Satellites and the New War on Infection: Tracking Ebola in West Africa

Satellite technologies are increasingly being deployed to manage infectious disease outbreaks. Although there is a substantive literature concerned with the geopolitics of space and the ethical issues raised by the use of remote sensing in warfare and counterinsurgency, little study has been made of the critical role played by satellites in public health crises. In this paper, we focus on the 2014–2015 Ebola virus disease (EVD) epidemic in West Africa, which saw the widespread use of public and commercial satellite-derived data, to investigate how overhead orbital and close-up viewpoints enabled by satellites are shaping attitudes to disease and determining responses to infectious threats. We argue that high-resolution satellite imagery is acting as a spur to a new spatio-temporal targeting of disease that parallels the ever more vertical dimension of contemporary warfare. At the same time, this new visualization of disease is promoting a broader ecological perspective on pathogen emergence. How can these divergent perspectives be reconciled? In addressing this question, we analyze the different uses to which satellite imagery has been put in tracking and mapping Ebola ‘hotspots’ across Guinea, Liberia, and Sierra Leone. We also consider the institutional contexts that have enabled the acquisition of this imagery. Given the rapid integration of space technologies in epidemiology and health logistics, there is now a need to examine how and with what consequences remote-sensing and communication technologies may be reconfiguring the practices and scope of global health.     

人工智能神经网络在岩性识别、孔隙度和渗透率预测中的应用——以十红滩铀矿床为例

分析了传统测井解释方法的局限性。从神经网络的机理、特点出发,提出了一种基于人工智能神经网络技术的岩性识别、孔隙度和渗透率预测方法。首先选取适当的测井资料向量组成一个训练模式对,由多个训练模式对构成一个学习样本集。通过神经网络的学习,使网络记住这些特征并形成预测模型,最后根据预测模型计算相应参数。以十红滩地区的找矿目的层为对象,进行了岩性分析与对比,预测了孔隙度与渗透率,并与实测值进行了对比。上述实例分析表明,该方法用于砂岩型铀矿预测岩性、孔隙度和渗透率具有一定的可行性。与传统方法相比,该方法不需要建立具体的解释模型和计算公式,有较好的适应性和预测精度。基于人工智能神经网络技术的岩性识别、孔隙度和渗透率预测方法具有较高的实用价值。     

ID3决策树推理模型及其在道路网选取中的应用

介绍了自动制图综合中知识推理的研究现状及存在的问题,指出了借鉴人工智能优秀技术成果提升自动综合智能化水平是解决当前问题的重要途径之一。对ID3智能算法的基本原理进行了详细介绍,提出基于ID3决策树的知识推理模型。将该模型引入到道路网智能化选取当中。对该模型应用到道路网自动选取的合理性进行了论述,并进行了实验验证。在对实验结果进行详细分析的基础上,探讨了该算法应用于道路网选取的优势和不足,指出了进一步研究的方向。     

基于不同学科解决粗差探测问题的方法研究

通过对已有粗差探测成果的研究,本文按照基于的学科不同将其大致分为4类:数理统计粗差探测方法,基于多元统计分析粗差探测方法,线性代数粗差探测方法,人工智能粗差探测方法。然后从这4个方面辐射出已有的关于粗差发现、定位、定值等相关方法的研究,并且针对国内学者对用人工智能方法实现粗差探测未进行成熟研究的现状,提出可行策略并进行实现从而为人工智能和测量数据处理2个学科的结合开拓新的研究方向。     

Graphic Biostratigraphic Correlation Using Genetic Algorithms

The most generally used method for estimating the basin-wide sequence and scaling of first and last occurrences, based on their occurrence in local sections, is Shaw’s graphic correlation method. The key step in this method is the determination of the line of correlation (LOC), which represents the best estimate of the correlation between two local sections, or between a local section and a composite standard. In general, available techniques for fitting the LOC for multiple sections are tedious, subjective, or computationally expensive. A new method employing genetic algorithms can dramatically reduce the effort involved in determining the LOC and produces stable biostratigraphic correlations and composite range charts objectively and efficiently. Genetic algorithms are an artificial intelligence technique that excels in locating the optimum solution from a large number of alternative choices. In the case of the LOC, the alternative choices are the number of line segments comprising the complete line and the positions of each segment’s beginning and end points. For a given number of segments, a wide range of alternative LOCs can be rapidly evaluated and a potential optimum fit determined. It is also possible to estimate the point when no further refinement of the fit by adding line segments is necessary. Genetic algorithms can also be applied to other methods for quantitative biostratigraphy.     

Spatio-temporal modelling of the HIV epidemic in Japan based on the national HIV/AIDS surveillance

In this paper, we develop a multiregion epidemic model in order to provide the basic information on local HIV epidemic states in Japan. By considering the previous efforts of national epidemic projections in Japan, we statistically calibrate a model by employing an estimation method that allows the inclusion of geographically varying parameters. Using this model, we present a geographical projection of local epidemics until 2015 by examining geographical variations in future epidemic growth and spatial relationships in HIV transmission. We also discuss the implications of planning preventive measures and improvement in the Japanese HIV/AIDS surveillance system based on analytical results.     

基于知识与规则的城市管线数据计算机监理校验

本文通过对城市管线数据的分析与处理，得到对城市管线数据进行计算机监理校验的知识与规则，并利用这些知识与规则进行综合的城市管线数据校验。     

中国智力资源空间分布及其影响因素研究

现代社会已步入知识经济时代。知识经济显著特点就在于信息、知识等各种类型的智力资源取代工业经济的资本上升成为新的、决定性的终极资源和核心生产要素。在研究智力资源涵义的基础上，选取了投入、产出、环境支持、智力资源4个系统30个不同指标，运用数理统计方法中的因子分析来定量研究中国智力资源空间分布特点，从而进一步分析出影响中国智力资源的空间分布的4个主要因素：经济发展程度、行政区标准问题、历史因素和区域文化模式不同。     

Model of Land Suitability Evaluation Based on Computational Intelligence

A novel model of land suitability evaluation is built based on computational intelligence (CI). A fuzzy neural network (FNN) is constructed by the integration of fuzzy logic and artificial neural network (ANN). The structure and process of this network is clear. Fuzzy rules (knowledge) are expressed in the model explicitly, and can be self-adjusted by learning from samples. Genetic algorithm (GA) is employed as the learning algorithm to train the network, and makes the training of the model efficient. This model is a self-learning and self-adaptive system with a rule set revised by training.     

ARTIFICIAL INTELLIGENCE IN GEOGRAPHY: CONJECTURES ON THE SHAPE OF THINGS TO COME

Artificial intelligence (Al) and geography are brought together within a broad context involving fundamental issues of theory, epistemology and scientific method. The little known logico-mathematical background of Al is explored and shown to have substantial implications for modeling in general, prediction, the interpretation of theoretical structures, and our understanding of science itself. These more abstract aspects of the “computational revolution,”of which Al is one product, could have far-reaching consequences for geographic research.