当前位置: X-MOL 学术Geophysics › 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.)
Generalized neural network trained with a small amount of base samples: Application to event detection and phase picking in downhole microseismic monitoring
Geophysics ( IF 3.0 ) Pub Date : 2021-09-03 , DOI: 10.1190/geo2020-0955.1
Xiong Zhang 1 , Huihui Chen 1 , Wei Zhang 2 , Xiao Tian 1 , Fangdong Chu 3
Affiliation  

The deep-learning method has been successfully applied to many geophysical problems to extract features from seismic big data. However, some applications may not have sufficient available data to directly train a generalized neural network. We have applied data augmentation on a significantly small number of samples to train a generalized neural network for microseismic event detection and phase picking, which could be used in different project settings and areas. We use the U-Net architecture consisting of 2D convolutional layers to create the prediction function, and we map the waveforms recorded by using multiple receivers to the P/S arrival time labels; thus, the neural network can learn the P/S moveout features from multiple receivers. The training set is generated by simulating various realizations of the data based on 10 original samples from the beginning of a hydraulic fracturing stage. The trained neural network is then used to detect the events and pick the P/S phases from the continuous data for different stages and projects. A grid search from a precalculated traveltime table is performed to determine the event location after an event is detected. We build a real-time event detection and location workflow without human intervention by combining the neural network and grid search method, and we apply the workflow to a different stage from the training events and a completely independent project that the neural network has not encountered. The results indicate that microseismic events are successfully detected and located, and the picking performance of the neural network is superior to that of a traditional autoregression picker.

中文翻译:

用少量基础样本训练的广义神经网络:在井下微地震监测中的事件检测和相位拾取中的应用

深度学习方法已成功应用于许多地球物理问题,从地震大数据中提取特征。但是,某些应用程序可能没有足够的可用数据来直接训练广义神经网络。我们在极少数样本上应用了数据增强,以训练用于微震事件检测和相位拾取的广义神经网络,该网络可用于不同的项目设置和领域。我们使用由 2D 卷积层组成的 U-Net 架构来创建预测函数,并将使用多个接收器记录的波形映射到 P/S 到达时间标签;因此,神经网络可以从多个接收器中学习 P/S 时差特征。训练集是通过模拟数据的各种实现而生成的,该数据基于来自水力压裂阶段开始的 10 个原始样本。然后使用经过训练的神经网络来检测事件并从不同阶段和项目的连续数据中选择 P/S 阶段。在检测到事件后,执行从预先计算的旅行时间表进行网格搜索以确定事件位置。我们通过结合神经网络和网格搜索方法构建了一个无需人工干预的实时事件检测和定位工作流,并将该工作流应用于与训练事件不同的阶段和神经网络未遇到的完全独立的项目。结果表明微震事件被成功探测和定位,
更新日期:2021-09-04
down
wechat
bug