人工神经网络在地震危险性分析中应用的探讨

人工神经网络是新近发展起来的一项高新仿生信息处理技术，本文以地震潜在震源区识别为例，探讨了人工神经网络分类识别在地震危险性分析中应用的可行性和前景，结果表明，人工神经网络具有识别精度高、方法简单、适应性强等多项优点，在地震危险性分析、烈度评定、地震预报等方面具有广阔应用前景。     

地震序列类型预测的人工神经网络方法

本文提出预测地震序列类型的人工神经网络方法，并选取一组实例作为研究对象，验证了该方法的可靠性。结果表明，人工神经网络方法性能良好，可望成为地震序列类型预测的有效工具。     

基于人工神经网络的地震活动性研究

人工神经网络通过神经元之间的相互作用来完成整个网络的信息处理,具有自学习和自适应等一系列优点,因而用它来进行地震活动性研究是可行的。针对地震活动性问题,初步建立了基于人工神经网络的计算分析系统,给出了应用实例。     

浅谈地震谣言及正确应对地震

简述地震谣言的社会危害、特征、传播途径及引起民众恐慌的原因,着重论述正确识别地震谣言的有效方法和应对措施,探讨地震突发时如何正确应对地震。     

浅谈地震剖面的假象识别

假象识别是正确解释地震剖面的前提,也是描述地震成像保真度(精准度)的主要标准之一.本文通过分析反射地震剖面实例,对几种常见的、易被误解的地震成像假象的特征进行了分类阐述,提出基于成因识别地震成像假象的思路.从地震剖面成像过程来看,假象的成因包括信号误判、成像畸变和波速模型误差这三个主要因素.许多不易被识别的假象起源于地...     

应用地震子波理论识别破碎带

本文提出了在浅层地震勘探中应用地震子波理论识别破碎带的方法。简略地给出了数学方法的指导过程和思路,并以东川工程实测资料进行判别计算。结果表明,用该法辅助识别破碎带效果好,在理论和实用上很有价值。     

地震与测井数据综合预测裂缝发育带

章针对前新生代海相残留盆地碳酸盐岩裂缝识别这一难题提出一种利用地震与测井数据综合预测裂缝发育带的方法.用测井资料标识出裂缝发育层段,同时利用地震资料具有空间上数据点多、分布均匀的特点通过地震多属性的人工神经网络方法将测井与地震数据结合起来综合预测裂缝发育带,充分利用测井资料和地震资料的各自优势,达到在剖面上和区域上预测裂缝发育带的目的.本方法经过实际资料的处理与预测证实比常规方法预测精度高.     

基于AlexNet卷积神经网络模型的宁夏天然地震和非天然地震识别研究

宁夏回族自治区及周边天然地震和非天然地震频发,精确快速识别天然和非天然地震有利于震后应急响应、科学研究、赈灾救援等工作。基于AlexNet卷积神经网络模型,选取宁夏境内及周边130个地震事件（天然地震80个、非天然地震50个）,对其进行了单个台站波形记录地震事件的训练和多个台站波形记录地震事件的测试,并将模型结果与宁夏测震台网人工编目结果进行比对,结果表明单个台站波形记录地震事件的训练结果中,AlexNet卷积神经网络模型对宁夏天然地震和非天然地震的正确识别率为99%;多个台站波形记录地震事件的测试结果中,此模型对宁夏天然地震和非天然地震的正确识别率为97.01%。AlexNet卷积神经网络模型作为人工智能领域的成熟技术之一,可以很好的运用于宁夏天然地震和非天然地震的识别工作之中。     

人工神经网络在潜在地震危险区估计中的应用

利用环境剪应力较高的地区较容易发生中强地震这一原理,提出了将人工神经网络应用于估计潜在地震危险区的方法。由于该方法是通过人工神经网络技术提前1~2年预测某一地区未来环境应力值的变化来估计潜在地震危险区,因而可大大提高估计的准确性。该方法今后在多震地区的预报工作中值得一试。     

基于地震属性的煤层厚度预测模型及其应用

地震属性技术在岩性和构造解释等方面得到了越来越广泛的应用,特别是在煤、油气资源勘探中具有重要的作用.基于淮南矿区谢桥1区13 1煤层地震勘探资料,提取了28种地震属性数据;通过地震属性的分析,优选出平均峰值振幅、振幅的峰态、最大绝对振幅、瞬时频率斜率等4种地震属性作为煤层厚度预测模型基本参数,结合已知钻孔资料,利用多元多项式回归以及BP人工神经网络方法,求出了各属性与煤厚之间的多元多项式回归模型及人工神经网络模型,并对模型进行了误差分析和应用结果对比分析,反映出人工神经网络模型在煤厚预测中具有好的应用效果.     

