Amazon no longer offers textbook rentals. We do!

Advanced Mapping of Environmental Data

by: Kanevski, Mikhail

Advanced Mapping of Environmental Data

by: Kanevski, Mikhail

ISBN 13:
9781848210608
ISBN 10:
1848210604
Edition: 1st
Format: Hardcover
Copyright: 12/15/2008
Publisher: Wiley-ISTE

Rent From $143.22

New From $216.36

List Price $217.54 Save

Rent $143.22

TERM	PRICE	DUE
SEMESTER	$150.76	Dec 13
QUARTER	$143.22	Aug 16
SHORT TERM	$135.68	Jul 04

Added Benefits of Renting

Free Shipping Both Ways
Highlight/Take Notes Like You Own It
Purchase/Extend Before Due Date

Add to Cart

List Price $217.54 Save $1.18

New $216.36

Usually Ships in 3-4 Business Days

We Buy This Book Back!

Included with your book

Free Shipping On Every Order

Add to Cart

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

Extend or Purchase Your Rental at Any Time

Need to keep your rental past your due date? At any time before your due date you can extend or purchase your rental through your account.

Summary

This book combines geostatistics and global mapping systems to present an up-to-the-minute study of environmental data. Featuring numerous case studies, the reference covers model dependent (geostatistics) and data driven (machine learning algorithms) analysis techniques such as risk mapping, conditional stochastic simulations, descriptions of spatial uncertainty and variability, artificial neural networks (ANN) for spatial data, Bayesian maximum entropy (BME), and more.

