共查询到20条相似文献，搜索用时 140 毫秒
1.
J. Hou 《Geophysical Prospecting》2002,50(5):453-462
The evaluation of coalbed methane reservoirs using log data is an important approach in the exploration and development of coalbed methane reservoirs. Most commonly, regression techniques, fuzzy recognition and neural networks have been used to evaluate coalbed methane reservoirs. It is known that a coalbed is an unusual reservoir. There are many difficulties in using regression methods and empirical qualitative recognition to evaluate a coalbed, but fuzzy recognition, such as the fuzzy comprehensive decision method, and neural networks, such as the back-propagation (BP) network, are widely used. However, there are no effective methods for computing weights for the fuzzy comprehensive decision method, and the BP algorithm is a local optimization algorithm, easily trapped in local minima, which significantly affect the results. In this paper, the recognition method for coal formations is developed; the improved fuzzy comprehensive decision method, which uses an optimization approach for computing weighted coefficients, is developed for the qualitative recognition of coalbed methane reservoirs. The homologous neural network, using a homologous learning algorithm, which is a global search optimization, is presented for the quantitative analysis of parameters for coalbed methane reservoirs. The applied procedures for these methods and some problems related to their application are also discussed. Verification of the above methods is made using log data from the coalbed methane testing area in North China. The effectiveness of the methods is demonstrated by the analysis of results for real log data. 相似文献
2.
A pattern recognition approach to liquefacation evaluation is propoesed. The state of any soil layer at a level ground site subject to seismic loads is represented by a pattern in a seven-dimensional feature space and can be classified into one of three classes: liquefiable cohesive soil, and non-liquefiable cohesionless soil. The liquefaction potential of the soil layer can be assessed according to the probabilities of the pattern belonging to the three classes. Training patterns derived from field data (piezocone (CPTU) data and maximum ground acceleration) from sites which liquefied or did not liquefy during earthquakes in New Zealand are randomly chosen to design a pattern recognition system to provide an optimal estimation of the liquefaction potential of any soil stratum of interest. Two recognition systems have been set up to estimate the state-conditional probability density function. One is based on a Parzen window approach in which no knowledge of the probabilistic structure of the training patterns is assumed; the other is based on a parameter estimation approach assuming a multivariate normal distribution. The error rate of recognition by the Parzen window approach is 6·9% when taking the window size as 1·5, and the error rate by the parameter estimation approach, which can be easily, is 7·7%. implemented without reference to our training patterns 相似文献
3.
Identification of fuel samples from the Prestige wreckage by pattern recognition methods 总被引：1，自引：0，他引：1
Fernández-Varela R Andrade JM Muniategui S Prada D Ramírez-Villalobos F 《Marine pollution bulletin》2008,56(2):335-347
A set of 34 worldwide crude oils, 12 distilled products (kerosene, gas oils, and fuel oils) and 45 oil samples taken from several Galician beaches (NW Spain) after the wreckage of the Prestige tanker off the Galician coast was studied. Gas chromatography with flame ionization detection was combined with chemometric multivariate pattern recognition methods (principal components analysis, cluster analysis and Kohonen neural networks) to differentiate and characterize the Prestige fuel oil. All multivariate studies differentiated between several groups of crude oils, fuel oils, distilled products, and samples belonging to the Prestige's wreck and samples from other illegal discharges. In addition, a reduced set of 13 n-alkanes out of 36, were statistically selected by Procrustes Rotation to cope with the main patterns in the datasets. These variables retained the most important characteristics of the data set and lead to a fast and cheap analytical screening methodology. 相似文献
4.
This paper presents some results from an investigation into the utility of pattern recognition methods in seismic interpretation. The seismic instantaneous attributes of amplitude, phase and frequency provide a way of quantifying the character of a simple reflection. Measures of character can be developed from cross-plots and cluster analysis of these attributes. It is demonstrated that such seismic character can produce better-defined maps than a single attribute. These procedures can be extended to attributes derived from seismic trace segments, such as trace energy and centre frequency, and to multitrace attributes, but more effort is then needed to analyse the attributes and search out useful ones. An introduction is given to projection pursuit which has proved a useful exploratory tool for the anlysis of attribute relationships. It is important to stress that pattern recognition techniques simply help bring relationships and patterns in the data to the attention of the interpreter and the most persistent problem in applying these techniques is the evaluation of potentially interesting patterns. The decision on what use can be made of them is highly interpretive and their calibration is difficult. Well control is vital but it normally allows only very limited supervision of a seismic classifier. An example is presented to illustrate these problems. 相似文献
5.
