Temporal GIS: Advanced Functions for Field-Based ApplicationsTrustonlymovement. Life happens at the level of events not of words. Trust movement. A. Adler As its title suggests, the main goal of this book is the development of advanced fu- tions for field-based Temporal Geographical Information Systems (TGIS).These fields may describe a variety of natural, epidemiological, economical, and social phen- ena distributed across space and time.Within such a framework, the book makes an attempt to establish links between, (a) the currently conceived TGIS techniques, and (b) the Bayesian maximum entropy (BME) techniques of Modern Spatiotemporal G- statistics.This link could be vital for offering significant improvements in the advanced functions of TGIS analysis and modelling, as well as generating useful information in a variety of real-world decision making and planning situations. To achieve the above goals, the eight Chapters of the book are organized around four main themes: Concepts, mathematical tools, computer programs, and applications. In fact, the focus is mainly on the step-by-step implementation of the compu- tional BME approach and the extensive use of illustrative examples and real-world applications.Indeed, because of the applied character of the present book, no detailed theoretical explanations or mathematical derivations are included.Instead, the reader is referred to the earlier book by Christakos (Modern Spatiotemporal Geostatistics, Oxford Univ.Press, New York, N.Y., 2000) for a comprehensive presentation of these BME aspects.With this in mind, the chapter-by-chapter organization of the book is described next. |
Contents
A BME View to the New Realities of TGIS | 1 |
112 Synthesis Organization and Visualization | 2 |
113 ActionOriented | 3 |
12 FieldBased TGIS | 4 |
13 TGIS Functions | 8 |
14 Novel Contribution to TGIS | 10 |
141 BMEBased Advanced Functions | 11 |
143 BMElib Software | 12 |
636 NonBayesian Analysis | 119 |
64 Quantifying the Mapping Efficiency of Soft Data | 120 |
65 Numerical Investigations of Popular Techniques | 122 |
652 The Inadequacy of Indicator Kriging | 131 |
66 Merging Maps with BME | 138 |
67 Synopsis | 141 |
The BME Computer Library | 143 |
72 Getting Started | 144 |
145 Scientific Hypothesis Testing and Explanation | 13 |
15 Concluding Remarks | 14 |
Spatiotemporal Modelling | 17 |
22 The Random Field Model | 24 |
23 The Role of Metaphors in TGIS | 27 |
24 The Importance of Physical Geometry | 28 |
25 Synopsis | 32 |
Knowledge Bases Synthesis | 33 |
32 General KB and the Associated Physical Constraints | 35 |
321 SpaceTime Correlation Functions Between Two or More Points MultiplePoint Statistics | 36 |
322 Physical Models | 41 |
33 Specificatory KB | 44 |
331 Hard and Soft Data | 45 |
332 The Effect of Soft Data on the Calculation of the SpaceTime Correlation Functions | 50 |
34 Accommodating Knowledge Needs | 51 |
Spatiotemporal Mapping | 53 |
42 Formal BME Analysis and Mapping | 56 |
421 The Basic BME Procedure | 57 |
422 The Advantage of Composite SpaceTime Mapping | 59 |
423 ContinuousValued Map Reconstruction | 63 |
424 Modifications of the BME Procedure | 64 |
425 Spatiotemporal Filtering | 66 |
426 Spatiotemporal Mapping and ChangeofScale Procedures | 68 |
43 Other Mapping Techniques | 73 |
432 Geostatistical Kriging and Neural Networks | 74 |
433 KalmanBucy Filtering | 76 |
434 Some Comparisons | 77 |
44 Concluding Remarks | 81 |
Interpretive BME | 83 |
52 An Epistemic Analysis of the BME Approach | 84 |
53 NonBayesian Conditionalization | 87 |
531 Material Biconditionalization | 88 |
532 Material Conditionalization | 94 |
54 By Way of a Summary | 95 |
The BME Toolbox in Action | 97 |
62 StepbyStep BME | 98 |
622 The Diagrammatic Representation | 100 |
63 Analytical and Numerical CaseStudies | 103 |
632 Spatiotemporal Filtering | 104 |
633 Exogenous Information | 105 |
634 Physical Laws | 110 |
635 Using Soft Data to Improve TGIS Mapping | 113 |
723 Getting Started with BMELib | 145 |
73 The iolib Directory | 149 |
731 The readGeoEASm and writeGeoEASm Functions | 150 |
732 The readProbam and writeProbam Functions | 151 |
733 The readBMEprobam and writeBMEprobam Functions | 153 |
742 The colorplotm Function | 154 |
744 The valplotm Function | 155 |
75 The modelslib Directory | 156 |
752 The modelplotm Function | 158 |
753 A Tutorial Use of the modelslib Directory | 159 |
761 The kerneldensitym Function | 161 |
763 The covariom Function | 162 |
764 The crosscovariom Function | 163 |
766 A Tutorial Use of the statlib Directory | 164 |
771 The probam Functions | 165 |
773 The BMEprobaModem Function | 170 |
775 The BMEprobaClm Function | 171 |
776 The BMEprobaTModem BMEprobaTPdfm and BMEprobaTCIm Functions | 172 |
777 Working with Files | 173 |
778 A Tutorial Use of the bmeprobalib Directory | 175 |
781 The BMEintervalModenl Function | 176 |
783 The BMEintervalTModem Function | 177 |
784 The BMEintervalTPdfm Function | 178 |
785 A Tutorial Use of the bmeintlib Directory | 179 |
792 The krigingfilterm Function | 180 |
793 A Tutorial Use of the bmehrlib Directory | 181 |
7102 The simuseqm Function | 182 |
7103 A Tutorial Use of the simulib Directory | 183 |
7112 The iso2anisom Function | 184 |
7114 The coord2Km Function | 185 |
7116 A Tutorial Use of the genlib Directory | 186 |
7121 The mvnlibcompilem Function | 187 |
7133 The testslib Directory | 188 |
Scientific Hypothesis Testing Explanation and Decision Making | 189 |
82 Hypothesis Testing | 193 |
83 Scientific Explanation | 197 |
84 Geographotemporal Decision Making | 200 |
85 Prelude | 205 |
209 | |
215 | |
Other editions - View all
Temporal GIS: Advanced Functions for Field-Based Applications George Christakos,Patrick Bogaert,Marc Serre No preview available - 2013 |
Common terms and phrases
BME analysis BME approach BME technique BME-based BMElib BMEmode bmeprobalib BMEprobaMoments.m Bryansk calculated Cholesky decomposition Column vector computational conditionalization considered correlation functions corresponding covariance model covariance or variogram data points dataset datum distance distribution dmax domain epidemiological epistemic equations estimation errors estimation points Euclidean Example field values Fisher information Fortran77 Function This function Gaussian geographotemporal Geostatistics hard data hypothesis testing input variables integration interval data invoking the function Kalman-Bucy filter knowledge Kriging linear locations mapping techniques mathematical MatLab matrix mean squared error metric Modern Spatiotemporal Geostatistics multivariate nested models obtained output variables paradigm physical laws posterior pdf predictions random field reader Sā Sect simulated site-specific situation soft data soft pdf soft probabilistic data space space/time mapping spatial spatiotemporal mapping specified statistics stochastic syntax for invoking temporal TGIS applications TGIS specialist tion variance variogram model Xā Xdata Xmap
Popular passages
Page 212 - The real voyage of discovery consists not in seeking new landscapes, but in having new eyes. M. Proustā