Mixed models and point processes. Statistical models for the prediction and prevention of wildfires

      Аннотация: This book presents different methodologies to model the occurrence of wildfires and evaluate how they are distributed in space and time. All the methods developed in this work are included in the theory of point processes and, in particular, they belong to the theory of point processes with marks. The book is structured in three main parts. First, there is an initial chapter where the theory on fires is introduced. Then, the second chapter describes the methodology used. Finally, the results are exposed in the third chapter. The methodology used through this book have been applied to the wildfires occurred in Catalonia during the period 1994-2011. The results may be useful in fire management decision-making and planning and so, may contribute to the prediction and prevention of wildfires.

Ключевые слова: Bayesian Inference, Mixed Models, Wildfires, Spatio-temporal point processes, Log-Gaussian Cox Processes, Spde, INLA