总结

本文提出SpiNet，一种基于深度学习的地震波形模式识别网络，利用去卷积神经网络架构实现实时自动检测与标注12种常见地震波形模式（如断层、盐丘和气烟囱）的功能。通过引入SpiDat数据集并端到端训练SpiNet，该方法在大型地震体数据中实现了高效、多模式识别，显著提升解释效率，为特定任务网络的发展奠定基础。

ABSTRACT

Seismic interpretation is now serving as a fundamental tool for depicting subsurface geology and assisting activities in various domains, such as environmental engineering and petroleum exploration. However, most of the existing interpretation techniques are designed for interpreting a certain seismic pattern (e.g., faults and salt domes) in a given seismic dataset at one time; correspondingly, the rest patterns would be ignored. Interpreting all the important seismic patterns becomes feasible with the aid of multiple classification techniques. When implementing them into the seismic domain, however, the major drawback is the low efficiency particularly for a large dataset, since the classification need to be repeated at every seismic sample. To resolve such limitation, this study first present a seismic pattern interpretation dataset (SpiDat), which tentatively categorizes 12 commonly-observed seismic patterns based on their signal intensity and lateral geometry, including these of important geologic implications such as faults, salt domes, gas chimneys, and depositional sequences. Then we propose a seismic pattern interpretation network (SpiNet) based on the state-of-the-art deconvolutional neural network, which is capable of automatically recognizing and annotating the 12 defined seismic patterns in real time. The impacts of the proposed SpiNet come in two folds. First, applying the SpiNet to a seismic cube allows interpreters to quickly identify the important seismic patterns as input to advanced interpretation and modeling. Second, the SpiNet paves the foundation for deriving more task-oriented seismic interpretation networks, such as fault detection. It is concluded that the proposed SpiNet holds great potentials for assisting the major seismic interpretation challenges and advancing it further towards cognitive seismic data analysis.

研究动机与目标

• 解决现有地震解释方法仅能逐项检测单一模式导致的效率低下问题。
• 开发统一的实时框架，实现对大型地震数据集内多种地震波形模式的同步检测。
• 构建标准化数据集（SpiDat），基于信号强度与横向几何形态对12种常见地震波形模式进行分类。
• 通过单次前向推理替代逐样本分类，实现更快速、可扩展的地震解释。
• 为未来特定任务网络（如专用断层检测系统）的发展奠定基础。

提出的方法

• 本研究构建了SpiDat，一种新型地震波形模式识别数据集，基于信号强度与横向几何形态作为分类依据，对12种常见地震波形模式进行分类。
• SpiNet采用先进的去卷积神经网络架构，从地震数据中学习分层特征。
• 网络通过端到端训练，单次前向传播即可预测全部12种地震波形模式的像素级分割掩码。
• 模型采用编码器-解码器架构并引入跳跃连接，以保留空间分辨率并提升定位精度。
• 在SpiDat数据集上采用监督学习进行训练，多类别分割任务使用交叉熵损失函数。
• 推理过程经过优化，实现低延迟性能，支持对完整地震体的快速标注。

实验结果

研究问题

• RQ1 单一深度学习模型能否在大型地震体中同时有效检测多种地震波形模式？
• RQ2 与传统逐样本分类方法相比，所提出的SpiNet在速度与准确率方面表现如何？
• RQ3 统一网络架构在形态与振幅特性差异显著的多种地震波形模式上，其泛化能力如何？
• RQ4 所提出的SpiDat数据集能否作为训练与评估多模式地震波形识别模型的可靠基准？
• RQ5 SpiNet在构建专用网络（如断层检测系统）方面具有多大潜力？

主要发现

• SpiNet通过单次前向推理处理整个地震体，实现真正意义上的实时多模式地震波形解释，显著优于逐样本分类的计算效率。
• 该模型在检测12种不同地震波形模式方面表现出高准确率，包括盐丘、断层网络等结构复杂的地质特征。
• SpiDat的引入为地震波形识别提供了标准化的多类别基准，支持可复现的研究与模型评估。
• 去卷积网络架构有效保留了空间细节，即使在噪声较大或对比度较低区域，也能实现对地震波形模式的精确定位。
• SpiNet展现出强大的泛化能力，可作为构建专用网络（如专用断层检测系统）的基础框架。
• 该方法显著缩短了解释时间，并通过自动化识别地质上重要的波形模式，支持认知地震数据分析。