Spatio-temporal Forest fire monitoring using spatial-statistical and Geo-spatial analysis of factors determining forest fire in Margalla Hills, Islamabad, Pakistan

The spatio-temporal changes in burnt area were identified using Landsat satellite data and modeling was used to predict the fire ignition and size distribution daily and yearly. Forest fire ignition models are effective ways to predict and classify drivers for ignition probability across broad areas. The aim was therefore to compare the predictive output and significance of predictable ignition and spatial patterns of three inflammation-distribution model types; one parametric, a statistical model and two machine-learning algorithms: Maximum entropy (Maxent) and Random Forests (RF). We parameterized the models for Margalla Hills, the National Park, Islamabad, Pakistan using 30 years of ignition, socio-economic, and environmental data. The best predictors of forest fire sites in all models were human population and development variables (although variable rankings were slightly differentiated), as well as elevation. However, despite similar model performance and variables, the map of ignition probabilities generated by Maxent was markedly different from those of the two other models.

Related Published papers:

1. Tariq, A.; Shu, H.; Siddiqui, S.; Munir, I.; Sharifi, A.; Li, Q.; Lu, L. Spatio-temporal analysis of forest fire events in the Margalla Hills, Islamabad, Pakistan using socio-economic and environmental variable data with machine learning methods. For. Res. 2021, 13, 12, doi: https://doi.org/10.1007/s11676-021-01354-4 (Journal of Forestry Research)
2. Tariq, A*.; Shu, H.; Saddiqui, S.; Mousa, B.G.; Munir, I.; Nasri, A.; Waqas, H.; Baqa, M.F.; Lu, L. Forest fire Monitoring using spatial-statistical and Geo-spatial analysis of factors determining Forest fire in Margalla Hills, Islamabad, Pakistan. Geomatics, Nat. Hazards Risk 2021, 12, 1212–1233, doi: https://doi.org/10.1080/19475705.2021.1920477  (Geomatics, Natural Hazards and Risks).