Use of Noise to Augment Training Data: A Neural Network Method of Mineral–Potential Mapping in Regions of Limited Known Deposit Examples

One of the main factors that affects the performance of MLP neural networks trained using the backpropagation algorithm in mineral-potential mapping isthe paucity of deposit relative to barren training patterns. To overcome this problem, random noise is added to the original training patterns in order to create additional synthetic deposit training data. Experiments on the effect of the number of deposits available for training in the Kalgoorlie Terrane orogenic gold province show that both the classification performance of a trained network and the quality of the resultant prospectivity map increasesignificantly with increased numbers of deposit patterns. Experiments are conducted to determine the optimum amount of noise using both uniform and normally distributed random noise. Through the addition of noise to the original deposit training data, the number of deposit training patterns is increased from approximately 50 to 1000. The percentage of correct classifications significantly improves for the independent test set as well as for deposit patterns in the test set. For example, using ±40% uniform random noise, the test-set classification performance increases from 67.9% and 68.0% to 72.8% and 77.1% (for test-set overall and test-set deposit patterns, respectively). Indices for the quality of the resultant prospectivity map, (i.e. D/A, D × (D/A), where D is the percentage of deposits and A is the percentage of the total area for the highest prospectivity map-class, and area under an ROC curve) also increase from 8.2, 105, 0.79 to 17.9, 226, 0.87, respectively. Increasing the size of the training-stop data set results in a further increase in classification performance to 73.5%, 77.4%, 14.7, 296, 0.87 for test-set overall and test-set deposit patterns, D/A, D × (D/A), and area under the ROC curve, respectively.     

Use of Fuzzy Membership Input Layers to Combine Subjective Geological Knowledge and Empirical Data in a Neural Network Method for Mineral-Potential Mapping

Use of GIS layers, in which the cell values represent fuzzy membership variables, is an effective method of combining subjective geological knowledge with empirical data in a neural network approach to mineral-prospectivity mapping. In this study, multilayer perceptron (MLP), neural networks are used to combine up to 17 regional exploration variables to predict the potential for orogenic gold deposits in the form of prospectivity maps in the Archean Kalgoorlie Terrane of Western Australia. Two types of fuzzy membership layers are used. In the first type of layer, the statistical relationships between known gold deposits and variables in the GIS thematic layer are used to determine fuzzy membership values. For example, GIS layers depicting solid geology and rock-type combinations of categorical data at the nearest lithological boundary for each cell are converted to fuzzy membership layers representing favorable lithologies and favorable lithological boundaries, respectively. This type of fuzzy-membership input is a useful alternative to the 1-of-N coding used for categorical inputs, particularly if there are a large number of classes. Rheological contrast at lithological boundaries is modeled using a second type of fuzzy membership layer, in which the assignment of fuzzy membership value, although based on geological field data, is subjective. The methods used here could be applied to a large range of subjective data (e.g., favorability of tectonic environment, host stratigraphy, or reactivation along major faults) currently used in regional exploration programs, but which normally would not be included as inputs in an empirical neural network approach.     

Flow and fracture maps for basaltic rock deformation at high temperatures

Understanding how the strength of basaltic rock varies with the extrinsic conditions of stress state, pressure and temperature, and the intrinsic rock physical properties is fundamental to understanding the dynamics of volcanic systems. In particular it is essential to understand how rock strength at high temperatures is limited by fracture. We have collated and analysed laboratory data for basaltic rocks from over 500 rock deformation experiments and plotted these on principal stress failure maps. We have fitted an empirical flow law (Norton’s law) and a theoretical fracture criterion to these data. The principal stress failure map is a graphical representation of ductile and brittle experimental data together with flow and fracture envelopes under varying strain rate, temperature and pressure. We have used these maps to re-interpret the ductile–brittle transition in basaltic rocks at high temperatures and show, conceptually, how these failure maps can be applied to volcanic systems, using lava flows as an example.     

北京市地形图图式应用研究

城市建设出现了地形图图式未规定的地物要素,地形测量、地理信息系统、数字制图技术的应用给图式的设计提出了新的课题,本文旨在探讨设计和修订图式的思路和方法。     

Validation of Landslide Susceptibility Maps; Examples and Applications from a Case Study in Northern Spain

A procedure for validating landslide susceptibility maps wasapplied in a study area in northern Spain and the results obtained compared. Validationwas used to carry out sensitivity analysis for individual variables and combinationsof variables. The validity of different map-making methods was tested, as well as theutility of different types of Favourability Functions. The results obtained show thatvalidation is essential to determine the predictive value of susceptibility maps. Italso helps to better select the most suitable function and significant variables, thus improving the efficiency of the mapping process. Validation based on a temporal strategy makes it possible to derive hazard maps from susceptibility maps.     

地图数学定义的研究

在地图内容和形式数学表示的基础上研究了地图的数学定义。由于引入隐式地图和变换条件，故所有储存地图信息的载体均可属于地图的范围，从而使地图定义获得了广义的解释和精确的表达     

The l:200,000-scale map of the near-surface mineral resources of the Federal Republic of Germany

For those who deal with aspects of regional planning that are affected by the extraction of near-surface mineral resources, a simple map that shows the distribution of these resources accompanied by explanatory notes is essential; a preliminary 1:1 million-scale map was published in 1982. The Geological Surveys of the Federal States of Germany, in conjunction with the Federal Institute for Geosciences and Natural Resources, are compiling a series of maps that will cover the country at a scale of 1:200,000. When completed by the end of the next decade, this set of maps will consist of 57 sheets, each of which will be accompanied by explanatory notes. By the end of 1995, 17 sheets had been published BGR reports on the status of a Federal mineral-resource mapping program.     

Crustal and mantle strengths in continental lithosphere: is the jelly sandwich model obsolete?

The relative importance of the contribution of the lower crust and of the lithospheric mantle to the total strength of the continental lithosphere is assessed systematically for realistic ranges of layer thickness, composition, and temperature. Results are presented as relative strength maps, giving the ratio of the lower crust to upper mantle contribution in terms of crustal thickness and surface heat flow. The lithosphere shows a “jelly sandwich” rheological layering for low surface heat flow, thin to average crustal thickness, and felsic or wet mafic lower crustal compositions. On the other hand, most of the total strength resides in the seismogenic crust in regions of high surface heat flow, crust of any thickness, and dry mafic lower crustal composition.     

矢量地形图拓扑等问题的研究与实践

对矢量地图生产过程中常见的图形拓扑、数据冗余问题进行分析和研究；在此基础上结合生产实践，提出了相应的解决办法。研制了基于AutoCAD2000平台的相关程序。     

Visualization issues in the development of electronic atlas in China

In this paper, we discuss the development of electronic atlas in China, with focus on the issues of visualization. We particularly categorise this development into four periods, and then analyse the characters in each period and discuss the visualization issues. The four periods are highlighted: 1) Infant period (<1990) characterized as computer assisted mapping with products of screen maps; 2) Starting period (1991-1995) characterized as object-oriented mapping with products of interactive maps/atlases; 3) Advancing period (1996-2000) characterized as integrated mapping with products of multimedia cartographic maps; 4) New era (> 2001) characterized as web mapping and adaptive map design with products of Internet maps and atlas as well as adaptive maps. It is obvious that the development follows the logical way from static to dynamic, and even real time visualization, from single user to multiple users, from presentation to exploration for effective communication and knowledge construction. Current research and development projects are focused on customisation of atlas information systems for real-time tasks, Internet operability, small displays and mobile environments. The major challenges involved in each of such customisation processes are identified and commented in relation to the further development of visualization.