We show how microscopic modelling techniques such as Cellular Automata linked with detailed geographical information systems (GIS) and meteorological data can be used to efficiently predict the evolution of fire fronts on mountainous and heterogeneous wild forest landscapes. In particular, we present a lattice-based dynamic model that includes various factors, ranging from landscape and earth statistics, attributes of vegetation and wind field data to the humidity of the fuel and the spotting transfer mechanism. We also attempt to model specific fire suppression tactics based on air tanker attacks utilising technical specifications as well as operational capabilities of the aircrafts. We use the detailed model to approximate the dynamics of a large-scale fire that broke out in a region on the west flank of the Greek National Park of Parnitha Mountain in June of 2007. The comparison between the simulation and the actual results showed that the proposed model predicts the fire-spread characteristics in an adequate manner. Finally, we discuss how such a detailed model can be exploited in order to design and develop, in a systematic way, fire risk management policies.
The popular radial basis function (RBF) neural network architecture and a new fast and efficient method for training such a network are used to model nonlinear dynamical multi-input multioutput (MIMO) discrete-time systems. The proposed training methodology is based on a fuzzy partition of the input space and combines self-organized and supervised learning. The algorithm is illustrated through the development of neural network models using simulated and experimental data. Results show that the methodology is much faster and produces more accurate models compared to the standard techniques used to train RBF networks. Another important advantage is that, for a given fuzzy partition of the input space, the proposed method is able to determine the proper network structure, without using a trial and error procedure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.