共查询到18条相似文献，搜索用时 942 毫秒
1.
在地震勘探采集到的地震数据中不可避免的存在随机噪声,而高信噪比的地震数据是地震资料反演和解释的基础.因此随机噪声压制一直是地震资料处理中的重要工作.近些年来,随着深度学习技术的发展,基于卷积神经网络的地震数据去噪方法已经取得了丰硕的成果.常规的监督学习策略需要获取无噪数据作为标签,然而从实际地震数据中获取无噪数据只能通过传统去噪方法进行预处理,以此方法构建标签数据的监督学习去噪网络必然受构建数据集的去噪方法影响.针对此问题,本文提出了一种基于Noise-to-Noise自监督学习的地震数据去噪方法,该方法通过对实际地震数据添加不同等级的噪声构建训练数据集,仅需要含噪地震数据即可训练去噪网络.合成数据测试和实际数据测试表明,本文方法可以有效去除地震数据中的随机噪声,性能优于受数据集构建方法所限的监督学习去噪方法和传统去噪方法. 相似文献
2.
3.
分布式光纤传感器(distributed fiber-optical acoustic sensor,DAS)是一种快速发展的具有巨大应用前景的地震勘探检波器技术.实际DAS地震资料往往会受到大量强能量随机噪声的干扰,通常表现为低信噪比(signal-to-noise ratio,SNR).这一现象给接下来的成像、反演以及解释带来了巨大的困难,因此如何压制DAS地震资料中的随机噪声并提高其SNR成为一个有待解决的技术问题.卷积神经网络(convolutional neural network,CNN)已经被证明是一种有效的噪声压制工具.通常情况下,CNN需要一个理论纯净地震数据集来优化网络,这极大地限制了CNN在DAS地震资料处理中的应用.在本文中,我们采用正演模拟的方法来构建理论纯净DAS地震数据集,通过正演模型的参数多样化增强数据集的真实性,从而获得适合DAS地震资料随机噪声压制的CNN去噪模型.此外,在网络结构方面,我们利用泄漏线性整流单元作为CNN的激活函数增强训练后模型对微弱有效信号的恢复能力;在训练过程中,通过能量比矩阵调节噪声片和有效信号片之间的SNR,增强CNN去噪模型对于不同SNR的DAS地震数据的适应性.模拟和实际实验均表明本文提出的这种正演模型驱动的卷积神经网络(forward-model-actuation convolutional neural network,FMA-CNN)能够有效地压制DAS随机噪声同时完整地恢复有效信号. 相似文献
4.
估计地震数据的信噪比对于地震数据的处理和解释具有重要作用.以往估计地震数据信噪比的方法都需要分离数据中的有效信号和噪声,然后再估计相应的信噪比.这些估计方法的精度严重依赖信号估计方法或噪声压制方法的有效性,往往存在偏差.本文提出一种估计地震数据局部信噪比的深度卷积神经网络模型,通过迭代训练优化参数,构建从含噪地震数据到其信噪比的特征映射.然后使用该神经网络完成信噪比的推理预测,不需要分离地震数据中的有效信号和噪声.模拟数据和实际资料的处理结果都表明,本文的方法可以准确而高效地估计局部地震数据的信噪比,为地震数据质量的定量评价提供依据. 相似文献
5.
深度学习算法已广泛应用于地震数据处理分析领域,并在地震数据去噪等方面取得了较好的应用效果.目前业界关注重点在于各种不同深度学习算法和相关的网络结构形式,以及不同标签数据对算法效果的影响,较少关注数据集本身的差异对深度学习算法的应用效果影响.本文以卷积神经网络(Convolutional Neural Network, CNN)算法中批量规范化层(Batch Normalization)对地震数据去噪的影响分析为例,通过理论公式和应用效果的对比分析,提出了基于地震数据特征分析下的批量规范化层的使用建议.批量规范化层的使用依赖于数据集的统计分布特征,只有当训练集的归一化能量分布集中在能量较强的区域,批量规范化层的使用才会提升网络的效果.但通常情况下,在地震数据去噪的应用中,不建议使用批量规范化层.这些特征为深度学习算法在地震数据去噪应用中的网络结构设计提供了有价值的参考. 相似文献
6.
地震数据中存在的多次波影响偏移成像,误导地震资料的解释,因此通常视为相干噪声而被去除.为了对多次波进行智能化衰减,本文提出了一种基于数据增广训练的使用深度神经网络的多次波压制方法.设计的深度神经网络包括卷积编码和卷积解码过程,其中卷积编码过程学习全波场数据中的一次波特征,卷积解码过程利用这些特征来重构一次波并压制多次波和随机噪声.在训练阶段,旋转训练集并在输入数据中加入随机噪声构成增广训练数据集来提升神经网络的抗噪稳定性和泛化性,通过迁移学习让深度神经网络具备跨工区压制多次波的能力.简单模型与Sigsbee2B模型三套模拟数据的实例验证了本文方法在一次波重构和多次波压制中的有效性、稳定性和良好泛化性;一套崎岖海底模型地震物理模拟数据的应用实例表明本文方法具有应用于复杂条件下压制地震多次波的能力. 相似文献
7.
