共查询到20条相似文献，搜索用时 531 毫秒
1.
《地球物理学报》2021,64(6)
微地震震相识别和初至拾取是水力压裂微地震监测资料处理中的两个关键步骤,其结果会对后续事件定位和压裂裂缝缝网解释产生重要影响.常规方法如STA/LTA法、模板匹配法、多道互相关法等需要提取有效信号与噪声间振幅、偏振、频率、波形相似性等方面的特征差异完成震相识别和拾取工作.本文基于深度学习技术的自动特征提取能力,根据井中微地震观测系统的多道数据源特点,提出基于U-Net的多道联合震相识别和初至拾取方法(MT-Net).方法采用具有"逐采样点"识别能力的U-Net模型,模型训练阶段以具有不同信号特征的多道微地震监测记录作为输入,以P波、S波及噪声的概率分布标签作为输出,通过设置二维卷积操作使得道内与道间的波形信息同时被自适应地学习,以满足对相邻道间波形记录处理结果高度一致性的要求;测试阶段将连续记录中的分段波形馈入模型,通过设定P波、S波概率分布曲线阈值完成单震相、双震相和噪声的波形分类,同时对含有效震相的微地震事件完成初至拾取.实际微地震资料处理结果显示,本文方法与同样基于U-Net的单道方法(ST-Net)相比,显著降低了震相识别中低信噪比事件漏拾与误拾发生的概率;同时有效避免了部分单道发生严重的初至拾取结果偏差及P、S震相误拾等情况.本文方法的识别与拾取结果整体上达到了与多道互相关法接近的水平,可满足微地震监测资料处理中实时性和准确性的要求. 相似文献
2.
3.
《世界地震译丛》2020,(2)
地震震源位置和震源机制解的确定需要精确的P波到时和初动极性信息。由于这些参数的自动化算法的精度比人工识别的要低,因而在处理大数据时是存在一定问题的。本文通过训练卷积神经网络来获取P波到时和初动极性信息,该方法直接对波形记录进行学习,而不是特征提取。我们利用南加州地区1 820万条手动拾取的波形记录,来训练卷积神经网络。1 200万条无关联波形记录的交叉验证显示,自动与人工拾取之间的差异的标准差为0.023s。以人工识别的初动极性做参考,分类器拾取的精度为95%。同时,在不影响质量的前提下,与人工识别相比,分类器拾取的极性数量更多,从而获得的震源机制解数量几乎翻倍。经过训练的卷积神经网络具有很好的精度,这表明它们可以与地震专家一样好,甚至更好。 相似文献
4.
由于激发、接收及工区现场等导致野外采集的地震数据出现异常道,这时需要对地震记录道编辑处理.当数据量比较大时,人工进行道编辑工作量庞大.非人工做法主要是利用计算机将异常道剔除,没有对异常道细致分类,由此造成了大量的原始数据损失,异常道的产生原因也无从得知.随着计算机性能的提高,深度学习发展迅猛,卷积神经网络(CNN)在深度学习领域起着至关重要的作用.CNN避免了前期很多工作,可以直接输入数据训练模型,将模型用于分类预测.作为一种快速高效的识别算法,可以广泛应用到各个研究领域.本文对极性反转、单频信号、强振幅噪声、空道四种常见的异常道和正常道进行细致分类编号,利用优化的深度卷积神经网络算法识别坏道并进行有效分类,不仅有利于后续对相应道的特殊处理,而且有利于推断产生异常道的原因,在以后的工作中针对产生原因做相应的工作调整. 相似文献
5.
6.
勘探和开发非常规油气藏已经成为国际油气工业界的新热点.由于这类油藏具有低渗透率的特点,开采过程中往往需要多级压裂形成能够使烃类自由流动的裂隙.通过定位分析压裂过程中诱导的微地震震源能够帮助人们刻画裂缝属性(走向、密度等),评价压裂效果,分析断裂模式,推定震源机制等.微地震定位可以采用波动方程逆时聚焦方法实现.由于微地震数据信噪比低,加之速度模型不准确、稀疏观测等诸多因素使得定位的精度大打折扣.本文将波动方程逆时聚焦定位原理与干涉"成像"原理相结合,探讨多源微地震信号的干涉逆时定位算法,尤其扩展该算法到三维多分量地面、井中以及井地联合观测条件下.通过理论合成数据与实际射孔资料的数值试验,展示了该微地震定位算法的精度优势与抗噪特点,并指出波场聚焦微地震定位方法在实际应用中的制约因素与应对策略. 相似文献
7.
