A Data-Driven Approach to Assess Large Fire Size Generation in Greece. Mitsopoulos, I. & Mallinis, G. 88(3):1591–1607. ![A Data-Driven Approach to Assess Large Fire Size Generation in Greece [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Identifying factors and drivers which control large fire size generation is critical for planning fire management activities. This study attempts to determine the role of fire suppression tactics and behavior, weather, topography and landscape features on two different datasets of large fire size (500-1000 ha) and very large fire size ($>$1000 ha) compared to two datasets of small fire size ($<$50 ha) which occurred in Greece, during the period 1984-2009. In this context, we used a logistic regression (LR) analysis and two machine learning algorithms: random forest (RF) and boosting classification trees (BCT). The models comparison was based on the area under the receiver operating characteristic curve and the observed overall accuracy. The comparison indicated that RF had greater ability than LR and BCT to predict large fire generation. Results from the RF classifier algorithm showed that large fire generation mainly depended on fire suppression tactics and the prevailing weather conditions. This improved understanding of the factors which drive fire ignitions to turn into large fire sizes will provide the opportunity for land and forest managers to increase fire awareness and the development of concrete initiatives for successful fire management.
@article{mitsopoulosDatadrivenApproachAssess2017,
title = {A Data-Driven Approach to Assess Large Fire Size Generation in {{Greece}}},
author = {Mitsopoulos, Ioannis and Mallinis, Giorgos},
date = {2017},
journaltitle = {Natural Hazards},
volume = {88},
pages = {1591--1607},
issn = {1573-0840},
doi = {10.1007/s11069-017-2934-z},
url = {https://doi.org/10.1007/s11069-017-2934-z},
abstract = {Identifying factors and drivers which control large fire size generation is critical for planning fire management activities. This study attempts to determine the role of fire suppression tactics and behavior, weather, topography and landscape features on two different datasets of large fire size (500-1000 ha) and very large fire size ({$>$}1000 ha) compared to two datasets of small fire size ({$<$}50 ha) which occurred in Greece, during the period 1984-2009. In this context, we used a logistic regression (LR) analysis and two machine learning algorithms: random forest (RF) and boosting classification trees (BCT). The models comparison was based on the area under the receiver operating characteristic curve and the observed overall accuracy. The comparison indicated that RF had greater ability than LR and BCT to predict large fire generation. Results from the RF classifier algorithm showed that large fire generation mainly depended on fire suppression tactics and the prevailing weather conditions. This improved understanding of the factors which drive fire ignitions to turn into large fire sizes will provide the opportunity for land and forest managers to increase fire awareness and the development of concrete initiatives for successful fire management.},
keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-14570683,burnt-area,classification-trees,clc,evapotranspiration,forest-resources,greece,land-cover,logistic-regression,machine-learning,topographic-position-index,topographic-wetness-index,wildfires,wildland-urban-interface},
number = {3}
}
Downloads: 0
{"_id":"DapFWk4TmQNxmWYDp","bibbaseid":"mitsopoulos-mallinis-adatadrivenapproachtoassesslargefiresizegenerationingreece","authorIDs":[],"author_short":["Mitsopoulos, I.","Mallinis, G."],"bibdata":{"bibtype":"article","type":"article","title":"A Data-Driven Approach to Assess Large Fire Size Generation in Greece","author":[{"propositions":[],"lastnames":["Mitsopoulos"],"firstnames":["Ioannis"],"suffixes":[]},{"propositions":[],"lastnames":["Mallinis"],"firstnames":["Giorgos"],"suffixes":[]}],"date":"2017","journaltitle":"Natural Hazards","volume":"88","pages":"1591–1607","issn":"1573-0840","doi":"10.1007/s11069-017-2934-z","url":"https://doi.org/10.1007/s11069-017-2934-z","abstract":"Identifying factors and drivers which control large fire size generation is critical for planning fire management activities. This study attempts to determine the role of fire suppression tactics and behavior, weather, topography and landscape features on two different datasets of large fire size (500-1000 ha) and very large fire size ($>$1000 ha) compared