Developing a Geological Management Information System： National Important Mining Zone Database

INTRODUCTIONGeographic information systems (GIS) is a newtechnology of storing and processing spatial informa-tion , which can combine graphics with many types ofdatabase .It can also exhibit accurate and real spaceinformation with charts and texts according to actualneed ,and canintegrate geographic locations and cor-related data attributes as an organic whole .Geoscien-tists have shown GIS to be a very useful tool in theanalysis of geoscience problems (Zhao et al .,2004 ;Singer ,1993…     

Association Rule Discovery and Its Applications

ＩＮＴＲＯＤＵＣＴＩＯＮＤａｔａｍｉｎｉｎｇｏｒｋｎｏｗｌｅｄｇｅｄｉｓｃｏｖｅｒｙｉｎｄａｔａｂａｓｅ (ＫＤＤ)ｈａｓｉｎｒｅｃｅｎｔｙｅａｒｓａｔｔｒａｃｔｅｄａｌｏｔｏｆｉｎｔｅｒｅｓｔｉｎｔｈｅｄａｔａｂａｓｅｃｏｍｍｕｎｉｔｙ .Ｔｈｅｉｎｔｅｒｅｓｔｉｓｍｏｔｉｖａｔｅｄｂｙｔｈｅｌａｒｇｅａｍｏｕｎｔｏｆｃｏｍｐｕｔｅｒｉｚｅｄｄａｔａｔｈａｔｍａｎｙｏｒｇａｎｉｚａｔｉｏｎｓｎｏｗｈａｖｅｔｈｅｉｒｂｕｓｉ ｎｅｓｓ .Ｆｏｒｉｎｓｔａｎｃｅ,ｓｕｐｅｒｍａｒｋｅｔｓｓｔｏｒｅｅｌｅｃ…     

全国矿山地质环境调查信息系统及应用

全国矿山地质环境信息系统是为了配合中国地质调查局在全国范围内开展以省(区、市)为单元的矿山地质环境调查与评估工作而开发的应用程序。系统主要功能包括:数据录入、数据存储、数据查询、数据统计、数据分析、数据报表、图形数据组织、显示与管理、多媒体链接等。该系统界面清晰,操作简单,扩展性强,可作为省级矿山地质环境调查与评估的信息管理平台,也可以应用于矿山企业管理部门或矿山企业本身。文章详细介绍了系统的功能,并以北京市矿山地质环境调查为例介绍了该系统的应用。     

大数据与数学地球科学研究进展——大数据与数学地球科学专题代序

大数据与数学地球科学的核心应用技术包括高维数据降维、图像数据处理、无限数据流挖掘、机器学习、关联规则算法与推荐系统算法等。人工智能地质学,包括大数据-智能矿床成因模型与找矿模型的构建,是具有重要价值的研究方向。高维数据降维旨在从初始高维特征集合中选出低维特征集合,有效地消除无关和冗余特征,增强学习结果的易理解性。哈希算法、聚类分析、主成分分析等是较常用的数学降维工具。机器学习是人工智能的核心,是使计算机具有智能的根本途径。机器学习与人工智能各种基础问题的统一性观点正在形成。深度学习的训练模型往往需要海量数据作为支撑,因此迁移学习方法日益受到重视。图像模式识别是大数据挖掘的重要技术。网络中的社区结构识别对理解整个网络的结构和功能有重要价值,可帮助分析、预测网络各元素间的交互关系。沉浸式虚拟现实技术是实现大数据可视化的重要方向,对具有多元、异构、时空性、非线性、多尺度地质矿产勘查数据的展示要求有特别的价值。引入VR技术进行矿产地质大数据的可视化,可实现大数据时代矿产勘查数据的新认知。无限数据流在地质、地球化学、地球物理监测中大量存在,甚至可以持续自动产生。对数据流数据的计算包括对点查询、范围查询、内积查询、分位数计算、频繁项计算等。关联规则和推荐系统算法是大数据挖掘中的重要算法,其应用范围越来越广泛。贝叶斯原理在大数据时代有独特的价值,贝叶斯网络是成因建模的一个革命性工具。智能地质学研究刚刚起步,构建大数据-智能矿床成因模型与找矿模型是智能地质学研究的重要内容。矿床模型研究方式的变革,将出现于互联网、云计算技术环境下全球各地的矿床研究团队的共同参与。     

