Germán Bianchini

S 2 F 2 M : statistical system for forest fire management

One of the most serious problems in wildland fire simulators is the lack of precision for input parameters (moisture content, wind speed, wind direction, etc.). In this paper, a statistical method based on a factorial experiment is presented. This method evaluates a high number of parameter combinations instead of considering a single value for each parameter, in order to obtain a prediction which is closer to reality. The proposed methodology has been implemented in a parallel scheme and tested in a Linux cluster using MPI.

Improved prediction methods for wildfires using high performance computing: a comparison

Recently, dry and hot seasons have seriously increased the risk of forest fire in the Mediterranean area. Wildland simulators, used to predict fire behavior, can give erroneous forecasts due to lack of precision for certain dynamic input parameters. Developing methods to avoid such parameter problems can improve significantly the fire behavior prediction. In this paper, two methods are evaluated, involving statistical and uncertainty schemes. In each one, the number of simulations that must be carried out is enormous and it is necessary to apply high-performance computing techniques to make the methodology feasible. These techniques have been implemented in parallel schemes and tested in Linux cluster using MPI.

Evolutionary-Statistical System: A parallel method for improving forest fire spread prediction

Abstract Fighting fires is a very risky job, where loss of life is a real possibility. Proper training is essential. Several firemen academies offer courses and programs whose goal is to enhance the ability of fire and emergency services to deal more effectively with fire. Among the tools that can be found in the training process are fire simulators, which are used both for training and for the prediction of forest fires. In many cases, the used simulators are based on models that present a series of limitations related to the need for a large number of input parameters. Moreover, such parameters often have some degree of uncertainty due to the impossibility of measuring all of them in real time. Therefore, they have to be estimated from indirect measurements, which negatively impacts on the output of the model. In this paper we present a method which combines Statistical Analysis with Parallel Evolutionary Algorithms to improve the quality of the model output.

Between classical and ideal: enhancing wildland fire prediction using cluster computing

One of the challenges still open to wildland fire simulators is the capacity of working under real-time constrains with the aim of providing fire spread predictions that could be useful in fire mitigation interventions. We propose going one step beyond the classical wildland fire prediction by linking evolutionary optimization strategies to the traditional scheme with the aim of emulating an “ideal” fire propagation model as much as possible. In order to accelerate the fire prediction, this enhanced prediction scheme has been developed in a fashion on a Linux cluster using MPI. Furthermore, a sensitivity analysis has been carried out to determine the input parameters that we can fix to their typical values in order to reduce the search-space involved in the optimization process and, therefore, accelerates the whole prediction strategy.

Comparative Analysis of Performance and Quality of Prediction Between ESS and ESS-IM

Wildfires cause major damage and losses around the world. Such damages range from human and economical losses to environmental ones. Therefore, having models to predict their behavior can be a key element in the process of firefighting. In this paper, we present a comparative study between two methods we have developed. Both methods use Statistical Analysis, Parallel Evolutionary Algorithms and High Performance Computing, respectively named: Evolutionary-Statistical System (ESS) and Evolutionary-Statistical System with Island Model (ESS-IM). In this study, we have compared these two methods in terms of quality of prediction and performance in the parallel environment.

Improving Wildland Fire Prediction on MPI Clusters

One of the challenges still open to wildland fire simulators is the capacity of working under real- time constrains with the aim of providing fire spread predictions that could be useful in fire mitigation interventions. In this paper, a parallel optimization framework for improving wildland fire prediction is applied to a real laboratory fire. The proposed prediction methodology has been tested on a Linux cluster using MPI.

Calibration of the parameters of ESS system for Forest Fire prediction

Forest fires are a major risk factor with strong impact at ecological-environmental and socio-economical levels, reasons why their study and modeling is very important. However, the models frequently have a certain level of uncertainty in some input parameters given that they must be approximated or estimated, as a consequence of diverse difficulties to accurately measure the conditions of the phenomenon in real time. This has resulted in the development of several methods of uncertainty reduction, whose trade-off between accuracy and complexity can vary significantly. The system ESS (Evolutionary-Statistical System) is a method whose aim is to reduce the uncertainty, by combining Statistical Analysis, High Performance Computing (HPC) and Parallel Evolutionary Algorithms (PEA). The PEA use several parameters that require adjustment and that determine the quality of their use. The calibration of the parameters is a crucial task for reaching a good performance. This paper presents an empirical study of the parameters tuning to evaluate the effectiveness of different configurations and the impact on their use in the Forest Fires prediction.

Graduate students learning strategies through research collaboration

It is already known that the learning process can be accelerated with the mixture of theoretical classes and experimental work. This paper describes an interesting experiment with that combination in the teaching of computer architecture for Ph.D. students in collaboration with a researcher in a real design investigation. As the work progressed, a simple cyclical methodology arose as reference for future works.

A comparative study of evolutionary statistical methods for uncertainty reduction in forest fire propagation prediction

Abstract Predicting the propagation of forest fires is a crucial point to mitigate their effects. Therefore, several computational tools or simulators have been developed to predict the fire propagation. Such tools consider the scenario (topography, vegetation types, fire front situation), and the particular conditions where the fire is evolving (vegetation conditions, meteorological conditions) to predict the fire propagation. However, these parameters are usually difficult to measure or estimate precisely, and there is a high degree of uncertainty in many of them. This uncertainty provokes a certain lack of accuracy in the predictions with the consequent risks. So, it is necessary to apply methods to reduce the uncertainty in the input parameters. This work presents a comparison of ESSIM-EA and ESSIM-DE: two methods to reduce the uncertainty in the input parameters. These methods combine Evolutionary Algorithms, Parallelism and Statistical Analysis to improve the propagation prediction.

Hierarchical parallel model for improving performance on differential evolution: Hierarchical parallel model for improving performance on differential evolution

This paper presents a parallel distributed model for the Differential Evolution algorithm. The proposed model, Hierarchical Island‐Based Model for Differential Evolution, follows a double‐hierarchy master‐worker scheme and offers two parallelism levels. In this proposal, the processes are associated with certain cooperation hierarchy, allowing them to explore in a more comprehensive way the search space of the problem at hand. A comparative study with other algorithms from the state of art is also presented. The results show that Hierachical Island‐Based Model for Differential Evolution is a flexible model and achieves good performance in terms of results quality and computing time.