GC/MS Nontarget Analysis to Examine an Organic Groundwater Contamination. Part II: Graphical and Multivariate Methods for Searching Key Substances In the nontarget analysis, a maximum of organic substances was extracted by a sequence which separates high polar, medium polar, and nonpolar compounds. This leads to the detection of 477 different organic substances in the example of the groundwater contamination investigated. To reduce the high expense for an exact identification of 477 compounds as a first step the individual compound is defined as a data set of retention time and the mass spectrum belonging to this retention time. The table of data contains now 477 individual compounds in groundwater samples collected at 10 different locations. The application of mathematical filters helps to reduce the size of the data set. Graphical methods enable large amounts of data to be visualized in a clear manner and enable to detect patterns in a data set. These patterns are the key to select typical compounds as indicator substances for the contamination source as well as the geogenic background. Similarities between the groundwater samples should not be changed by selection of the indicator compounds. Therefore, cluster analysis was applied as a controlling instrument for the final selection of the indicator compounds. The combination of graphical and multivariate data analysis is a useful tool to deduce indicator compounds for monitoring and control of complex environmental pollution states. 相似文献
6.
Mathematical aspects of predicting water quality class based on data of hydrobiological analysis with the use of pattern recognition are considered. A series of calculations of indicator valences of zoobenthos was performed using saprobic analysis by the M. Zelinka–P. Marvan method based on the occurrence of aquatic animals in different types of water bodies. Models using nonlinear optimization methods for the recognition of water quality classes by zoobenthos are proposed. Detailed comparative analysis is made for the results obtained from the observational data on small rivers in the Samara region. 相似文献
7.
ＴｈｅｓｔｕｄｙａｎｄａｐｐｌｉｃａｔｉｏｎｏｆＰＴＲａｌｇｏｒｉｔｈｍｏｎｒｅｃｏｇｎｉｚｉｎｇｖａｒｉｏｕｓｓｔｒｕｃｔｕｒｅｓａｍｐｌｅｓＢｉ－ＱｕａｎＷＡＮＧ（王碧泉）；Ｈａｎ－ＭｉｎｇＨＵＡＮＧ（黄汉明）ａｎｄＨｏｎｇ－ＳｈｕｎＦＡＮ（范洪... 相似文献
8.
Environmental data are highly variable. They also include uncertainties resulting from all steps of the analytical process e. g. sampling, or sampling pre‐treatment. However, a lot of information is unfortunately often lost because only univariate statistical methods are used for data evaluation and interpretation. This neglects correlation between different pollutants and relationships among various sampling points. It is therefore necessary to apply additional methods of analysis that can accommodate such relationships. This ability is provided by the established, and by the more modern, multivariate statistical methods because they can analyze complex sets of multidimensional data. These methods are used to visualize large amounts of data and to extract latent information (e. g. differently polluted areas, dischargers, or interactions between different environmental compartments). The goal of this paper is to present the use of established statistical techniques, like cluster or factor analysis, and the progress made in basic modern techniques (e. g. cluster imaging, multiway‐partial least squares regression, projection pursuit, or information theory) and to demonstrate each with examples and illustrations. 相似文献
9.
I. B. HOYLE 《Geophysical Prospecting》1986,34(5):648-664
This paper reviews computer techniques used in the automatic zoning and correlation of well-logs. Prior to correlating, well-logs are to be segmented–or ‘zoned’–so as to delineate sections that have similar properties. Techniques discussed include statistical methods such as variance tests and Student's t-test, linguistic analysis, the use of Walsh functions and spectral analysis. Well-log correlation, which may be between traces from different wells or between traces from the same hole (as in dip logs), is used in basin studies and the determination of structural dip. A variety of methods are reviewed including conventional time and frequency correlation, sequence slotting, pattern recognition and frequency analysis. Future directions for investigation are proposed. 相似文献
10.