Adaptive Training of Neural Networks for Automatic Seismic Phase Identification

—?A neural network module has been implemented in the Prototype International Data Centre (PIDC) for automated identification of the initial phase type of seismic detections. Initial training of the neural networks for stations of the International Monitoring System (IMS) requires considerable effort. While there are many seismic phases in the analyst-reviewed database that can be assumed as the ground-truth resource of the initial phase type of Teleseism (T), Regional P (P), and Regional S (S), no ground-truth database of noise (N) is available. To reduce analyst effort required in building a ground-truth database, an “Adaptive Training Approach” is proposed in this paper. This approach automatically selects training patterns to take advantage of the learning ability of neural networks and information on the accumulated observation database. Using this approach, neural networks were trained on the data provided by station STKA, Australia. The performance of automated phase identification has been improved significantly by the retrained neural networks. This approach is also validated by comparison with the performance using the ground-truth noise database.     

Rock Properties and Seismic Attenuation: Neural Network Analysis

—Using laboratory data, the influence of rock parameters on seismic attenuation has been analyzed using artificial neural networks and regression models. The predictive capabilities of the neural networks and multiple linear regresssion were compared. The neural network outperforms the multiple linear regression in predicting attenuation values, given a set of input of rock parameters. The neural network can make complex decision mappings and this capability is exploited to examine the influence of various rock parameters on the overall seismic attenuation. The results indicate that the most influential rock parameter on the overall attenuation is the clay content, closely followed by porosity. Though grain size contribution is of lower importance than clay content and porosity, its value of 16 percent is sufficiently significant to be considered in the modeling and interpretation of attenuation data.     

基于机器学习算法的银川台阵资料自动化震相分析和定位

近年来快速发展的机器学习算法显著提高了震相拾取的精度和效率。采用卷积神经网络和递归神经网络的震相识别方法对银川台阵2019年6～7月的连续波形数据进行事件检测和P、 S震相拾取,并通过快速震相关联和事件定位得到了银川地区较全的地震目录。结果表明,当震相数小于10时,虽然可以检测出较多事件,但分布呈弥散状,与区域地震活动特征不符。进一步对震相数≥10的事件进行了人工复核。总体而言,随着震相数量的增加,事件的误检率逐步降低。震相数16是该地区自动检测和定位结果准确性的拐点。当震相数≥20时,全部召回了地震目录中的13个地震事件,二者平均定位差异4.27 km。经过人工复核,检测到的真实地震事件为区域内地震目录中事件数量的9倍。本文使用的基于机器学习和快速震相关联和定位方法的流程可在确保准确率的基础上降低人工检测的难度,提高地震检测的效率。     

利用多分辨率小波网络进行地震资料反演

在讨论小波网络理论方法的基础上,研究了利用地震纪录小波多尺度分解属性资料进行虚井声波时差反演的技术方法。分析了利用地震信号进行小波分解和网络学习、训练的理论方法。研究中发现:对于相邻的地震道,较小一段的相似性比整个地震道的相似性要好。据此,利用小波时-频分析技术方法,可以把相邻道的信息外推到其它地震道上。通过以上综合研究及对实际资料进行反演计算、分析,认为小波网络与人工神经网络相比其网络结构要容易选定,并且收敛速度快。同时,利用地震资料分段时-频分析的相似性较好和小波网络学习、训练及记忆能力较强的特点,可以较好地把井旁道的高、低频信息转换到相邻道上。这样在提高分辨率的同时,又增加了反演结果的真实可靠性     

Deep Artificial Neural Networks as a Tool for the Analysis of Seismic Data

The number of seismological studies based on artificial neural networks has been increasing. However, neural networks with one hidden layer have almost reached the limit of their capabilities. In the last few years, there has been a new boom in neuroinformatics associated with the development of third-generation networks, deep neural networks. These networks operate with data at a higher level. Unlabeled data can be used to pretrain the network, i.e., there is no need for an expert to determine in advance the phenomenon to which these data correspond. Final training requires a small amount of labeled data. Deep networks have a higher level of abstraction and produce fewer errors. The same network can be used to solve several tasks at the same time, or it is easy to retrain it from one task to another. The paper discusses the possibility of applying deep networks in seismology. We have described what deep networks are, their advantages, how they are trained, how to adapt them to the features of seismic data, and what prospects are opening up in connection with their use.     

