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

• Published in: Journal of forestry research Vol. 33; no. 1; pp. 183 - 194
• Main Authors: Tariq, Aqil, Shu, Hong, Siddiqui, Saima, Munir, Iqra, Sharifi, Alireza, Li, Qingting, Lu, Linlin
• Format: Journal Article
• Language: English
• Published: Singapore Springer Singapore 01.02.2022; Springer; Springer Nature B.V; State Key Laboratory of Information,Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,Hubei,People's Republic of China%Department of Geography,University of the Punjab,Lahore,Punjab,Pakistan%Department of Surveying Engineering,Faculty of Civil Engineering,Shahid Rajaee Teacher Training University,Tehran,Iran%Airborne Remote Sensing Center,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,People's Republic of China%Key Laboratory of Digital Earth Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,People's Republic of China
• Subjects: altitude; Analysis; Biomedical and Life Sciences; Economics; Entropy; Environmental conditions; fire history; Forest & brush fires; Forest fires; forest types; Forestry; Hills; Human acts; Human behavior; humans; humidity; landscapes; Learning algorithms; Life Sciences; Machine learning; Maximum entropy; Methods; Original Paper; Pakistan; Population density; risk; Risk reduction; Risk taking; Social factors; Socioeconomic factors; Socioeconomics; Urban areas; Pakistan; GIS; Random forest machine learning; Maxent; Disaster risk reduction; Multi-temporal analysis; Forest fires
• ISSN: 1007-662X; 1993-0607
• DOI: 10.1007/s11676-021-01354-4

Most forest fires in the Margalla Hills are related to human activities and socioeconomic factors are essential to assess their likelihood of occurrence. This 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 fires. Maximum 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 Hills. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were used to compare the models. We studied the fire history from 1990 to 2019 to establish the relationship between the probability of forest fire and environmental and socioeconomic changes. Using Maxent, the AUC fire probability values for the 1999s, 2009s, and 2019s were 0.532, 0.569, and 0.518, respectively; using RF, they were 0.782, 0.825, and 0.789, respectively. Fires were mainly distributed in urban areas and their probability of occurrence was related to accessibility and human behaviour/activity. AUC principles for validation were greater in the random forest models than in the Maxent models. Our results can be used to establish preventive measures to reduce risks of forest fires by considering socio-economic and environmental conditions.