Methodology for Time Response and Quality Assessment in Natural Hazards Evolution Prediction

Student thesis: Doctoral thesis

Abstract

This thesis describes a methodology for time response and quality assessment in natural hazards evolution prediction. This work has been focused on the specific case of forest fires as an important and worrisome catastrophe, but it can easily be extrapolated to all other kinds of natural hazards. There exist many prediction frameworks based on the use of simulators of the evolution of the hazard. Given the increasing computing capabilities allowed by new computing advances such as multicore and manycore architectures, and even distributed-computing paradigms, such as Grid and Cloud Computing, the need arises to be able to properly exploit the computational power they offer. This goal is fulfilled by introducing the capability to assess in advance how the present constraints at the time of attending to an ongoing forest fire will affect the results obtained from them, both in terms of quality (accuracy) obtained and time needed to make a decision, and therefore being able to select the most suitable configuration of both the prediction strategy and computational resources to be used. As a consequence, the framework derived from the application of this methodology is not supposed to be a new Decision Support System (DSS) for fire departments and Civil Protection agencies, but a tool from which most of forest fire (and other kinds of natural hazards) DSSs could benefit notably. The problem has been tackled by means of characterizing the behavior of these two factors during the prediction process. For this purpose, a two-stage prediction framework is presented and considered as a suitable and powerful strategy to enhance the quality of the predictions. This methodology involves dealing with Artificial Intelligence techniques, such as Genetic Algorithms and Decision Trees and also relies on a strong statistical study from training databases, composed of the results of thousands of different simulations. The results obtained in this long-term research work are fully satisfactory, and give rise to several new challenges. Moreover, the flexibility offered by the methodology allows it to be applied to other kinds of emergency contexts, which turns it into an outstanding and very useful tool in fighting against these catastrophes.
Date of Award17 Jul 2012
Original languageEnglish
Awarding Institution
  • Universitat Autònoma de Barcelona (UAB)
SupervisorAna Cortes Fite (Director)

Cite this

'