8.
本文以分层均匀"多层介质模型"为依据,正演模拟多炮人工地面地震记录.其观测方式为:三炮位置分别在1500m,2500m,3500m处;道检距25m,140道(或道检距5m,700道),偏移距1000 m.为提高地震反射层析成像的精度,运用"走时最小纵横波速度层析成像"与"波形基本解纵横波速度层析成像"相结合的方法,反演... 相似文献
9.
为了探索地震加速度时程记录的震级信息,训练卷积神经网络基于地震震级大小对地震记录进行分类,将K-NET和KiK-net中将近12万个地震记录作为样本,对其进行信息筛选和归一化,之后将地震加速度时程记录用作输入,训练卷积神经网络模型以M5.5为分类界限来区分大震和小震。结果显示,在训练集中基于该模型的分类准确率为93.6％,在测试集中的准确率为92.3％,具有良好的分类效果,这表明大震记录与小震记录之间存在一些根本的区别,即可通过地震动加速度时程记录获取一定的震级信息。 相似文献
10.
《地震地质》2021,43(3)
为实现天然地震与爆破、塌陷事件类型的快速高效识别,文中应用深度学习技术中的卷积神经网络模型,设计了基于单个事件单个台站波形记录的深度学习训练模块和基于单个事件多个台站波形记录的实时测试模块。以每个事件P波到时最早的5个台站记录到的原始三分向波形为输入,分别采用目前主流的Alex Net、VGG16、VGG19、Goog Le Net 4种卷积神经网络结构进行学习训练,结果显示各类卷积神经网络结构对训练集与测试集的识别准确率均达93%以上,且各个网络在训练过程中的训练集与测试集的准确率及代价函数的走势曲线基本一致。其中,Alex Net网络结构的识别准确率最高,测试集为98.51%,且未发生过拟合现象; VGG16、VGG19网络结构的准确率次之;Goog Le Net网络结构的识别准确率相对较低。为检验深度学习卷积神经网络在数字地震台网实时运行过程中的事件判别效能,选取训练好的Alex Net卷积神经网络开展基于单个事件多个台站波形记录的事件类型判定检验。最终结果显示,在山东台网实时触发的110个M≥0.7事件中,共有89个事件的类型被准确识别,准确率约为80.9%。具体到各个类型事件中,天然地震的准确率约为74.6%;爆破的准确率约为90.9%;塌陷事件的准确率为100%。若删除其中由于波形失真而造成的类型识别错误事件,则天然地震的识别准确率将提高至91.4%,而所有事件的整体识别准确率也将由80.9%提高至91.7%,与目前地震台网日常工作中人工判定的识别准确率基本相当。这表明,深度学习技术可以快速高效地实现天然地震与爆破、塌陷的事件类型识别。 相似文献
11.
Reservoir earthquake characteristics such as small magnitude and large quantity may result in low monitoring efficiency when using traditional methods. However, methods based on deep learning can discriminate the seismic phases of small earthquakes in a reservoir and ensure rapid processing of arrival time picking. The present study establishes a deep learning network model combining a convolutional neural network (CNN) and recurrent neural network (RNN). The neural network training uses the waveforms of 60 000 small earthquakes within a magnitude range of 0.8-1.2 recorded by 73 stations near the Dagangshan Reservoir in Sichuan Province as well as the data of the manually picked P-wave arrival time. The neural network automatically picks the P-wave arrival time, providing a strong constraint for small earthquake positioning. The model is shown to achieve an accuracy rate of 90.7% in picking P waves of microseisms in the reservoir area, with a recall rate reaching 92.6% and an error rate lower than 2%. The results indicate that the relevant network structure has high accuracy for picking the P-wave arrival times of small earthquakes, thus providing new technical measures for subsequent microseismic monitoring in the reservoir area. 相似文献
12.