A. A. Soloviev A. D. Gvishiani A. I. Gorshkov M. N. Dobrovolsky O. V. Novikova 《Izvestiya Physics of the Solid Earth》2014,50(2):151-168
We present the results of verifying the areas that were detected as prone to strong earthquakes by the pattern recognition algorithms in different regions of the world with different levels of seismicity and, therefore, different threshold magnitudes demarcating the strong earthquakes. The analysis is based on the data presented in the catalog of the U.S. National Earthquake Information Center (NEIC) as of August 1, 2012. In each of the regions considered, we examined the locations of the epicenters of the strong earthquakes that occurred in the region after the publication of the corresponding result. There were 91 such earthquakes in total. The epicenters of 79 of these events (87%) fall in the recognized earthquake-prone areas, including 27 epicenters located in the areas where no strong earthquakes had ever been documented up to the time of publication of the result. Our analysis suggests that the results of the recognition of areas prone to strong earthquakes are reliable and that it is reasonable to use these results in the applications associated with the assessment of seismic risks. The comparison of the recognition for California with the analysis of seismicity of this region by the Discrete Perfect Sets (DPS) algorithm demonstrates the agreement between the results obtained by these two different methods. 相似文献
11.
本文论述了模式识别在地震油气解释中的应用,并提出了一套实现的方法.在地震资料处理中提出了信息保持的思想和处理方法.从特殊处理后的地震记录中提取多种地震特征,这些特征主要来自地震道的自回归系数、最大熵频谱和自相关函数.利用聚类分析和判别分析方法对地震特征向量进行分类,实例表明,本文提出的地震模式识别方法能有效地划分油气储集层,即使在油层较薄或是反射变化不明显的地区也能奏效. 相似文献
12.
13.
To illustrate the structure of a data set, different display methods are applied in pattern recognition. With non-linear mapping the attempt is made to transfer all distances of the objects in the multidimensional space to the plane as well as possible, the minimization of the imaging error being performed by a gradient method. Suitable starting configurations are selected appropriately from the principal component analysis or from results of the cluster analysis. The advantages and drawbacks of the non-linear mapping compared with the principal component analysis are discussed and examples of results are presented also with respect to the cluster analysis. For the implementation of the non-linear mapping a BASIC program is proposed. 相似文献
14.
15.
An information-fusion method to identify pattern of spatial heterogeneity for improving the accuracy of estimation 总被引：1，自引：0，他引：1
Lianfa Li Jinfeng Wang Zhidong Cao Ershun Zhong 《Stochastic Environmental Research and Risk Assessment (SERRA)》2008,22(6):689-704
While spatial autocorrelation is used in spatial sampling survey to improve the precision of the feature’s estimate of a certain
population at area units, spatial heterogeneity as the stratification frame in survey also often have a considerable effect
upon the precision. Under the context of increasingly enriched spatiotemporal data, this paper suggests an information-fusion
method to identify pattern of spatial heterogeneity, which can be used as an informative stratification for improving the
estimation accuracy. Data mining is major analysis components in our method: multivariate statistics, association analysis,
decision tree and rough set are used in data filter, identification of contributing factors, and examination of relationship;
classification and clustering are used to identify pattern of spatial heterogeneity using the auxiliary variables relevant
to the goal and thus to stratify the samples. These methods are illustrated and examined in the case study of the cultivable
land survey in Shandong Province in China. Different from many stratification schemes which just uses the goal variable to
stratify which is too simplified, information from multiple sources can be fused to identify pattern of spatial heterogeneity,
thus stratifying samples at geographical units as an informative polygon map, and thereby to increase the precision of estimates
in sampling survey, as demonstrated in our case research. 相似文献
16.
