## Machine Learning for Spatial Environmental Data: Theory, Applications, and SoftwareThis 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. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

LEARNING FROM GEOSPATIAL DATA | 1 |

11 Problems and important concepts of machine learning | 2 |

12 Machine learning algorithms for geospatial data | 20 |

13 Contents of the book Software description | 36 |

14 Short review of the literature | 47 |

EXPLORATORY SPATIAL DATA ANALYSIS PRESENTATION OF DATA AND CASE STUDIES | 53 |

22 Data preprocessing | 68 |

Variography | 70 |

ARTIFICIAL NEURAL NETWORKS | 127 |

42 Radial basis function neural networks | 172 |

43 General regression neural networks | 187 |

44 Probabilistic neural networks | 211 |

45 Selforganising maps | 218 |

46 Gaussian mixture models and mixture density network | 231 |

47 Conclusions | 244 |

SUPPORT VECTOR MACHINES AND KERNEL METHODS | 247 |

24 Presentation of data | 75 |

a benchmark model for regression and classification | 84 |

26 Conclusions to chapter 2 | 94 |

GEOSTATISTICS | 95 |

32 Geostatistical conditional simulations | 114 |

33 Spatial classification | 122 |

34 Software | 123 |

35 Conclusions | 126 |

52 Support vector classification | 253 |

53 Spatial data classification with SVM | 267 |

54 Support vector regression | 309 |

56 Advanced topics in kernel methods | 327 |

347 | |

373 | |

### Other editions - View all

### Common terms and phrases

altitude anisotropic applied approach artificial neural networks binary Chapter classification clustering complexity computed considered correlation corresponding cross-validation data analysis data samples data set decision function defined digital elevation model distribution environmental example exploratory geostatistical grid GRNN model high dimensional hyper-parameters important input space inversion k-NN Kanevski and Maignan kernel bandwidth kriging layer linear loss function machine learning machine learning algorithms matrix mean measurements methods minimization mixture density monitoring network multilayer perceptron neurons nonlinear optimal output overfitting parameters pattern points prediction intervals prediction mapping presented in Figure problem procedure provides RBF network realisations region residuals Sigma simulations soil types spatial data spatial predictions spatial structure statistical subsets support vector machines target temperature testing error training data training error training samples training set tuning unsupervised learning validation data values variables variance variogram variogram model variogram rose variography visualization weights wind speed