A comparison of seismic saltbody interpretation via neural networks at sample and pattern levels

Saltbodies are important subsurface structures that have significant implications for hydrocarbon accumulation and sealing in petroleum reservoirs, and accurate saltbody imaging and delineation is now greatly facilitated with the availability of three-dimensional seismic surveying. However, with the growing demand for larger survey coverage and higher imaging resolution, the size of seismic data is increasing dramatically. Correspondingly, manual saltbody interpretation fails to offer an efficient solution, particularly in exploration areas of complicated salt intrusion history. Recently, artificial intelligence is attracting great attention from geoscientists who desire to utilize the popular machine learning technologies for evolving the interpretational tools capable of mimicking an experienced interpreter's intelligence. This study first implements two popular machine learning tools, the multi-layer perceptron and the convolutional neural network, for delineating seismic saltbodies at sample and pattern levels, respectively, then compares their performance through applications to the synthetic SEAM seismic volume, and moreover tentatively investigates what contributes to the better convolutional neural network delineation. Specifically, the multi-layer perceptron scheme is capable of efficiently utilizing an interpreter's knowledge by selecting, pre-conditioning and integrating a set of seismic attributes that best highlight the target saltbodies, whereas the convolutional neural network scheme makes it possible for saltbody delineation directly from seismic amplitude and thus significantly reduces the dependency on attribute selection from interpreters. It is concluded that the better performance from the convolutional neural network scheme results from two factors. First, the convolutional neural network builds the mapping relationship between the seismic signals and the saltbodies using the original seismic amplitude instead of manually selected seismic attributes, so that the negative impact of using less representative attributes is virtually eliminated. Second and more importantly, the convolutional neural network defines, learns and identifies the saltbodies by utilizing local seismic reflection patterns, so that the seismic noises and processing artefacts of distinct patterns are effectively identified and excluded.     

Marine transient electromagnetic sounding of deep buried hydrocarbon reservoirs: principles,methodologies and limitations

The possibility of a time‐domain electromagnetic sounding method using excitation and measurement of vertical electric fields to search for and identify deeply buried reservoirs of hydrocarbons offshore is investigated. The method operates on source–receiver offsets, which are several times less than the depth of the reservoir. Geoelectric information is obtained from the transient responses recorded in the pauses between the pulses of electric current in the absence of the source field. The basics of the method, as well as its sensitivity, resolution, and the highest accessible depth of soundings for various geological conditions in a wide range of sea depths, are analyzed. For the analysis, 1D and 3D geoelectric models of hydrocarbon reservoirs are used. It is shown that under existing technologies of excitation and measurement of vertical electric fields, the highest accessible depth of soundings can be up to 4 km. Technology for the inversion and interpretation of transient responses is demonstrated on experimental data.     

Connectivity constrained segmentation of geologic features

Segmentation of geologic features plays a significant role in seismic interpretation. Based on the segmentation results, interpreters can readily recognize the shape and distribution of geologic features in three-dimensional space and conduct further quantitative analysis. Usually, there are mainly two steps for the segmentation of geologic features: the first step is to extract seismic attributes that can highlight the occurrence of geologic features, and the second step is to apply the segmentation algorithm on the seismic attribute volumes. However, the occurrence of geologic features is not always corresponding to the anomaly value on the seismic attribute volumes and vice versa because of several factors, such as noise in the seismic data, the limited resolution of seismic images and the limited effectiveness of the seismic attribute. Therefore, the segmentation results, which are generated solely based on seismic attributes, are not sufficient to give an accurate depiction of geologic features. Aiming at this problem, we introduce the connectivity constraint into the process of segmentation based the assumption that for one single geologic feature all of its components should be connected to each other. Benefiting from this global constraint, the segmentation results can precisely exclude the interference by false negatives on seismic attribute volumes. However, directly introducing the connectivity constraint into segmentation would face the risk that the segmentation results would deteriorate significantly because of false positives with relatively large area when the connectivity constraints are enforced. Therefore, based on the seismic attribute that highlights the boundary of geologic feature, we further propose a post-processing technique, called pruning, to refine the segmentation results. By taking the segmentation of the channel as an example, we demonstrate that the proposed method is able to preserve the connectivity in the process of segmentation and generate better segmentation results on the field data.     