发展高效、高精度、普适性强的自动波形拾取算法在地震大数据时代背景下显得越来越重要.波形自动拾取算法的主要挑战来自如何适应不同区域的不同类型地震事件的分类与筛选.本文针对地震事件-噪音分类这一问题,使用13839个汶川地震余震事件建立数据集,应用深度学习卷积神经网络(CNN)方法进行训练,并用8900个新的汶川余震事件作为检测数据集,其训练和检测准确率均达到95%以上.在对连续波形的检测中,CNN方法在精度和召回率上优于STA/LTA和Fbpicker传统方法,并能找出大量人工挑选极易遗漏的微震事件.最后,我们应用训练好的最优模型对选自全国台网的441个台站8天的连续波形数据进行了识别、到时挑取及与参考地震目录关联,CNN检出7016段波形,用自动挑选算法拾取到1380对P,S到时,并与540个地震目录事件成功关联,对1级以上事件总体识别准确率为54%,二级以上为80%,证明了CNN模型具有泛化能力,初步展示了CNN在发展兼具效率、精度、普适性算法,实时地震监测等应用上具有巨大潜力. 相似文献
13.
水力压裂是页岩气开发过程中的核心增产技术,微地震则广泛用于压裂分析、水驱前缘监测和储层描述.微地震反演过程中,用于反演的速度模型往往基于测井、地震或标定炮资料构建,忽略了压裂过程中裂缝及孔隙流体压力变化对地层速度的影响.本文首先基于物质守恒、渗流理论和断裂力学模拟三维水力压裂过程,得到地下裂缝发育特征和孔隙压力分布.继而根据Coates-Schoenberg方法和裂缝柔量参数计算裂缝和孔隙压力对速度场的影响,得到压裂过程中的实时速度模型.最后利用三维射线追踪方法正演微地震走时和方位信息,并采用常规微地震定位方法反演震源位置及进行误差分析.数值模拟结果表明,检波器空间分布影响定位精度,常规方法的定位误差随射线路径在压裂带中传播距离增加而变大,且不同压裂阶段的多点反演法与单点极化法精度相当. 相似文献
14.
Distributed acoustic sensing is a growing technology that enables affordable downhole recording of strain wavefields from microseismic events with spatial sampling down to ∼1 m. Exploiting this high spatial information density motivates different detection approaches than typically used for downhole geophones. A new machine learning method using convolutional neural networks is described that operates on the full strain wavefield. The method is tested using data recorded in a horizontal observation well during hydraulic fracturing in the Eagle Ford Shale, Texas, and the results are compared to a surface geophone array that simultaneously recorded microseismic activity. The neural network was trained using synthetic microseismic events injected into real ambient noise, and it was applied to detect events in the remaining data. There were 535 detections found and no false positives. In general, the signal-to-noise ratio of events recorded by distributed acoustic sensing was lower than the surface array and 368 of 933 surface array events were found. Despite this, 167 new events were found in distributed acoustic sensing data that had no detected counterpart in the surface array. These differences can be attributed to the different detection threshold that depends on both magnitude and distance to the optical fibre. As distributed acoustic sensing data quality continues to improve, neural networks offer many advantages for automated, real-time microseismic event detection, including low computational cost, minimal data pre-processing, low false trigger rates and continuous performance improvement as more training data are acquired. 相似文献
15.
由于地面微地震监测台站布设在地表,会受到地表起伏、低降速带厚度和速度变化的影响,降低了微地震事件的识别准确度和定位精度,限制了地面微地震监测技术在复杂地表地区的应用.因此,将三维地震勘探技术的思路引入到地面微地震监测中,提出了三维地震与地面微地震联合校正方法,将油气勘探和开发技术更加紧密地结合在一起.根据三维地震数据和低降速带测量数据,通过约束层析反演方法建立精确的近地表速度模型,将地面微地震台站从起伏地表校正到高速层中的平滑基准面上,有效消除复杂近地表的影响.其次,根据射孔数据和声波测井速度信息,通过非线性反演方法建立最优速度模型,由于已经消除复杂近地表的影响,在进行速度模型优化时不需要考虑近地表的影响,因而建立的速度模型更加准确.最后,在精确速度模型的基础上,通过互相关方法求取剩余静校正量,进一步消除了复杂近地表和速度模型近似误差的影响.三维地震与地面微地震联合校正方法采用逐步校正的思路,能够有效消除复杂近地表的影响,提高微地震数据的品质和速度模型的精确度,保证了微地震事件的定位精度,具有良好的应用前景. 相似文献
16.
微震监测是直观评价压裂过程和压裂效果的有效手段.微震事件识别是微震监测的首要步骤.然而对于低信噪比微震监测数据,常规识别方法很难取得满意效果.基于微震事件在时频域中的稀疏性,本文提出利用Renyi熵值表示微震监测数据的时频稀疏程度,并以时频距离为约束条件,建立以低熵值的道数为判别阈值的目标函数.本文方法能在识别出微震事件的同时,恢复出较为清晰的微震事件.通过数值计算和对实际监测数据的测试,表明该方法对低信噪比的微震监测数据有较好的处理效果. 相似文献
17.
