Spatio-temporal analysis of forest fire events in the Margalla Hills,Islamabad,Pakistan using socio-economic and environmental variable data with machine learning methods

作     者：Aqil Tariq Hong Shu Saima Siddiqui Iqra Munir Alireza Sharifi Qingting Li Linlin Lu 

作者机构：State Key Laboratory of InformationEngineering in SurveyingMapping and Remote SensingWuhan UniversityWuhan 430079HubeiPeople’s Republic of China Department of GeographyUniversity of the PunjabLahorePunjabPakistan Department of Surveying EngineeringFaculty of Civil EngineeringShahid Rajaee Teacher Training UniversityTehranIran Airborne Remote Sensing CenterAerospace Information Research InstituteChinese Academy of SciencesBeijing 100094People’s Republic of China Key Laboratory of Digital Earth ScienceAerospace Information Research InstituteChinese Academy of SciencesBeijing 100094People’s Republic of China 

出 版 物：《Journal of Forestry Research》 (林业研究（英文版）)

年 卷 期：2022年第33卷第1期

页      面：183-194页

核心收录：

学科分类：08[工学] 0838[工学-公安技术] 

基　　金：supported by the National Key Research and Development Program of China(Grant No.2019YFE0127700) 

主　　题：Forest fires Maxent GIS Disaster risk reduction Random forest machine learning Multi-temporal analysis 

摘      要：Most forest fires in the Margalla Hills are related to human activities and socioeconomic factors are essential to assess their likelihood of *** study considers both environmental(altitude,precipitation,forest type,terrain and humidity index)and socioeconomic(population density,distance from roads and urban areas)factors to analyze how human behavior affects the risk of forest *** entropy(Maxent)modelling and random forest(RF)machine learning methods were used to predict the probability and spatial diffusion patterns of forest fires in the Margalla *** receiver operating characteristic(ROC)curve and the area under the ROC curve(AUC)were used to compare the *** studied the fire history from 1990 to 2019 to establish the relationship between the probability of forest fire and environmental and socioeconomic *** Maxent,the AUC fire probability values for the 1999 s,2009 s,and 2019 s were 0.532,0.569,and 0.518,respectively;using RF,they were 0.782,0.825,and 0.789,*** were mainly distributed in urban areas and their probability of occurrence was related to accessibility and human behaviour/*** principles for validation were greater in the random forest models than in the Maxent *** results can be used to establish preventive measures to reduce risks of forest fires by considering socio-economic and environmental conditions.