Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

L.Peeters; F.Ba??o; V.Lobo; A.Dassargues

首页> 外文期刊>Hydrology and Earth System Sciences >Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

【24h】

Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

机译：利用Kohonen自组织图的一种变体GEO3DSOM进行探索性数据分析和多元空间水文地质数据的聚类

获取原文

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

The use of unsupervised artificial neural network techniques likethe self-organizing map (SOM) algorithm has proven to be a usefultool in exploratory data analysis and clustering of multivariatedata sets. In this study a variant of the SOM-algorithm is proposed,the GEO3DSOM, capable of explicitly incorporating three-dimensionalspatial knowledge into the algorithm. The performance of theGEO3DSOM is compared to the performance of the standard SOM inanalyzing an artificial data set and a hydrochemical data set. Thehydrochemical data set consists of 131 groundwater samples collectedin two detritic, phreatic, Cenozoic aquifers in Central Belgium.Both techniques succeed very well in providing more insight in thegroundwater quality data set, visualizing the relationships betweenvariables, highlighting the main differences between groups ofsamples and pointing out anomalous wells and well screens. TheGEO3DSOM however has the advantage to provide an increasedresolution while still maintaining a good generalization of the dataset.

机译：无监督人工神经网络技术（如自组织映射（SOM）算法）的使用已被证明是探索性数据分析和多元数据集聚的有用工具。在这项研究中，提出了一种SOM算法的变体GEO3DSOM，它能够将三维空间知识明确地整合到算法中。将GEO3DSOM的性能与标准SOM的性能进行比较，分析了人工数据集和水化学数据集。水化学数据集由在比利时中部的两个碎屑，潜水，新生代含水层中收集的131个地下水样品组成，这两种技术均能很好地提供对地下水质量数据集的更多见解，可视化变量之间的关系，突出显示各组样品之间的主要差异并指出异常井和筛网。但是，GEO3DSOM的优点是可以提供更高的分辨率，同时仍然可以很好地概括数据集。

著录项

来源
《Hydrology and Earth System Sciences》 |2007年第4期|共13页
作者
L.Peeters; F.Ba??o; V.Lobo; A.Dassargues;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种
中图分类水文科学（水界物理学）;
关键词

相似文献

外文文献
中文文献
专利

1. Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map [J] . Peeters L, Bacao R, Lobo V, Hydrology and Earth System Sciences . 2007,第4期

机译：利用Kohonen自组织图的变体GEO3DSOM进行探索性数据分析和多元空间水文地质数据的聚类
2. Clustering spatial-temporal precipitation data using wavelet transform and self-organizing map neural network [J] . Kuo-Chin Hsu, Sheng-Tun Li Advances in Water Resources . 2010,第2期

机译：利用小波变换和自组织映射神经网络对时空降水数据进行聚类
3. The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data [J] . Rauber A., Merkl D., Dittenbach M. IEEE Transactions on Neural Networks . 2002,第6期

机译：不断增长的分层自组织图：高维数据的探索性分析
4. Exploratory data analysis with Multi-Layer Growing Self-Organizing Maps [C] . Proceedings of the 2010 5th International Conference on Information and Automation for Sustainability . 2010

机译：利用多层增长的自组织图进行探索性数据分析
5. The use of data topology in unsupervised clustering of high-dimensional data with self-organizing maps. [D] . Tasdemir, Kadim. 2008

机译：在具有自组织映射的高维数据的无监督聚类中使用数据拓扑。
6. Cluster Analysis of Comparative Genomic Hybridization (CGH) Data Using Self-Organizing Maps: Application to Prostate Carcinomas [O] . Torsten Mattfeldt, Hubertus Wolter, Ralf Kemmerling, 2001

机译：使用自组织图的比较基因组杂交（CGH）数据的聚类分析：在前列腺癌中的应用
7. Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map [O] . Peeters, Luk, Bacao, R., Lobo, V., 2007

机译：利用Kohonen自组织图的变体GEO3DSOM进行探索性数据分析和多元空间水文地质数据的聚类

Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

摘要

著录项

相似文献

相关主题

期刊订阅