Semi-automatic fault/fracture interpretation based on seismic geometry analysis

Fault and fracture interpretation is a fundamental but essential tool for subsurface structure mapping and modelling from 3D seismic data. The existing methods for semi-automatic/automatic fault picking are primarily based on seismic discontinuity analysis that evaluates the lateral changes in seismic waveform and/or amplitude, which is limited by its low resolution on subtle faults and fractures without apparent vertical displacements in seismic images. This study presents an innovative workflow for computer-aided fault/fracture interpretation based on seismic geometry analysis. First, the seismic curvature and flexure attributes are estimated for highlighting both the major faults and the subtle fractures in a seismic volume. Then, fault probability is estimated from the curvature and flexure volumes for differentiation between the potential faults and non-faulting features in the geometric attributes. Finally, the seeded fault picking is implemented for interpreting the target faults and fractures guided by the knowledge of interpreters to avoid misinterpretation and artefacts in the presence of faulting complexities as well as coherent seismic noises. Applications to two 3D seismic volumes from the Netherlands North Sea and the offshore New Zealand demonstrate the added values of the proposed method in imaging and picking the subtle faults and fractures that are often overlooked in the conventional seismic discontinuity analysis and the following fault-interpretation procedures.     

探地雷达应用概述

以ASTM标准规范为基础对探地雷达（Ground Penetrating Radar 以下简称GPR）的地下探测方法的应用做了比较系统的概述,主要内容包括：部分专业术语的解释;测试过程中雷达探测深度及其中心频率、垂直分辨率、水平分辨率等的关系,测试过程中常见的天线移动方式,以及雷达波速的预测几种方法,数据显示方式;雷达数据解释和数据处理的一般过程及方法.目前我国尚没有关于GPR的国家规范或行业标准,文章对GPR的使用及规范的编制具有一定的参考意义.     

非纵观测系统地震测深资料分析处理的人机对话过程

本文在三维壳幔结构中两点射线追踪分步搜索算法的基础上,在物探中心地震方法研究室ＳＵＮ工作站上研究开发出可应用于非纵观测系统深地震测深资料人机对话三维分析处理的方法及软件。对研究区域的三角形剖分减少了人机对话过程中的工作量及人为干预,并用该方法以反演得到的华北块状模型作为初始模型,对该模型的剩余ＰｍＰ波残差进行了人机对话拟合。     

约束型贝叶斯网络在遥感图像解译中的应用方法研究

采用一种带有约束条件的贝叶斯网络来构造分类器,即特征节点被约束为类节点的子节点,子节点间允许有不同的连接关系,并将约束型贝叶斯网络的几种典型模型--NB、TAN、BAN用于遥感图像的解译中.通过评价结构的似然函数得到网络结构,综合特征节点和类别节点的拓扑和概率统计信息学习得到分类器.将这些模型用于多光谱和高光谱影像的分类,并就其性能进行探讨.     

庐-枞金属矿集区深地震反射剖面解释结果——揭露地壳精细结构,追踪成矿深部过程

深地震反射剖面揭示了庐枞矿集区全地壳的精细结构,在研究火山岩盆地的深部构造、探讨成矿深部过程等方面取得了新认识。从长江至大别山下,Moho由30km左右加深至33km左右,罗河矿下方Moho错断大约3km。庐枞火山岩盆地是一个沿着罗河断裂向东发育的"耳状"非对称盆地,并不存在另外一半隐伏在红层之下的盆地。罗河铁矿对应Moho错断处,处在构造的转换带上。罗河断裂之下存在近于透明的弱反射区域,可能是地幔流体和岩浆上涌、喷发的通道。郯庐断裂、罗河-缺口断裂、长江断裂是庐枞地区的三个重要断裂。郯庐断裂带为不对称花束状构造,近于直立,切穿地壳。小岭矿与龙桥矿可能产出在一个隆起的火成岩体的两翼。     

集合数值预报发展与研究进展

较系统地概述了集合预报系统发展过程与集合预报中的主要研究问题，总结了集合预报概念、系统组成、初始扰动理论技术和产品解释与应用原理的研究成果，简单分析了近年来集合预报中的一些研究热点，介绍了先进国家集合预报的发展计划。     

基于“3S”技术土地利用基础图件与数据更新的应用

以潍坊市土地利用基础图件与数据更新项目为例,采用内外业相结合的作业方式,讨论了基于“3S”技术土地利用基础图件与数据库更新方法的应用、关键问题和解决方案以及成果应用。