Active Source Seismic Identification and Automatic Picking of the P-wave First Arrival Using a Convolutional Neural Network 总被引：1，自引：1，他引：0
XU Zhen WANG Tao XU Shanhui WANG Baoshan FENG Xuping SHI Jing YANG Minghan 《中国地震研究》2019,33(2):288-304
In seismic data processing, picking of the P-wave first arrivals takes up plenty of time and labor, and its accuracy plays a key role in imaging seismic structures. Based on the convolution neural network (CNN), we propose a new method to pick up the P-wave first arrivals automatically. Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment, the vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals (a total of 7242). Based on these arrivals, we establish the training and testing sets, including 25,290 event samples and 710,616 noise samples (length of each sample:2s). After 3,000 steps of training, we obtain a convergent CNN model, which can automatically classify seismic events and noise samples with high accuracy (> 99%). With the trained CNN model, we scan continuous seismic records and take the maximum output (probability of a seismic event) as the P-wave first arrival time. Compared with STA/LTA (short time average/long time average), our method shows higher precision and stronger anti-noise ability, especially with the low SNR seismic data. This CNN method is of great significance for promoting the intellectualization of seismic data processing, improving the resolution of seismic imaging, and promoting the joint inversion of active and passive sources. 相似文献
18.
快速、准确地识别天然地震和人工爆破事件是地震台网监测的重要工作之一,也是提高地震观测记录质量、开展地震研究工作的重要基础.针对反向传播神经网络、支持向量机等主流分类识别方法在地震事件分类识别应用上的不足,提出一种基于改进 EWT 和 LogitBoost集成分类器的地震事件分类识别算法.首先,基于S谱能量曲线对传统经验小波变换进行改进,将信号自适应分解为按频率和能量分布的本征模函数;其次,提取 P波与S波最大振幅比,前4个本征模函数的香农熵、对数能量熵,以及去噪后重构信号主频等特征;最后,采用基于集成学习 LogitBoost的决策树集成分类器进行分类.实验结果表明,所提算法具有较高的鲁棒性,能有效解决样本不足的问题,识别准确率达93．1%以上,比集成学习 AdaBoost、反向传播神经网络和支持向量机等方法提高了1%以上,且分类识别效果好. 相似文献
19.
Surface arrays became an important tool for monitoring the induced seismicity in hydraulic fracturing experiments and for assessing the impact of fluid injection on the fracturing process of microearthquakes. The layout of sensors plays a key role in this task because it controls the accuracy of event locations and retrieved seismic moment tensors. We simulate various configurations of grid sensor arrays characterized by a different number of sensors, array span, sensor spacing, depth of sources and various shear/tensile source mechanisms of events. The moment tensor inversion is carried out using synthetically calculated P-wave amplitudes with added random noise. A bias in the solutions is evaluated by errors in the double-couple percentage of inverted moment tensors because the double-couple errors inform us about the sensitivity of the network to detect the shear/tensile fracturing mode of induced microearthquakes. The results show that the accuracy of the double-couple percentage is mostly controlled by the offset-to-depth ratio R defined as the ratio of half of the network size to the event depth. The optimum value of R is in the range of 0.75–1.5 irrespective of the type of the focal mechanism. If 121 (11 × 11) sensors are distributed in a regular grid and recorded data are characterized by a 10% random noise, the double-couple error is less than 6%. This error increases, if R is not optimum or if the number of sensors is reduced. However, even sparse arrays with 49 (7 × 7) or 16 (4 × 4) sensors can yield a reasonable accuracy, provided the surface grid arrays are designed to have an optimum size. 相似文献
20.
The paper discusses microseismic monitoring during oil well stimulation by hydraulic fracturing, an emergent technology used
for hydraulic fracturing layer control. The passive monitoring is a new widely developing technology of HFL control. The main
factor affecting the results of passive seismic monitoring is the event location accuracy. The passive monitoring acquisition
system utilizes one three components seismic probe deployed into the observation well. To evaluate the location accuracy of
induced events for one observation well we applied traditional kinematic approach based on picking of earthquake P- and S-waves arrivals. The influence of geometric parameters of geophones location in a borehole, their quantity, picking errors
of waves arrivals on the accuracy of microearthquakes location is studied. 相似文献