基于简单语义的地理信息服务发现方法研究

为了解决目前地理信息发现查全率和查准率不高的问题,提出了一种简单语义的地理信息服务发现方法。该方法引入虚拟文档的概念,将服务划分为"操作级"进行匹配;运用同义词对服务操作中的概念词汇进行简单语义扩展;引入词汇语义相似度概念,应用词汇语义库来实现地理信息服务的简单语义匹配。实验结果表明,文中提出的方法在查全率和查准率等性能上均优于基于关键字和向量空间模型的方法,且完全基于当前网络服务环境实现。     

A new approach for crude oil price prediction based on stream learning

Crude oil is the world's leading fuel, and its prices have a big impact on the global environment, economy as well as oil exploration and exploitation activities. Oil price forecasts are very useful to industries, governments and individuals. Although many methods have been developed for predicting oil prices, it remains one of the most challenging forecasting problems due to the high volatility of oil prices. In this paper, we propose a novel approach for crude oil price prediction based on a new machine learning paradigm called stream learning. The main advantage of our stream learning approach is that the prediction model can capture the changing pattern of oil prices since the model is continuously updated whenever new oil price data are available, with very small constant overhead. To evaluate the forecasting ability of our stream learning model, we compare it with three other popular oil price prediction models. The experiment results show that our stream learning model achieves the highest accuracy in terms of both mean squared prediction error and directional accuracy ratio over a variety of forecast time horizons.     

Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China

The Support Vector Machine (SVM) is an increasingly popular learning procedure based on statistical learning theory, and involves a training phase in which the model is trained by a training dataset of associated input and target output values. The trained model is then used to evaluate a separate set of testing data. There are two main ideas underlying the SVM for discriminant-type problems. The first is an optimum linear separating hyperplane that separates the data patterns. The second is the use of kernel functions to convert the original non-linear data patterns into the format that is linearly separable in a high-dimensional feature space. In this paper, an overview of the SVM, both one-class and two-class SVM methods, is first presented followed by its use in landslide susceptibility mapping. A study area was selected from the natural terrain of Hong Kong, and slope angle, slope aspect, elevation, profile curvature of slope, lithology, vegetation cover and topographic wetness index (TWI) were used as environmental parameters which influence the occurrence of landslides. One-class and two-class SVM models were trained and then used to map landslide susceptibility respectively. The resulting susceptibility maps obtained by the methods were compared to that obtained by the logistic regression (LR) method. It is concluded that two-class SVM possesses better prediction efficiency than logistic regression and one-class SVM. However, one-class SVM, which only requires failed cases, has an advantage over the other two methods as only “failed” case information is usually available in landslide susceptibility mapping.     

Method and application of comprehensive knowledge discovery

This paper proposes the principle oi comprehensive knowledge discovery. Unlike most of the current knowledge discovery methods, the com-prehensive knowledge discovery considers both the spatial relations and attributes of spatial entities or objects. We intro-duce the theory of spatial knowledge ex-pression system and some concepts inclu-ding comprehensive knowledge discovery and spatial union information table (SUIT). In theory, SUIT records all in-formation contained in the studied ob-jects, but in reality, because of the com-plexity and varieties of spatial relations,only those factors of interest to us are se-lected. In order to find out the compre-hensive knowledge from spatial databas-es, an efficient comprehensive knowledge discovery algorithm called recycled algo-rithm (RAR) is suggested.     

KNOWLEDGE DISCOVERY OF REMOTELY SENSED DATA FROM ECOLOGICAL VIEW ——A Case Study of Urban Spatial—temporal Relationship in the Pearl River Delta

From the ecological viewpoint this paper discusses the urban spatial-temporal relationship.We take regional towns and cities as a complex man-land system of urban eco-community,This complex man-land system comprises two elements of “man“ and “land“,Here,“man“ means organization with self-determined consciousness,and “land“ means the physical environment (niche ) that “man “depends on .The complex man-land system has three basic components,They are individual,population and community,Therefore there are six types of spatial relationship for the complex man-land system.They are individual,population,community,man-man,land-land and man-land spatial realtionships,Taking the Pearl(Zhujiang) River Delta as a case study,the authors found some evidence of the urban spatial relationship from the remote sensing data,Firstly,the concentration and diffusion of the cities spatial relationship was found in the remote sensing imagery,Most of the cities concentrate in the core area of the Pearl River Delta ,but the diffusion situation is also significant ,Secondly,the growth behavior and succession behavior of the urban spatial relationship was found in the remote sensing images comparison with different temporal data ,Thirdly,the inheritance,break ,or meeting emergency behavior was observed from the remoted sensing data.Fourthly,the authors found many cases of symbiosis and competi-tion in the remote sensing data of the Pearl River Delta ,Fifthly,The autoeciousness,stranglehold and invasion behavior of the urban spatial relationship was discovered from the remote sensing data.     