人工神经网络与分析测试技术的研究与发展

回顾了人工神经网络研究的发展历程，简要介绍了神经网络模型与算法，对分析测试技术和相关学科中的人工神经网络研究及在流程控制、错误诊断、参数估计、传感器模型、模式识别与分类、环境监测与治理及光谱与化学分析中的应用等作了评述。引用参考文献１１３篇。     

Uncertain spatiotemporal data modeling and algebraic operations based on XML

The problem of modeling and operating spatiotemporal data has received a great deal of interest, due to its various applications in the real world such as GIS and sensor database. A wide range of work covering spatial data, temporal data and spatiotemporal data assumes that the data is known, accurate and complete. But in reality, information is often imprecise and imperfect. In addition, traditional data models which are investigating in the context of traditional database suffer from some inadequacy of necessary semantics such as inability to handle imprecise and uncertain information. Consequently, the advent of XML, which has the advantages of simplicity, readability and extensibility, seems to provide an opportunity for modeling and operating uncertain spatiotemporal data. Hence, the new problem that emerges is how to model and operate uncertain spatiotemporal data in XML. Therefore, in this paper, we establish an uncertain spatiotemporal data model based on XML. Then, on the basis of the model we provide a set of algebraic operations for capturing and handling uncertain spatiotemporal data. By employing algebraic operations, we demonstrate how to translate queries expressed in XQuery to our algebra. A translation example shows that our algebraic operations are full of expressive power and illustrates that our algebra can be applied to general data. Apart from this, we also propose a set of equivalence rules to optimize the process of query and give an example to show how the optimization approach works.     

Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams

In longwall development mining of coal seams, planning, optimizing and providing adequate ventilation are very important steps to eliminate the accumulation of explosive methane–air mixtures in the working environment. Mine operators usually try to supply maximum ventilation air based on the capacity of the system and the predicted need underground. This approach is neither economical nor safer as ventilation capacity may decrease in time depending on various mining and coalbed parameters. Thus, it is important to develop better engineered approaches to optimize mine ventilation effectiveness and, therefore, to ensure a safer work environment.This study presents an approach using coalbed methane reservoir modeling and an artificial neural network (ANN) design for prediction and optimization of methane inflows and ventilation air requirements to maintain methane concentrations below statutory limits. A coalbed reservoir model of a three-entry development section, which is typical of Pittsburgh Coalbed mines in the Southwestern Pennsylvania section of Northern Appalachian Basin, was developed taking into account the presence and absence of shielding boreholes around the entries against methane inflow. In the model, grids were dynamically controlled to simulate the advance of mining for parametric simulations.Development and application of artificial neural networks as an optimization tool for ventilation requirements are introduced. Model predictions are used to develop, train, and test artificial neural networks to optimize ventilation requirements. The sensitivity and applications of proposed networks for predicting simulator data are presented and discussed. Results show that reservoir simulations and integrated ANN models can be practical and powerful tools for predicting methane emissions and optimization of ventilation air requirements.     

Artificial Intelligence Applications in Transportation Geotechnics

This paper presents a brief overview of artificial intelligence applications in transportation geotechnics, highlighting new approaches and current research directions, including issues related to data mining interpretability and prediction capacities. Several practical applications to earthworks, including the compaction management and quality control aspects of embankments, as well as pavement evaluation, design and management, and the mechanical behaviour of jet grouting material, are presented to illustrate the advantages of using data mining, including artificial neural networks, support vector machines, and evolutionary computation techniques in this domain. This study also propose a novel simplified compaction table for reusing geomaterials and compaction management in embankments and applied one- and two-dimensional advanced sensitivity analyses to better interpret the proposed data-driven models for the prediction of the deformability modulus of jet grouting field samples. These applications show the capabilities of data mining models to address complex problems in transportation geotechnics involving highly nonlinear relationships of data and optimisation needs.     

野外地质调查作业管理与安全保障系统设计与实现

基于北斗导航定位、遥感卫星以及基础地理空间信息承载与综合显示平台而建立的野外地质调查作业管理与安全保障系统,采用组件化、平台化的系统体系结构,具备强大且灵活的可扩展性和可集成性。该系统可实现野外地质调查区域基础遥感影像、GIS和DEM数据等的分层显示、北斗通讯和导航信息的实时显示、通讯历史记录和定位信息的查询、野外地质调查人员的通讯与定位等;同时可实现野外地质调查人员与各级管理部门的互联互通,管理部门对野外作业人员的作业态势、作业进度可进行综合查询,对野外作业人员的外勤安全、遇险救援提供决策支撑。该系统在部分野外地质调查示范单位运行效果良好。      