to two datasets of small fire size ($<$50 ha) which occurred in Greece, during the period 1984-2009. In this context, we used a logistic regression (LR) analysis and two machine learning algorithms: random forest (RF) and boosting classification trees (BCT). The models comparison was based on the area under the receiver operating characteristic curve and the observed overall accuracy. The comparison indicated that RF had greater ability than LR and BCT to predict large fire generation. Results from the RF classifier algorithm showed that large fire generation mainly depended on fire suppression tactics and the prevailing weather conditions. This improved understanding of the factors which drive fire ignitions to turn into large fire sizes will provide the opportunity for land and forest managers to increase fire awareness and the development of concrete initiatives for successful fire management.","keywords":"*imported-from-citeulike-INRMM,~INRMM-MiD:c-14570683,burnt-area,classification-trees,clc,evapotranspiration,forest-resources,greece,land-cover,logistic-regression,machine-learning,topographic-position-index,topographic-wetness-index,wildfires,wildland-urban-interface","number":"3","bibtex":"@article{mitsopoulosDatadrivenApproachAssess2017,\n title = {A Data-Driven Approach to Assess Large Fire Size Generation in {{Greece}}},\n author = {Mitsopoulos, Ioannis and Mallinis, Giorgos},\n date = {2017},\n journaltitle = {Natural Hazards},\n volume = {88},\n pages = {1591--1607},\n issn = {1573-0840},\n doi = {10.1007/s11069-017-2934-z},\n url = {https://doi.org/10.1007/s11069-017-2934-z},\n abstract = {Identifying factors and drivers which control large fire size generation is critical for planning fire management activities. This study attempts to determine the role of fire suppression tactics and behavior, weather, topography and landscape features on two different datasets of large fire size (500-1000 ha) and very large fire size ({$>$}1000 ha) compared to two datasets of small fire size ({$<$}50 ha) which occurred in Greece, during the period 1984-2009. In this context, we used a logistic regression (LR) analysis and two machine learning algorithms: random forest (RF) and boosting classification trees (BCT). The models comparison was based on the area under the receiver operating characteristic curve and the observed overall accuracy. The comparison indicated that RF had greater ability than LR and BCT to predict large fire generation. Results from the RF classifier algorithm showed that large fire generation mainly depended on fire suppression tactics and the prevailing weather conditions. This improved understanding of the factors which drive fire ignitions to turn into large fire sizes will provide the opportunity for land and forest managers to increase fire awareness and the development of concrete initiatives for successful fire management.},\n keywords = {*imported-from-citeulike-INRMM,~INRMM-MiD:c-14570683,burnt-area,classification-trees,clc,evapotranspiration,forest-resources,greece,land-cover,logistic-regression,machine-learning,topographic-position-index,topographic-wetness-index,wildfires,wildland-urban-interface},\n number = {3}\n}\n\n","author_short":["Mitsopoulos, I.","Mallinis, G."],"key":"mitsopoulosDatadrivenApproachAssess2017","id":"mitsopoulosDatadrivenApproachAssess2017","bibbaseid":"mitsopoulos-mallinis-adatadrivenapproachtoassesslargefiresizegenerationingreece","role":"author","urls":{"Paper":"https://doi.org/10.1007/s11069-017-2934-z"},"keyword":["*imported-from-citeulike-INRMM","~INRMM-MiD:c-14570683","burnt-area","classification-trees","clc","evapotranspiration","forest-resources","greece","land-cover","logistic-regression","machine-learning","topographic-position-index","topographic-wetness-index","wildfires","wildland-urban-interface"],"downloads":0},"bibtype":"article","biburl":"https://tmpfiles.org/dl/58794/INRMM.bib","creationDate":"2020-07-02T22:41:15.776Z","downloads":0,"keywords":["*imported-from-citeulike-inrmm","~inrmm-mid:c-14570683","burnt-area","classification-trees","clc","evapotranspiration","forest-resources","greece","land-cover","logistic-regression","machine-learning","topographic-position-index","topographic-wetness-index","wildfires","wildland-urban-interface"],"search_terms":["data","driven","approach","assess","large","fire","size","generation","greece","mitsopoulos","mallinis"],"title":"A Data-Driven Approach to Assess Large Fire Size Generation in Greece","year":null,"dataSources":["DXuKbcZTirdigFKPF"]}