Comparison of Methods Used to Estimate Conventional Undiscovered Petroleum Resources: World Examples

Various methods for assessing undiscovered oil, natural gas, and natural gas liquid resources were compared in support of the USGS World Petroleum Assessment 2000. Discovery process, linear fractal, parabolic fractal, engineering estimates, PETRIMES, Delphi, and the USGS 2000 methods were compared. Three comparisons of these methods were made in: (1) the Neuquen Basin province, Argentina (different assessors, same input data); (2) provinces in North Africa, Oman, and Yemen (same assessors, different methods); and (3) the Arabian Peninsula, Arabian (Persian) Gulf, and North Sea (different assessors, different methods). A fourth comparison (same assessors, same assessment methods but different geologic models), between results from structural and stratigraphic assessment units in the North Sea used only the USGS 2000 method, and hence compared the type of assessment unit rather than the method. In comparing methods, differences arise from inherent differences in assumptions regarding: (1) the underlying distribution of the parent field population (all fields, discovered and undiscovered), (2) the population of fields being estimated; that is, the entire parent distribution or the undiscovered resource distribution, (3) inclusion or exclusion of large outlier fields; (4) inclusion or exclusion of field (reserve) growth, (5) deterministic or probabilistic models, (6) data requirements, and (7) scale and time frame of the assessment. Discovery process, Delphi subjective consensus, and the USGS 2000 method yield comparable results because similar procedures are employed. In mature areas such as the Neuquen Basin province in Argentina, the linear and parabolic fractal and engineering methods were conservative compared to the other five methods and relative to new reserve additions there since 1995. The PETRIMES method gave the most optimistic estimates in the Neuquen Basin. In less mature areas, the linear fractal method yielded larger estimates relative to other methods. A geologically based model, such as one using the total petroleum system approach, is preferred in that it combines the elements of petroleum source, reservoir, trap and seal with the tectono-stratigraphic history of basin evolution with petroleum resource potential. Care must be taken to demonstrate that homogeneous populations in terms of geology, geologic risk, exploration, and discovery processes are used in the assessment process. The USGS 2000 method (7th Approximation Model, EMC computational program) is robust; that is, it can be used in both mature and immature areas, and provides comparable results when using different geologic models (e.g. stratigraphic or structural) with differing amounts of subdivisions, assessment units, within the total petroleum system.     

地震前兆信息识别的一种人工智能方法

探讨了识别地震前兆信息的新途径。使衙“机器发现”方法，即利用计算机技术，运用递归函数理论处理前兆观测资料，建立其解析函数表达式，并以解析表达式的外推值作为识别异常的标准，实现了对地震前兆信息的定量分析。对倾斜固体潮Ｍ２波潮汐因子γ值进行实际处理，与平静期或有强震异常的时段进行映震分析，其吻合程度较好     

Numerical Modeling of Coupled Geodynamical Processes and Its Role in Facilitating Predictive Ore Discovery: An Example from Tongling, China

Abstract. Facilitating more predictive ore discovery is becoming an increasingly challenging task for the resources geology research and exploration industry. The numerical geodynamic modeling, which uses numerical code to reproduce feedback coupling of geodynamic processes in the computer, is one of endeavors for forming sound predictive exploration strategy by thoroughly understanding the mineralization system and its controlling factors. The FLAC (Fast Lagrangian Analysis of Continua) is a two-dimensional finite-difference code for studying the mechano-thermo-hydrological behavior of a continuous porous medium after it reached equilibrium or steady plastic flow. We used the FLAC to simulate the syn-deformation cooling and fluid flowing after the intrusion was emplaced and solidified in the Fenghuangshan ore field, Tongling Cu district for guiding analysis of ore-controlling factors and selection of the exploration target area. The results of numerical computation demonstrate that the dilatant deformation zones along the contact of the intrusion control the fluid focus and the location and scale of ore bodies. Further more, the simulation results suggest a most prospective exploration area in the south high dilation zone, where the subsequent exploration supported the prediction and the test bore hole disclosed the high quality copper ore bodies in the target. This example has demonstrated the positive role of the numerical geodynamic modeling in facilitating predictive ore discovery.