基于改进EWT和LogitBoost集成分类器的地震事件分类识别算法

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。     

神经网络模型在地震预报中的某些应用

本文介绍了人工神经网络模型以地震活动性指标为基础应用于地震预报的一些最新研究结果，选用多层前向神经网络模型及ＢＰ算法，其输入取不同的地震活动性指标的集合，输出为某一指定地区在未来时段内可能发生的最大地震的震级，以华北及首都圈地区为例，用多组不同类型的地震活动性指标进行学习与检验，结果表明，利用人工神经网络模型对未来时段震级预报的符合率较高，内检预报符合率可达１００％，外推预报符合率达到６０％以上。     

神经网络方法在爆炸地震震中定位方面的应用

地震定位过程中,由于地球介质的不均一性以及台站局部地质条件的复杂性,使震中距和地震波走时呈非线性关系。利用通常地震定位方法所确定的爆炸地震震中位置和实际震中存在２０～３０ｋｍ偏差。人工神经网络具有高度非线性映射功能,可应用于地震震中定位。应用ＢＰ（反向传播）神经网络确定远场爆破地震震中的实例表明,所确定的震中位置和实际震中位置偏差在８ｋｍ以内,外延预测确定的震中位置和实际震中位置偏差小于１８ｋｍ     

CRPN: A cascaded classification and regression DNN framework for seismic phase picking*

Current deep neural networks (DNN) used for seismic phase picking are becoming more complex, which consumes much computing time without significant accuracy improvement. In this study, we introduce a cascaded classification and regression framework for seismic phase picking, named as the classification and regression phase net (CRPN), which contains two convolutional neural network (CNN) models with different complexity to meet the requirements of accuracy and efficiency. The first stage of the CRPN are shallow CNNs used for rapid detection of seismic phase and picking P and S arrival times for earthquakes with magnitude larger than 2.0, respectively. The second stage of CRPN is used for high precision classification and regression. The regression is designed to reduce the time difference between the probability maximum and the real arrival time. After being trained using 500,000 P and S phases, the CRPN can process 400 hours’ seismic data per second, whose sampling rate is 1 Hz and 25 Hz for the two stages, respectively, on a Nvidia K2200 GPU, and pick 93% P and 89% S phases with the error being reduced by 0.1s after regression correction.     

Phase identification and attribute analysis of broadband seismograms at far-regional distances

A trained analyst can frequently provide a rapid assessment of a seismic record and provide identification for many seismic phases. For digital data a challenge is to find methods (or combinations of methods) which can provide equivalent levels of phase identification and attribute analysis. Until now, there have been few discussions on phase attribute analysis for broadband records, even though the character of the major phases has been recognised several decades ago. We introduce a combination of four simple methods into the analysis of broadband seismograms so as to provide a means of improving phase recognition and the full use of broadband information for far-regional distances where the seismograms are particularly complex (because of the influence of the upper mantle discontinuities). For arrival detection we can employ the energy ratios of the short term behaviour to the long-term trend, using the vertical component and horizontal components of unrotated seismic records. We also use auto-regressive analysis to endeavour to separate broadband records into three parts: the seismic signal, microseismic noise and white noise. The higher order auto- and cross-correlation coefficient (representing the similarity of waveform) can be used to identify the presence of seismic phases, by avoiding the influence of the relatively low order correlation of microseismic noise. For each broadband 3-component record a set of complex traces are constructed and then a variety of definitions of instantaneous phase and frequency can be exploited to separate the behaviour of signal and noise. The complex traces can also be used for polarisation analysis. The changes in the character of the eigenvectors are particularly helpful for recognising the phases of broadband records in the far-regional range. The individual methods are quite powerful but when used in combination can provide a very effective means of phase characterisation.