Benthic foraminiferal response to changes in mining pattern: a case study from the Zuari estuary,Goa, India

Being sensitive to environmental changes, foraminifera have been extensively used to monitor pollution level in the marine environment, including the effect of mining in coastal areas. In the Goa state of India, the rejects from opencast mining on land largely find their way to the estuaries, as washout during monsoon. Additionally, the Mormugao Port at the mouth of the Zuari estuary is the hub of activities due to the transport of ore from hinterland areas by barges and its subsequent loading for export. On the directive of the Supreme Court of India, all the mining-related activities abruptly stopped throughout India, including that in Goa in 2012, and got reinstated in 2015. Therefore, it provided a fit case to test the effectiveness of benthic foraminifera as an indicator of environmental impact due to mining activities. A total of ten surface sediment samples from five locations in Zuari estuary were collected from a depth range of 4.5–8.5 m in the years of 2013 and 2016 and were analyzed for both the living (stained) and dead benthic foraminifera. The year 2013 represents a time interval immediately after the closure of extensive mining activity, and the sampling during 2016 represents minimal mining. The living benthic foraminiferal abundance was higher (19–54/g sediment) during 2013 and decreased substantially during 2016 (3–22/g sediment), suggesting an adverse effect of activities associated with mine closure on benthic foraminifera. Additionally, the relative abundance of Ammonia was also significantly low during the year 2016. The temporal variation in dead foraminifera was, however, different than that of the living foraminifera. The differential response was attributed to the terrigenous dilution as a result of change in sedimentation rate. Therefore, we conclude that living foraminifera correctly incorporate the changes in mining pattern and may be used as an effective tool to monitor the impact of mining. We further suggest that the potential counter effect of terrigenous dilution on total and living benthic foraminiferal population should be considered while interpreting temporal variations in foraminiferal abundance in marginal marine settings.     

机器学习与成矿预测:以闽西南铁多金属矿预测为例

作为近年来爆炸式发展的方法模型,机器学习为地质找矿提供了新的思维和研究方法.本文探讨矿产预测研究的理论方法体系,总结机器学习在矿产预测领域的特征信息提取和信息综合集成两个方面的应用现状,并讨论机器学习在矿产资源定量预测领域面临的训练样本稀少且不均衡、模型训练中缺乏不确定性评估、缺少反哺研究、方法选择等困难和挑战.进一步...     

基于GIS的大型工程分布式光纤传感监测系统研究

BOTDR是一种新型的分布式光纤传感监测技术,其分布式、高精度、长距离、实时性、远程控制等特点,已逐渐受到工程界的广泛关注。本文结合工程实践中遇到的具体问题,研发了一套基于GIS的大型工程分布式光纤传感监测系统,讨论了系统的设计要求。并结合某隧道BOTDR监测工程实例,开发了一套相应的监测数据管理系统。该系统集工程监测数据的采集与管理、监测结果的可视化、监测信息的对比查询等功能于一体,是一套集智能化分析与决策化管理为一体的多功能管理系统。     

Evaluation of complex petroleum reservoirs based on data mining methods

In this study, we introduce the application of data mining to petroleum exploration and development to obtain high-performance predictive models and optimal classifications of geology, reservoirs, reservoir beds, and fluid properties. Data mining is a practical method for finding characteristics of, and inherent laws in massive multi-dimensional data. The data mining method is primarily composed of three loops, which are feature selection, model parameter optimization, and model performance evaluation. The method’s key techniques involve applying genetic algorithms to carry out feature selection and parameter optimization and using repeated cross-validation methods to obtain unbiased estimation of generalization accuracy. The optimal model is finally selected from the various algorithms tested. In this paper, the evaluation of water-flooded layers and the classification of conglomerate reservoirs in Karamay oil field are selected as case studies to analyze comprehensively two important functions in data mining, namely predictive modeling and cluster analysis. For the evaluation of water-flooded layers, six feature subset schemes and five distinct types of data mining methods (decision trees, artificial neural networks, support vector machines, Bayesian networks, and ensemble learning) are analyzed and compared. The results clearly demonstrate that decision trees are superior to the other methods in terms of predictive model accuracy and interpretability. Therefore, a decision tree-based model is selected as the final model for identifying water-flooded layers in the conglomerate reservoir. For the reservoir classification, the reservoir classification standards from four types of clustering algorithms, such as those based on division, level, model, and density, are comparatively analyzed. The results clearly indicate that the clustering derived from applying the standard K-means algorithm, which is based on division, provides the best fit to the geological characteristics of the actual reservoir and the greatest accuracy of reservoir classification. Moreover, the internal measurement parameters of this algorithm, such as compactness, efficiency, and resolution, are all better than those of the other three algorithms. Compared with traditional methods from exploration geophysics, the data mining method has obvious advantages in solving problems involving calculation of reservoir parameters and reservoir classification using different specialized field data. Hence, the effective application of data mining methods can provide better services for petroleum exploration and development.     

