Analysis and Modelling of Spatial Environmental Data

Analysis and Modelling of Spatial Environment Data presents traditional geostatistics methods for variography and spatial predictions, approaches to conditional stochastic simulation and local probability distribution function estimation, and select aspects of Geographical Information Systems. This authoritative reference describes real case studies using Geostat Office software tools under MS Windows and includes timely chapters on monitoring network analysis, artificial neural networks, support vector machines, and simulations. The book also provides tools and methods to solve challenges in prediction, characterization, optimization, and density estimation.

Analysis and Modelling of Spatial Environmental Data presents traditional geostatistics methods for variography and spatial predictions, approaches to conditional stochastic simulation and local probability distribution function estimation, and select aspects of Geographical Information Systems. It includes real case studies using Geostat Office software tools under MS Windows and also provides tools and methods to solve problems in prediction, characterization, optimization, and density estimation. The author describes fundamental methodological aspects of the analysis and modelling of spatially distributed data and the application by way of a specific and user-friendly software, GSO Geostat Office.

Presenting complete coverage of geostatistics and machine learning algorithms, the book explores the relationships and complementary nature of both approaches and illustrates them with environmental and pollution data. The book includes introductory chapters on machine learning, artificial neural networks of different architectures, and support vector machines algorithms. Several chapters cover monitoring network analysis, artificial neural networks, support vector machines, and simulations. The book demonstrates thepromising results of the application of SVM to environmental and pollution data.

INTRODUCTION TO ENVIRONMENTAL DATA ANALYSIS AND MODELLING
Introduction
Environmental Decision Support Systems and Prediction Mapping
Presentation of the Case Studies
Spatial Data Analysis with Geostat Office

EXPLORATORY SPATIAL DATA ANALYSIS, ANALYSIS OF MONITORING NETWORKS, AND DECLUSTERING
Introduction
Exploratory Data Analysis
Transformation of Data
Quantitative Description of Monitoring Networks
Declustering
Geostat Office: Monitoring Networks and Declustering
Conclusions

SPATIAL DATA ANALYSIS: DETERMINISTIC INTERPOLATIONS
Introduction
Validation Tools
Models of Deterministic Interpolations
Deterministic Interpolations with Geostat Office
Conclusions

INTRODUCTION TO GEOSTATISTICS: VARIOGRAPHY
Geostatistics: Theory of Regionalized Variables
Geostatistics: Basic Hypothesis
Variography
Coregionilzation Models
Exploratory Variography in Practice
Variography with Geostat Office
Comments and Interpretations
Conclusion

GEOSTATISTICAL SPATIAL PREDICTIONS
Introduction
Family of Kriging Models
Kriging Predictions with Geostat Office
Spatial Co-Estimations. Co-Kriging Models
Co-Kriging Predictions. A Case Study
Conclusions

ESTIMATION OF LOCAL PROBABILITY DENSITY FUNCTIONS
Introduction
Indicator Kriging
Indicator Kriging. A Case Study
Conclusions and Comments on Indicator Kriging

CONDITIONAL STOCHASTIC SIMULATIONS
Introduction
Models of Spatial Simulations
Conditional Stochastic Simulations. Case Studies
Review of Other Simulation Models
Comments and Discussions
Check of the Simulations
Conclusions
Annex 1. Conditioning Simulations with Conditional Kriging
Annex 2. Non-Conditional Simulations of Stationary Isotropic Multiglasseian Random Functions
Annex 3. Sequential Guassian Simulations with Geostat Office

ARTIFICIAL NEURAL NETWORKS AND SPATIAL DATA ANALYSIS
Introduction
Basics of ANN
Artificial Neural Networks Learning
Multilayer Feedforward Neural Networks
General Regression Neural Networks (GRNS)
Neural Network Residual Kriging Model (NNRK)
Conclusions

SUPPORT VECTOR MACHINES FOR ENVIRONMENTAL SPATIAL DATA
Introduction
Support Vector Machines Classification
Spatial Data Mapping with Support Vector Regression
A Case Study
Evaluation of SVM Binary Spatial Classification with Nonparametric Conditional Stochastic Simulations
GeoSVM Computer Program
Conclusions

GEOGRAPHICAL INFORMATION SYSTEMS AND SPATIAL DATA ANALYSIS
Introduction
Contributing Disciplines and Technologies
GIS Technology
GIS Functionality
Basic Objects of GIS
Representation of the GIS Object
GIS Layers
Map Projections
Geostat Office and GIS
Conclusions

CONCLUSIONS

GLOSSARIES
Statistics, Geostatistics, Fractals
Machine Learning
References