地震道编辑是数据预处理中一个繁琐的过程。这可能需要大量的人力和时间成本,特别是对于大型三维数据集。目前的地震道编辑方法通常耗时较长,如果粗略地去除噪声道,可能会遗漏一些潜在的重要信息。在本章的研究中,我们提出了一种基于机器学习的自动编辑地震道的方法。此外,我们还将霍夫变换技术与卷积神经网络（CNN）相结合,以提高方法的可行性。霍夫变换是一种帮助识别图像中异常直线的特征提取方法,我们将其用来预先检测可能存在的噪声道和坏道的位置。然后,利用设计好的带通滤波器和训练好的CNN模型来识别霍夫变换标记的目标区域内真正的噪声道和坏道。在识别之后,应用自动的处理方式来确定经过处理的地震道是否有用或是仍然应该丢弃。整个方案包括四个主要步骤:数据预处理、霍夫变换检测、CNN网络训练和CNN网络预测。在实际数据应用中,准确率达到了98%,表明所提出的自动道编辑方案在实际应用中是有前景的。 相似文献
8.
本文以提高地震数据的成像质量为目标,提出一种智能的卷积神经网络降噪框架,从带有噪声的地震数据中自适应地学习地震信号。为了加速网络训练和避免训练时出现梯度消失现象,我们在网络中加入残差学习和批标准化的方法,并采用了ReLU激活函数和Adam优化算法优化网络。此外,Marmousi和F3数据集被用来对网络进行训练和测试,经过充分训练的网络不仅能在学习中保留地震数据特征,而且能去除随机噪声。首先充分地训练网络,从中提取出随机噪声,并保留学习到的地震数据特征,之后通过重建地震数据估算测试集中的波形特征。合成记录和实际数据的处理结果显示了深度卷积神经网络在随机噪声压制任务中的潜力,并通过实验验证表明了深度卷积神经网络框架有很好的去噪效果。 相似文献
9.
基于稀疏反演的地震插值方法是一种重要的插值方法,然而大多数这类方法只针对无噪声数据或者高信噪比数据插值.实际上,地震数据含有各种噪声,使得插值问题变得更加困难.凸集投影方法是一种高效的插值算法,但是对于含噪声数据的插值效果不理想,针对含噪声数据提出的加权凸集投影方法能够实现同时插值和去噪,但是除了最小阈值需要认真选取外,增加一个权重因子来实现去噪功能.本文由迭代阈值算法推导出加权凸集投影方法,证明其是解无约束优化问题的一种方法,加权因子可以看作拟合误差项的系数.本文还提出了一种改进的凸集投影方法,与原始凸集投影方法相比该方法不需要增加任何计算量,只要通过阈值的选择来进行插值和去噪.数值模拟证明了该算法的计算效率,并且对含噪声数据能够实现较好的插值效果;先插值后去噪的结果证明了同时去噪和插值算法的可靠性和稳定性. 相似文献
10.
11.
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
12.
Within the field of seismic data acquisition with active sources, the technique of acquiring simultaneous data, also known as blended data, offers operational advantages. The preferred processing of blended data starts with a step of deblending, that is separation of the data acquired by the different sources, to produce data that mimic data from a conventional seismic acquisition and can be effectively processed by standard methods. Recently, deep learning methods based on the deep neural network have been applied to the deblending task with promising results, in particular using an iterative approach. We propose an enhancement to deblending with an iterative deep neural network, whereby we modify the training stage of the deep neural network in order to achieve better performance through the iterations. We refer to the method that only uses the blended data as the input data as the general training method. Our new multi-data training method allows the deep neural network to be trained by the data set with the input patches composed of blended data, noisy data with low amplitude crosstalk noise, and unblended data, which can improve the ability of the deep neural network to remove crosstalk noise and protect weak signal. Based on such an extended training data set, the multi-data training method embedded in the iterative separation framework can result in different outputs at different iterations and converge to the best result in a shorter iteration number. Transfer learning can further improve the generalization and separation efficacy of our proposed method to deblend the simultaneous-source data. Our proposed method is tested on two synthetic data and two field data to prove the effectiveness and superiority in the deblending of the simultaneous-source data compared with the general training method, generic noise attenuation network and low-rank matrix factorization methods. 相似文献
13.