Preface	p. xi
Advanced Mapping of Environmental Data: Introduction	p. 1
Introduction	p. 1
Environmental data analysis: problems and methodology	p. 3
Spatial data analysis: typical problems	p. 3
Spatial data analysis: methodology	p. 5
Model assessment and model selection	p. 8
Resources	p. 12
Books, tutorials	p. 12
Software	p. 12
Conclusion	p. 14
References	p. 15
Environmental Monitoring Network Characterization and Clustering	p. 19
Introduction	p. 19
Spatial clustering and its consequences	p. 20
Global parameters	p. 21
Spatial predictions	p. 22
Monitoring network quantification	p. 23
Topological quantification	p. 23
Global measures of clustering	p. 23
Topological indices	p. 23
Statistical indices	p. 24
Dimensional resolution: fractal measures of clustering	p. 26
Sandbox method	p. 27
Box-counting method	p. 30
Lacunarity	p. 33
Validity domains	p. 34
Indoor radon in Switzerland: an example of a real monitoring network	p. 36
Validity domains	p. 37
Topological index	p. 37
Statistical indices	p. 38
Morisita index	p. 38
K-function	p. 39
Fractal dimension	p. 40
Sandbox and box-counting fractal dimension	p. 40
Lacunarity	p. 42
Conclusion	p. 43
References	p. 44
Geostatistics: Spatial Predictions and Simulations	p. 47
Assumptions of geostatistics	p. 47
Family of kriging models	p. 49
Simple kriging	p. 50
Ordinary kriging	p. 50
Basic features of kriging estimation	p. 51
Universal kriging (kriging with trend)	p. 56
Lognormal kriging	p. 56
Family of co-kriging models	p. 58
Kriging with linear regression	p. 58
Kriging with external drift	p. 58
Co-kriging	p. 59
Collocated co-kriging	p. 60
Co-kriging application example	p. 61
Probability mapping with indicator kriging	p. 64
Indicator coding	p. 64
Indicator kriging	p. 66
Indicator kriging applications	p. 69
Indicator kriging for [superscript 241]Am analysis	p. 69
Indicator kriging for aquifer layer zonation	p. 71
Indicator kriging for localization of crab crowds	p. 74
Description of spatial uncertainty with conditional stochastic simulations	p. 76
Simulation vs. estimation	p. 76
Stochastic simulation algorithms	p. 77
Sequential Gaussian simulation	p. 81
Sequential indicator simulations	p. 84
Co-simulations of correlated variables	p. 88
References	p. 92
Spatial Data Analysis and Mapping Using Machine Learning Algorithms	p. 95
Introduction	p. 95
Machine learning: an overview	p. 96
The three learning problems	p. 96
Approaches to learning from data	p. 100
Feature selection	p. 101
Model selection	p. 103
Dealing with uncertainties	p. 107
Nearest neighbor methods	p. 108
Artificial neural network algorithms	p. 109
Multi-layer perceptron neural network	p. 109
General Regression Neural Networks	p. 119
Probabilistic Neural Networks	p. 122
Self-organizing (Kohonen) maps	p. 124
Statistical learning theory for spatial data: concepts and examples	p. 131
VC dimension and structural risk minimization	p. 131
Kernels	p. 132
Support vector machines	p. 133
Support vector regression	p. 137
Unsupervised techniques	p. 141
Clustering	p. 142
Nonlinear dimensionality reduction	p. 144
Conclusion	p. 146
References	p. 146
Advanced Mapping of Environmental Spatial Data: Case Studies	p. 149
Introduction	p. 149
Air temperature modeling with machine learning algorithms and geostatistics	p. 150
Mean monthly temperature	p. 151
Data description	p. 151
Variography	p. 152
Step-by-step modeling using a neural network	p. 153
Overfitting and undertraining	p. 154
Mean monthly air temperature prediction mapping	p. 156
Instant temperatures with regionalized linear dependencies	p. 159
The Fohn phenomenon	p. 159
Modeling of instant air temperature influenced by Fohn	p. 160
Instant temperatures with nonlinear dependencies	p. 163
Temperature inversion phenomenon	p. 163
Terrain feature extraction using Support Vector Machines	p. 164
Temperature inversion modeling with MLP	p. 165
Modeling of precipitation with machine learning and geostatistics	p. 168
Mean monthly precipitation	p. 169
Data description	p. 169
Precipitation modeling with MLP	p. 171
Modeling daily precipitation with MLP	p. 173
Data description	p. 173
Practical issues of MLP modeling	p. 174
The use of elevation and analysis of the results	p. 177
Hybrid models: NNRK and NNRS	p. 179
Neural network residual kriging	p. 179
Neural network residual simulations	p. 182
Conclusions	p. 184
Automatic mapping and classification of spatial data using machine learning	p. 185
k-nearest neighbor algorithm	p. 185
Number of neighbors with cross-validation	p. 187
Automatic mapping of spatial data	p. 187
KNN modeling	p. 188
GRNN modeling	p. 190
Automatic classification of spatial data	p. 192
KNN classification	p. 193
PNN classification	p. 194
Indicator kriging classification	p. 197
Automatic mapping - conclusions	p. 199
Self-organizing maps for spatial data - case studies	p. 200
SOM analysis of sediment contamination	p. 200
Mapping of socio-economic data with SOM	p. 204
Indicator kriging and sequential Gaussian simulations for probability mapping. Indoor radon case study	p. 209
Indoor radon measurements	p. 209
Probability mapping	p. 211
Exploratory data analysis	p. 212
Radon data variography	p. 216
Variogram for indicators	p. 216
Variogram for Nscores	p. 217
Neighborhood parameters	p. 218
Prediction and probability maps	p. 219
Probability maps with IK	p. 219
Probability maps with SGS	p. 220
Analysis and validation of results	p. 221
Influence of the simulation net and the number of neighbors	p. 221
Decision maps and validation of results	p. 222
Conclusions	p. 225
Natural hazards forecasting with support vector machines - case study: snow avalanches	p. 225
Decision support systems for natural hazards	p. 227
Reminder on support vector machines	p. 228
Probabilistic interpretation of SVM	p. 229
Implementing an SVM for avalanche forecasting	p. 230
Temporal forecasts	p. 230
Feature selection	p. 231
Training the SVM classifier	p. 232
Adapting SVM forecasts for decision support	p. 233
Extending the SVM to spatial avalanche predictions	p. 237
Data preparation	p. 237
Spatial avalanche forecasting	p. 239
Conclusions	p. 241
Conclusion	p. 241
References	p. 242
Bayesian Maximum Entropy - BME	p. 247
Conceptual framework	p. 247
Technical review of BME	p. 251
The spatiotemporal continuum	p. 251
Separable metric structures	p. 253
Composite metric structures	p. 255
Fractal metric structures	p. 256
Spatiotemporal random field theory	p. 257
Pragmatic S/TRF tools	p. 258
Space-time lag dependence: ordinary S/TRF	p. 260
Fractal S/TRF	p. 262
Space-time heterogenous dependence: generalized S/TRF	p. 264
About BME	p. 267
The fundamental equations	p. 267
A methodological outline	p. 273
Implementation of BME: the SEKS-GUI	p. 275
A brief review of applications	p. 281
Earth and atmospheric sciences	p. 282
Health, human exposure and epidemiology	p. 291
References	p. 299
List of Authors	p. 307
Index	p. 309
Table of Contents provided by Ingram. All Rights Reserved.

Amazon no longer offers textbook rentals. We do!

Advanced Mapping of Environmental Data

Advanced Mapping of Environmental Data

9781848210608

1848210604

Summary

Author Biography

Table of Contents

Supplemental Materials

Write a Review