Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction

Forest fires prediction represents a great computational and mathematical challenge. The complexity lies both in the definition of mathematical models for describing the physical phenomenon and in the impossibility of measuring in real time all the parameters that determine the fire behaviour. ESSI...

Descripción completa

Detalles Bibliográficos
Autores principales: Tardivo, María, Caymes Scutari, Paola, Méndez Garabetti, Miguel, Bianchini, Germán
Formato: Artículo acceptedVersion
Lenguaje:Inglés
Publicado: 2023
Materias:
Forest fires ,Island model, Evolutionary Algorithms, Prediction, Differential Evolution, Parallelism
Acceso en línea:http://hdl.handle.net/20.500.12272/8074
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-8074
record_format dspace
spelling I68-R174-20.500.12272-80742023-06-21T16:38:19Z Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction Tardivo, María Caymes Scutari, Paola Méndez Garabetti, Miguel Bianchini, Germán Forest fires ,Island model, Evolutionary Algorithms, Prediction, Differential Evolution, Parallelism Forest fires prediction represents a great computational and mathematical challenge. The complexity lies both in the definition of mathematical models for describing the physical phenomenon and in the impossibility of measuring in real time all the parameters that determine the fire behaviour. ESSIM (Evolutionary Statistical System with Island Model) is an uncertainty reduction method that uses Statistic, High Performance Computing and Evolutionary Strategies in order to guide the search towards better solutions. ESSIM has been implemented with two different search strategies: the method ESSIM-EA uses Evolutionary Algorithms as optimization engine, whilst ESSIM-DE uses the Differential Evolution algorithm. ESSIM-EA has shown to obtain good quality of predictions, while ESSIM-DE obtains better response times. This article presents an alternative to improve the quality of solutions reached by ESSIM-DE, based on the analysis of the relationship between the evolutionary strategy convergence speed and the population distribution at the beginning of each prediction step. Universidad Tecnológica Nacional. Facultad Regional Mendoza; Argentina Peer Reviewed 2023-06-21T16:38:19Z 2023-06-21T16:38:19Z 2018-01-01 info:eu-repo/semantics/article acceptedVersion Computer Science http://hdl.handle.net/20.500.12272/8074 10.1007/978-3-319-75214-3_2 eng openAccess http://creativecommons.org/publicdomain/zero/1.0/ CC0 1.0 Universal Universidad Tecnológica Nacional. Facultad Regional Mendoza Atribución pdf Computer Science 790, 13-23. (2018)
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
topic Forest fires ,Island model, Evolutionary Algorithms, Prediction, Differential Evolution, Parallelism
spellingShingle Forest fires ,Island model, Evolutionary Algorithms, Prediction, Differential Evolution, Parallelism
Tardivo, María
Caymes Scutari, Paola
Méndez Garabetti, Miguel
Bianchini, Germán
Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
topic_facet Forest fires ,Island model, Evolutionary Algorithms, Prediction, Differential Evolution, Parallelism
description Forest fires prediction represents a great computational and mathematical challenge. The complexity lies both in the definition of mathematical models for describing the physical phenomenon and in the impossibility of measuring in real time all the parameters that determine the fire behaviour. ESSIM (Evolutionary Statistical System with Island Model) is an uncertainty reduction method that uses Statistic, High Performance Computing and Evolutionary Strategies in order to guide the search towards better solutions. ESSIM has been implemented with two different search strategies: the method ESSIM-EA uses Evolutionary Algorithms as optimization engine, whilst ESSIM-DE uses the Differential Evolution algorithm. ESSIM-EA has shown to obtain good quality of predictions, while ESSIM-DE obtains better response times. This article presents an alternative to improve the quality of solutions reached by ESSIM-DE, based on the analysis of the relationship between the evolutionary strategy convergence speed and the population distribution at the beginning of each prediction step.
format Artículo
acceptedVersion
author Tardivo, María
Caymes Scutari, Paola
Méndez Garabetti, Miguel
Bianchini, Germán
author_facet Tardivo, María
Caymes Scutari, Paola
Méndez Garabetti, Miguel
Bianchini, Germán
author_sort Tardivo, María
title Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
title_short Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
title_full Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
title_fullStr Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
title_full_unstemmed Optimization for an Uncertainty Reduction Method Applied to Forest Fires Spread Prediction
title_sort optimization for an uncertainty reduction method applied to forest fires spread prediction
publishDate 2023
url http://hdl.handle.net/20.500.12272/8074
work_keys_str_mv AT tardivomaria optimizationforanuncertaintyreductionmethodappliedtoforestfiresspreadprediction
AT caymesscutaripaola optimizationforanuncertaintyreductionmethodappliedtoforestfiresspreadprediction
AT mendezgarabettimiguel optimizationforanuncertaintyreductionmethodappliedtoforestfiresspreadprediction
AT bianchinigerman optimizationforanuncertaintyreductionmethodappliedtoforestfiresspreadprediction
_version_ 1769355078803652608

Ejemplares similares