当前位置: X-MOL 学术Geophys. Prospect. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning from unlabelled real seismic data: Fault detection based on transfer learning
Geophysical Prospecting ( IF 1.8 ) Pub Date : 2021-04-16 , DOI: 10.1111/1365-2478.13097
Ruoshui Zhou 1 , Xingmiao Yao 1 , Guangmin Hu 1 , Fucai Yu 1
Affiliation  

Significant advances have been made towards fault detection using deep learning. However, the fault labelling of seismic data requires great human effort. The resulting small sample problem makes traditional deep learning methods difficult to achieve desired results. Existing research proposes to train a deep learning model with labelled synthetic seismic data to get good fault detection results. However, due to the complexity of the actual geological situation, there are inevitable differences between synthetic seismic data and real seismic data in many aspects such as seismic signal frequency, frequency of fault distribution and degree of noise disturbance, which lead to the fact that the deep learning model trained by synthetic seismic data is difficult to get good fault detection result in field data applications. We propose to use transfer learning to reduce the impact of data differences to solve this problem: part of the deep transfer learning model is used to learn fault-related features. And the other part of the deep transfer learning model is used to mine common features between the real seismic data and the synthetic seismic data, which makes the deep transfer learning model more suitable for real seismic data. Compared with the latest research progress, our method can greatly improve the effect of fault detection without real data label, which can significantly save the cost of manual label processing.

中文翻译:

从未标记的真实地震数据中学习:基于迁移学习的故障检测

使用深度学习进行故障检测已经取得了重大进展。然而,地震数据的断层标记需要大量的人力。由此产生的小样本问题使得传统的深度学习方法难以达到预期的效果。现有研究提出用标记的合成地震数据训练深度学习模型以获得良好的断层检测结果。但由于实际地质情况的复杂性,合成地震资料与真实地震资料在地震信号频率、断层分布频率、噪声扰动程度等诸多方面存在不可避免的差异,导致由合成地震数据训练的深度学习模型在现场数据应用中难以得到良好的断层检测结果。我们建议使用迁移学习来减少数据差异的影响来解决这个问题:部分深度迁移学习模型用于学习故障相关的特征。而深度迁移学习模型的另一部分则用于挖掘真实地震数据与合成地震数据的共性,使得深度迁移学习模型更适合真实地震数据。与最新的研究进展相比,我们的方法可以大大提高没有真实数据标签的故障检测效果,可以显着节省人工标签处理的成本。而深度迁移学习模型的另一部分则用于挖掘真实地震数据与合成地震数据的共性,使得深度迁移学习模型更适合真实地震数据。与最新的研究进展相比,我们的方法可以大大提高没有真实数据标签的故障检测效果,可以显着节省人工标签处理的成本。而深度迁移学习模型的另一部分则用于挖掘真实地震数据与合成地震数据的共性,使得深度迁移学习模型更适合真实地震数据。与最新的研究进展相比,我们的方法可以大大提高没有真实数据标签的故障检测效果,可以显着节省人工标签处理的成本。
更新日期:2021-06-14
down
wechat
bug