基于GMS软件的海砂矿体三维地质建模和资源量估算

本文以南海北部某海域海砂矿区为例,提出了基于GMS软件的海砂矿三维地质建模和资源量估算方法.以钻孔和综合物探数据为源数据,划定了矿区内V1和V2矿体的边界,基于GMS软件系统构建了数据库,综合利用钻孔、综合物探、剖面图和海底地形控制面等资料,建立了三维地质模型,有效实现了海砂矿体三维可视化和体积资源量的估算.三维地质模...     

Research and application of cluster and association analysis in geochemical data processing

For applications of data mining techniques in geosciences, through mining spatial databases which are constructed with geophysical and geochemical data measured in fields, critical knowledge, such as the spatial distribution of geological targets, the geophysical and geochemical characteristics of geological targets, the differentiation among the geological targets, and the relationship among geophysical and geochemical data, can be discovered. Due to the complexity of geophysical and geochemical data, traditional mining methods of cluster analysis and association analysis have limitations in processing complex data. In this paper, a clustering algorithm based on density and adaptive density-reachable is presented which has the ability to handle clusters of arbitrary shapes, sizes, and densities. For association analysis, mining the continuous attributes may reveal useful and interesting insights about the data objects in geoscientific applications. An approach for distance-based quantitative association analysis is presented in this paper. Experiments and applications indicate that the algorithm and approach are effective in real-world applications.     

各向异性介质中的浅海海洋可控源电磁响应特征

由于受到空气波的影响,浅海海洋可控源电磁数据对海底储油层的反映较弱,如何对浅海数据进行处理和解释一直是海洋电磁理论研究的热点。随着近年来海洋电磁理论的不断完善,浅海数据已经可以被较好地处理与反演,但是其解释水平仍然受基本理论研究不足的制约。针对这一现状,本文开展了海底电各向异性对浅海数据影响规律的研究。具体方法为:利用欧拉旋转建立不同的海底电性各向异性模型,然后采用交错网格有限差分法计算浅海海洋可控源电磁响应,最后通过分析同线情况下电场E_x分量的振幅和相位曲线特征以及海底电场及电流密度分布规律,分析各向异性对浅海海洋可控源电磁响应影响的物理机制,并讨论浅海各向异性情况下海洋电磁对高阻储油层的识别能力。得出的结论为各向异性介质中的浅海海洋电磁响应特征与深海有较大区别,在进行数据的处理、反演和解释时应区别于深海情况。     

Multi-agent distributed data mining approach for classifying meteorology data: case study on Iran’s synoptic weather stations

Today’s organizations, industries and research centers are geographically distributed in different sites. To achieve true knowledge of business, mining massive amounts of data is necessary. In earth-related sciences such as meteorology, the date obtained from the various types of sensors is huge because of the high-frequency rate of data acquisition process and also the geographical distribution of weather stations. Therefore, the data mining and knowledge discovery process of this big and distributed data is a challenging work. In this paper, we propose a new distributed data mining approach called multi-agent hierarchical data mining to classify meteorology data, which has been collected from different sites widely distributed around the country (Iran). Our method utilizes a modified version of REPTree algorithm, which has been optimized to work in multi-agent system. To evaluate the proposed approach, it is implemented on 20 million of meteorology data record. Experimental results show that multi-agent hierarchical data mining approach can achieve significant performance improvement over centralized and parallel methods for knowledge discovery in large amounts of data.     

海洋区域地质调查中的高分辨率单道地震资料关键处理技术

在海洋区域地质调查中,为了揭示浅地层结构、断裂、岩浆活动以及各种潜在地质灾害,高分辨率单道地震勘探是不可缺少的重要手段之一,但由于受到各种噪声干扰,原始地震资料质量不佳,信噪比较低,影响了后续的解释工作。笔者阐述了采用关键单道地震处理技术,极大地提高了资料的信噪比和分辨率,为海域区域地质研究提供了良好的基础资料。