| 地质大数据分析的若干工具与应用 |
| |
| 引用本文： | 周永章,陈川,张旗,王功文,肖凡,沈文杰,卞静,王亚,杨威,焦守涛,刘艳鹏,韩枫.地质大数据分析的若干工具与应用[J].大地构造与成矿学,2020(2):173-182. |
| |
| 作者姓名： | 周永章 陈川 张旗 王功文 肖凡 沈文杰 卞静 王亚 杨威 焦守涛 刘艳鹏 韩枫 |
| |
| 作者单位： | 中山大学地球环境与地球资源研究中心;广东省地质过程与矿产资源探查重点实验室;中国科学院地质与地球物理研究所;中国地质大学;中山大学地球科学与工程学院;广东高质资源环境研究院 |
| |
| 基金项目： | 国家自然科学基金项目(U1911202);国家重点研发计划项目(2016YFC0600506);中国地质调查局全国重要区带成矿远景调查项目(12120113067600);广东省地质过程与矿产资源探查重点实验室基金联合资助. |
| |
| 摘 要： | 大数据科学研究范式是大数据时代的必然结果。在大数据时代,地质学研究正面临着前所未有的挑战与机遇,亟需地质大数据分析的基础支撑。本文介绍若干种有价值的地质大数据分析工具及其应用。知识图谱以其强大的语义处理能力和开放组织能力,为大数据时代信息的知识化组织和智能应用提供了有效工具。它旨在描述真实世界中存在的各种实体或概念及其关系,构成一张巨大的语义网络图,以节点表示实体或概念,边则由属性或关系构成。机器学习与卷积神经网络模型仍然是当前地质大数据研究的热点。演化算法借鉴了自然界中生物进化与自适应过程的思想,是一种基于种群的元启发式最优化算法。它具有无需先验知识、能在全局范围内进行隐并行搜索的优点,可以用来精确地获取大数据中隐含的演化趋势与时空特征。图形社区发现技术将网络划分为若干个内部节点相似社区,为分析和理解网络提供有力的技术支持。随着空间分辨率、时间分辨率和辐射分辨率不断提高,遥感技术已广泛成为地质数据获得的主要技术手段。遥感大数据的数据存取和智能处理是最重要的发展方向。这些地质大数据分析方法已有成功的应用案例,并将广泛用于各种地质研究,如城市土壤污染智能监测、模拟、管控与预警研究,得益于地质大数据研究支撑系统的恰当选择以及地质大数据技术的强力支持,建立了可解释的多源多层城市土壤污染知识图谱,源于多源异构大数据有效融合的主要障碍正在去除。
|
| 关 键 词： | 地质大数据 知识图谱 机器学习 演化算法 图形社区发现 遥感大数据 多源异构大数据融合 |
Introduction of Tools for Geological Big Data Mining and Their Applications |
| |
| ZHOU Yongzhang,CHEN Chuan,ZHANG Qi,WANG Gongwen,XIAO Fan,SHEN Wenjie,BIAN Jing,WANG Ya,YANG Wei,JIAO Shoutao,LIU Yanpeng,and HAN Feng.Introduction of Tools for Geological Big Data Mining and Their Applications[J].Geotectonica et Metallogenia,2020(2):173-182. |
| |
| Authors: | ZHOU Yongzhang CHEN Chuan ZHANG Qi WANG Gongwen XIAO Fan SHEN Wenjie BIAN Jing WANG Ya YANG Wei JIAO Shoutao LIU Yanpeng and HAN Feng |
| |
| Institution: | (Center for Earth Environment and Resources,Sun Yat-sen University,Guangzhou 510275,Guangdong,China;Guangdong Provincial Key Laboratory of Mineral Resources and Geological Processes,Guangzhou 510275,Guangdong,China;Institute of Geology and Geophysics,China Academy of Sciences,Beijing 100029,China;China University of Geology,Beijing 100083,China;School of Earth Sciences and Engineering,Sun Yat-sen University,Guangzhou 510275,Guangdong,China;Guangdong Gaozhi Institute of Resources and Environment,Guangzhou 511493,Guangdong,China) |
| |
| Abstract: | The research paradigm of big data plays a key role in the emerging big data age.Geological research faces unprecedented challenges and opportunities,and calls for fundamental support by big data mining.This paper pays attention to a few tools of big data mining and their applications in geological field.With its powerful semantic processing ability and open organization ability,the knowledge map provides an effective tool for the knowledge-based organization and intelligent application of information in the big data age.It aims to describe the various entities or concepts that exist in the real world and their relationships.It constitutes a huge semantic network diagram.Nodes represent entities or concepts,and edges are composed of attributes or relationships.Machine learning and convolution neural network model is an important research hotspot in geological data mining.The evolutionary algorithm is a meta-heuristic optimization algorithm which draws lesson from the mode of biological evolution and adaptive processes in nature.It is advantageous that it can carry out hidden parallel search without prior knowledge and can be used to accurately obtain the evolutionary trends and space-time characteristics hidden in large data.Graphical community detection technology divides the network into several internal nodes-similar communities,and provides strong technical support for analysis and understanding of networks.With the continuous improvement of spatial resolution,time resolution and radiation resolution,the remote sensing technology has become the main technical means to obtain geological data.Data access and intelligent processing is the most important development direction of remote sensing big data research.There are successful application cases of the methods above and they will be widely used in various geological studies.The intelligent monitoring,simulation,control and early warning of urban soil pollution has benefitted from the proper selection of supporting systems for large-scale data research and the strong support of large-scale data technology in the field of geology.Major barriers to the effective fusion of large data from multiple sources are diminishing. |
| |
| Keywords: | geological big data knowledge graph machine learning evolutionary algorithm graphic communities detection remote sensing data multisource heterogeneous data fusion |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
