This title, developed from seminars given at two workshops at the Faculty of Geosciences and Environment, University of Lausanne, Switzerland in 2005 and 2006, brings together three topics normally covered separately: geostatistical methods and models, machine learning algorithms and the Bayesian maximum entropy approach. An introduction to environmental data mapping is provided before these areas, their features and applications are discussed in more depth.
The approach is designed to assist the reader in easily expanding their knowledge of the fields covered, and will be useful for both students and professionals involved in environmental data analysis and mapping.
1. Advanced mapping of environmental data. Introduction, M Kanevski.
2. Environmental monitoring networks characterization and clustering, D Tuia and M Kanevski.
3. Geostatistics: spatial predictions and simulations, E Savelieva, V Demyanov and M Maignan.
4. Spatial data analysis and mapping using machine learning algorithms, F Ratle, A Pozdnoukhov, V Demyanov, V Timonin and E Savelieva.
5. Advanced mapping of environmental spatial data. Case studies, L Foresti, A Pozdnoukhov, M Kanevski, V Timonin, E Savelieva, C Kaiser, R Tapia and R Purves.
6. Bayesian Maximum Entropy – BME, G Christakos.
Mikhail Kanevski is a Professor at the Institute of Geomatics and Analysis of Risk (IGAR), University of Lausanne, Switzerland.