气候变化领域集成服务门户(CCPortal): A Bayesian network model for prediction and analysis of possible forest fire causes

CCPortal

DOI	10.1016/j.foreco.2019.117723
	A Bayesian network model for prediction and analysis of possible forest fire causes
	Sevinc V.; Kucuk O.; Goltas M.
发表日期	2020
ISSN	0378-1127
卷号	457
英文摘要	Possible causes of a forest fire ignition could be human-caused (arson, smoking, hunting, picnic fire, shepherd fire, stubble burning) or natural-caused (lightning strikes, power lines). Temperature, relative humidity, tree species, distance from road, wind speed, distance from agricultural land, amount of burnt area, month and distance from settlement are the risk factors that may affect the occurrence of forest fires. This study introduces the use of Bayesian network model to predict the possible forest fire causes, as well as to perform an analysis of the multilateral interactive relations among them. The study was conducted in Mugla Regional Directorate of Forestry area located in the southwest of Turkey. The fire data, which were recorded between 2008 and 2018 in the area, were provided by General Directorate of Forestry. In this study, after applying some different structural learning algorithms, a Bayesian network, which is built on the nodes relative humidity, temperature, wind speed, month, distance from settlement, amount of burnt area, distance from agricultural land, distance from road and tree species, was estimated. The model showed that month is the first and temperature is the second most effective factor on the forest fire ignitions. The Bayesian network model approach adopted in this study could also be used with data obtained from different areas having different sizes. © 2019 Elsevier B.V.
英文关键词	Bayesian networks; Forest fires; Sensitivity analysis; Structural learning
语种	英语
scopus关键词	Deforestation; Fire hazards; Fires; Forecasting; Learning algorithms; Roads and streets; Sensitivity analysis; Timber; Wind; Agricultural land; Bayesian network models; Different sizes; Forest fires; Interactive relation; Lightning strikes; Prediction and analysis; Structural learning; Bayesian networks; algorithm; Bayesian analysis; biomass burning; forest fire; machine learning; numerical model; prediction; sensitivity analysis; Area; Deforestation; Distance; Forecasts; Forest Fires; Temperature; Wind; Mugla; Turkey
来源期刊	Forest Ecology and Management
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/155584
作者单位	Mugla Sitki Kocman University, Faculty of Science, Department of Statistics, Kotekli Kampusu, Mugla, Turkey; Kastamonu University, Faculty of Forestry, Department of Forest Engineering, Kastamonu, Turkey; Istanbul University-Cerrahpasa, Faculty of Forestry, Department of Forest Engineering, Istanbul, Turkey
推荐引用方式 GB/T 7714	Sevinc V.,Kucuk O.,Goltas M.. A Bayesian network model for prediction and analysis of possible forest fire causes[J],2020,457.
APA	Sevinc V.,Kucuk O.,&Goltas M..(2020).A Bayesian network model for prediction and analysis of possible forest fire causes.Forest Ecology and Management,457.
MLA	Sevinc V.,et al."A Bayesian network model for prediction and analysis of possible forest fire causes".Forest Ecology and Management 457(2020).