Environmental data are commonly constrained by a detection limit (DL) because of the restriction of experimental apparatus. In particular due to the changes of experimental units or assay methods, the observed data are often cut off by more than one DL. Measurements below the DLs are typically replaced by an arbitrary value such as zeros, half of DLs, or DLs for convenience of analysis. However, this method is widely considered unreliable and prone to bias. In contrast, maximum likelihood estimation (MLE) method for censored data has been developed for better performance and statistical justification. However, the existing MLE methods seldom address the multivariate context of censored environmental data especially for water quality. This paper proposes using a mixture model to flexibly approximate the underlying distribution of the observed data due to its good approximation capability and generation mechanism. In particular, Gaussian mixture model (GMM) is mainly focused in this study. To cope with the censored data with multiple DLs, an expectation–maximization (EM) algorithm in a multivariate setting is developed. The proposed statistical analysis approach is verified from both the simulated data and real water quality data. 相似文献
17.
应用模式识别定量划分潜在震源区 总被引：2，自引：0，他引：2
本文以陕西关中及部分邻区为例,考虑地质构造、地震活动及地球物地场等因素,采用不同的模式识别方法和多种计算方案,以定量判定潜在震源区。其结果表明,模式识别方法有利于地质、地震活动及地球物理场等多种因素综合应用,并能选择和显示判定潜有震源区的主要特征。不同模式识别方法的比较和多种试验方案的综合,则可提高潜在震源区判定的可靠性和稳定性。 相似文献
18.
Ozan Arslan 《Water Resources》2013,40(3):315-324
Incorporating spatial information data into the principal component analysis is of importance. Some proposed methods of spatial weighting schemes to be applied to the ordinary PCA are reviewed and a new version of the method is proposed in the context of spatial analysis for geospatial multivariate analysis. In view of spatial variations in the hydrochemistry of rivers such combined version of the technique might be useful for reliable estimates. 相似文献
19.
基岩油气藏裂缝性储层具有复杂的储集空间和储层非均质性,为了实现对基岩油气藏储层的精细评价,以地层微电阻率扫描成像测井和井周声波成像测井资料为核心,通过岩心资料标定,结合录井、常规测井、试油、地质等实际资料,系统建立了基岩油气藏变质岩储层的成像测井解释模式.根据成像测井模式的识别实现了对基岩油气藏特征的认识、准确的裂缝分析和现今地应力场分析.分析结果表明,研究区基底变质岩地层中基本以基岩内幕油气藏为主;裂缝以中高角度缝、网状裂缝为主,其主要走向与井旁断层走向大致平行,属纵裂缝;裂缝主要发育在东西两侧靠近断层、近源的构造陡坡上;现今最大水平主应力方向主要呈NE-SW和NEE-SWW.成像测井解释结果与地质情况吻合较好. 相似文献
20.
简要介绍当前国内外关于天然地震与爆破、塌陷等非天然地震特征研究及事件类型识别的进展。对各类事件的定义及主要波形特征进行简要综述,重点介绍了事件类型判定的各类识别方法。与自然界天然地震不同,非天然地震由人工干预或人类活动间接引发。爆破是炸药在爆炸瞬间能量迅速释放,部分能量以地震波形式向外传播,引起地表振动而产生破坏效应的一种地震;塌陷是由于岩层崩塌陷落而形成的地震。虽然在地震台网记录到的天然地震与爆破、塌陷的波形存在一定的共性特征,但由于震源类型、波的传播路径、震源深度等不同,各类事件的波形记录在P波初动、P波与S波最大振幅比、持续时间、震相、短周期面波发育情况、发震时刻、空间位置分布以及频谱特征等方面差异明显。目前主要有两类方法来识别地震与爆破、塌陷等非天然事件。一类为直接基于波形在信号、数据方面的特征,通过定性分析来进行事件类型判定,如波形时频分析对比法、小波变换、相关系数等;另一类为统计学领域诸如模式识别等算法,利用统计算法综合考虑多个事件特征判据的定量判定阀值来实现地震与爆破、塌陷事件类型的识别,如最小距离法、改进的连续亨明方法、Fisher方法、逐步代价最小决策法、支持向量机、前馈神经网络等。两类方法本质上均为提取有效特征判据,即对数据进行降维使用,未将事件记录的全部信息用于事件判定。因此,有必要使用一种可从全部事件记录中自动提取各类信息并可组合底层特征的算法来对各类事件进行判断识别。 相似文献