We propose to adopt a deep learning based framework using generative adversarial networks for ground-roll attenuation in land seismic data. Accounting for the non-stationary properties of seismic data and the associated ground-roll noise, we create training labels using local time–frequency transform and regularized non-stationary regression. The basic idea is to train the network using a few shot gathers such that the network can learn the weights associated with noise attenuation for the training shot gathers. We then apply the learned weights to test ground-roll attenuation on shot gathers, that are not a part of training input to obtain the desired signal. This approach gives results similar to local time–frequency transform and regularized non-stationary regression but at a significantly reduced computational cost. The proposed approach automates the ground-roll attenuation process without requiring any manual input in picking the parameters for each shot gather other than in the training data. Tests on field-data examples verify the effectiveness of the proposed approach. 相似文献
14.
利用北京国家观象台的测震记录,探索了样本构建、训练过程、模型结构等因素对远震震相P-S和近震震相Pg-Sg拾取模型性能的影响。结果表明：适中的卷积层深度、正则化和数据清洗能够有效地改善模型性能,而残差块的影响却相对有限。与此同时,基于类模型可视化和平滑GradCAM++的模型解释显示：卷积神经网络复现了震相的关键特征,其决策敏感区域也与震相识别的经验准则一致。最后,连续波形的扫描结果展示了卷积神经网络在远-近地震震相识别的应用前景与提升空间。此外,本文针对模型搭建与训练中存在的问题提出了样本选择、模型架构、标签标注和集成学习等改进方案,以供后续研究参考。 相似文献
15.
针对随机地震反演中存在的两个主要问题,随机实现含有噪声和难以从大量随机实现中挖掘有效信息,提出了一种基于神经网络的随机地震反演方法.通过对多组随机实现及其正演地震数据的计算,构建了基于序贯高斯模拟的训练集.这也为应用神经网络求解地球物理反问题,提供了一种有效建立训练集的方法.较之传统的神经网络反演,这种训练集不仅保证了学习样本具有多样性,同时还引入了空间相关性.数值模拟结果表明,该方法只需要通过单层前馈神经网络,就可以比较有效的解决一个500个阻抗参数的反演问题. 相似文献
16.
Gustavo Côrte Jesper Dramsch Hamed Amini Colin MacBeth 《Geophysical Prospecting》2020,68(7):2164-2185
In this work, we tackle the challenge of quantitative estimation of reservoir dynamic property variations during a period of production, directly from four-dimensional seismic data in the amplitude domain. We employ a deep neural network to invert four-dimensional seismic amplitude maps to the simultaneous changes in pressure, water and gas saturations. The method is applied to a real field data case, where, as is common in such applications, the data measured at the wells are insufficient for properly training deep neural networks, thus, the network is trained on synthetic data. Training on synthetic data offers much freedom in designing a training dataset, therefore, it is important to understand the impact of the data distribution on the inversion results. To define the best way to construct a synthetic training dataset, we perform a study on four different approaches to populating the training set making remarks on data sizes, network generality and the impact of physics-based constraints. Using the results of a reservoir simulation model to populate our training datasets, we demonstrate the benefits of restricting training samples to fluid flow consistent combinations in the dynamic reservoir property domain. With this the network learns the physical correlations present in the training set, incorporating this information into the inference process, which allows it to make inferences on properties to which the seismic data are most uncertain. Additionally, we demonstrate the importance of applying regularization techniques such as adding noise to the synthetic data for training and show a possibility of estimating uncertainties in the inversion results by training multiple networks. 相似文献
17.
作为深度学习方法的一种,长短时记忆神经网络(LSTM)是一种信号处理的重要方法.本文基于实际观测地电场数据来合成训练集,对特定结构的长短时记忆神经网络进行训练,将训练所得网络对测试集数据进行测试后,将网络应用至实际观测数据.结果显示,经过训练的网络很好地学到了训练集样本的特征,对测试集数据的信噪比压制了约20 dB,并过滤了人为添加的特定频率的干扰成分,对实际观测数据处理后得到明显的日变、半日变以及半月变、月变、半年变、年变等潮汐响应,表明长短时记忆神经网络可以有效应用于地电场数据处理研究. 相似文献
18.
Random noise attenuation, preserving the events and weak features by improving signal‐to‐noise ratio and resolution of seismic data are the most important issues in geophysics. To achieve this objective, we proposed a novel seismic random noise attenuation method by building a compound algorithm. The proposed method combines sparsity prior regularization based on shearlet transform and anisotropic variational regularization. The anisotropic variational regularization which is based on the linear combination of weighted anisotropic total variation and anisotropic second‐order total variation attenuates noises while preserving the events of seismic data and it effectively avoids the fine‐scale artefacts due to shearlets from the restored seismic data. The proposed method is formulated as a convex optimization problem and the split Bregman iteration is applied to solve the optimization problem. To verify the effectiveness of the proposed method, we test it on several synthetic seismic datasets and real datasets. Compared with three methods (the linear combination of weighted anisotropic total variation and anisotropic second‐order total variation, shearlets and shearlet‐based weighted anisotropic total variation), the numerical experiments indicate that the proposed method attenuates random noises while alleviating artefact and preserving events and features of seismic data. The obtained result also confirms that the proposed method improves the signal‐to‐noise ratio. 相似文献