Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples
Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples
复制标题
DOI：
10.3390/en14123650
复制
发表时间：
2021-06
期刊：
影响因子：
3.2
通讯作者：
Zhe Yan;Zheng Zhang;Shaoyong Liu
中科院分区：
文献类型：
--
作者：
Zhe Yan;Zheng Zhang;Shaoyong Liu
断层解释是地震构造解释和储层表征的重要组成部分。在传统方法中，断层被检测为反射不连续或突变，并在叠后地震数据中手动跟踪，这非常耗时。为了提高效率，人们提出了多种自动故障检测方法，其中基于深度学习的方法受到了广泛关注。然而，深度学习技术需要大量标记的地震样本作为训练数据集。虽然合成地震数据量可以保证，标注也准确，但合成数据与真实数据之间的差异仍然存在。为了克服这个缺点，我们应用迁移学习策略来通过深度学习方法提高自动故障检测的性能。我们首先使用合成地震数据预训练深度神经网络。然后我们用真实的地震样本重新训练网络。我们使用随机样本一致性（RANSAC）方法来获取真实的地震样本并自动生成相应的标签。三个真实的 3D 示例证明，通过使用少量真实地震样本重新训练网络，可以大大提高预训练网络模型的故障检测精度。
Fault interpretation is an important part of seismic structural interpretation and reservoir characterization. In the conventional approach, faults are detected as reflection discontinuity or abruption and are manually tracked in post-stack seismic data, which is time-consuming. In order to improve efficiency, a variety of automatic fault detection methods have been proposed, among which widespread attention has been given to deep learning-based methods. However, deep learning techniques require a large amount of marked seismic samples as a training dataset. Although the amount of synthetic seismic data can be guaranteed and the labels are accurate, the difference between synthetic data and real data still exists. To overcome this drawback, we apply a transfer learning strategy to improve the performance of automatic fault detection by deep learning methods. We first pre-train a deep neural network with synthetic seismic data. Then we retrain the network with real seismic samples. We use a random sample consensus (RANSAC) method to obtain real seismic samples and generate corresponding labels automatically. Three real 3D examples are included to demonstrate that the fault detection accuracy of the pre-trained network models can be greatly improved by retraining the network with a few amount of real seismic samples.