Modern Spatiotemporal Geostatistics
Modern Spatiotemporal Geostatistics
复制标题
DOI：
--
复制
发表时间：
2000-11
期刊：
影响因子：
--
通讯作者：
G. Christakos
中科院分区：
文献类型：
--
作者：
G. Christakos
人们普遍认识到，已经使用了几十年的经典地质统计学技术已经达到了极限，现在是给一些替代方法一个机会的时候了。因此，本书是对现代地质统计学基础的介绍，这是一组时空概念和方法，是随机数据分析的认知地位进步的产物。后者是从一个新颖的角度来考虑的，促进了这样一种观点，即对知识理论的更深入理解是发展改进的科学制图数学模型的重要先决条件。本书的主要焦点是贝叶斯最大熵（BME）的方法，用于研究自然变量的时空分布。作为现代地质统计学范式的一部分，BME方法提供了对绘图问题的基本见解，其中自然变量的知识，而不是变量本身，是研究的直接对象。贯穿全书的主线是，解决环境问题的现代地质统计学方法是自然科学家的方法，他们对随机分析更感兴趣，这些分析涉及本体论层面（为物理系统建立模型）和认识论层面（利用我们对物理系统的了解，整合和建模来自各种科学学科的知识）。而不是仅仅基于数据和假设之间的线性关系，以及可能在其他领域有用的无理论技术，对科学进行纯粹的朴素归纳。
It is widely recognized that the techniques of classical geostatistics, which have been used for several decades, have reached their limit, and the time has come for some alternative approaches to be given a chance. This book, therefore, is an introduction to the fundamentals of modern geostatistics, which is a group of spatiotemporal concepts and methods that are the products of the advancement of the epistemic status of stochastic data analysis. The latter is considered from a novel perspective, promoting the view that a deeper understanding of a theory of knowledge is an important prerequisite for the development of improved mathematical models of scientific mapping. The main focus of the book is the Bayesian Maximum Entropy (BME) approach for studying spatiotemporal distributions of natural variables. As part of the modern geostatistics paradigm, the BME approach provides a fundamental insight into the mapping problem in which the knowledge of a natural variable, not the variable itself, is the direct object of study. The thread running throughout the book is that the modern geostatistical approach to environmental problems is that of natural scientists who are more interested in a stochastic analysis concerned with both the ontological level(building models for physical systems) and the epistemic level (using what we know about the physical systems and integrating and modeling knowledge from a variety of scientific disciplines), rather than in the pure naive inductive account of science based merely on a linear relationship between data and hyptheses and theory-free techniques that may be useful in other areas.