Mikhail Kanevski

The book presents the state of the art in machine learning algorithms (artificial neural networks of different architectures, support vector machines, etc.) as applied to the classification and mapping of spatially distributed environmental data. Basic geostatistical algorithms are presented as well. New trends in machine learning and their application to spatial data are given, and real case studies based on environmental and pollution data are carried out. The book provides a CD-ROM with the Machine Learning Office software, including sample sets of data, that will allow both students and researchers to put the concepts rapidly to practice.

This book discusses machine learning algorithms, such as artificial neural networks of different architectures, statistical learning theory, and Support Vector Machines used for the classification and mapping of spatially distributed data. It presents basic geostatistical algorithms as well. The authors describe new trends in machine learning and their application to spatial data. The text also includes real case studies based on environmental and pollution data. It includes a CD-ROM with software that will allow both students and researchers to put the concepts to practice.

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.