Multiscale Modeling

A Bayesian Perspective
1. Auflage 2007
ISBN: 978-0-387-70898-0
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 245 Seiten

This highly useful book contains methodology for the analysis of data that arise from multiscale processes. It brings together a number of recent developments and makes them accessible to a wider audience. Taking a Bayesian approach allows for full accounting of uncertainty, and also addresses the delicate issue of uncertainty at multiple scales. These methods can handle different amounts of prior knowledge at different scales, as often occurs in practice.

Autoren/Hrsg.

Inhaltsverzeichnis

1;Preface;7
2;Contents;9
3;Part I Introduction;13
3.1;1 Introduction;14
3.2;2 Models for Spatial Data;17
3.3;3 Illustrative Example;26
4;Part II Convolutions and Wavelets;29
4.1;4 Convolution Methods;32
4.2;5 Wavelet Methods;46
5;Part III Explicit Multiscale Models;61
5.1;6 Overview of Explicit Multiscale Models;62
5.2;7 Gaussian Multiscale Models on Trees;67
5.3;8 Hidden Markov Models on Trees;82
5.4;9 Mass-Balanced Multiscale Models on Trees;90
5.5;10 Multiscale Random Fields;100
5.6;11 Multiscale Time Series;116
5.7;12 Change of Support Models;147
6;Part IV Implicit Multiscale Models;155
6.1;13 Implicit Computationally Linked Model Overview;156
6.2;14 Metropolis-Coupled Methods;165
6.3;15 Genetic Algorithms;178
7;Part V Case Studies;192
7.1;16 Soil Permeability Estimation;193
7.2;17 Single Photon Emission Computed Tomography Example;211
7.3;18 Conclusions;220
8;References;222
9;Index;239