A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China |
| |
Authors: | Haoyuan Hong Seyed Amir Naghibi Mostafa Moradi Dashtpagerdi Hamid Reza Pourghasemi Wei Chen |
| |
Affiliation: | 1.College of Geographic Sciences,Nanjing Normal University,Nanjing,China;2.Jiangsu Center for Collaborative Innovation in Geographic Information Resource Development and Application,Nanjing,China;3.Young Researchers and Elite Club, Mashhad Branch,Islamic Azad University,Mashhad,Iran;4.Department of Watershed Management Engineering, College of Natural Resources,Tarbiat Modares University,Noor,Iran;5.Department of Natural Resources and Environmental Engineering, College of Agriculture,Shiraz University,Shiraz,Iran;6.School of Geology and Environment,Xi’an University of Science and Technology,Xi’an,China |
| |
Abstract: | Forest fire is known as an important natural hazard in many countries which causes financial damages and human losses; thus, it is necessary to investigate different aspects of this phenomenon. In this study, performance of four models of linear and quadratic discriminant analysis (LDA and QDA), frequency ratio (FR), and weights-of-evidence (WofE) was investigated to model forest fire susceptibility in the Yihuang area, China. For this purpose, firstly, a forest fire locations map was prepared implementing MODIS satellite images and field surveys. Then, it was classified into two groups including training (70%) and validation (30%) by a random algorithm. In addition, 13 forest fire effective factors were prepared and used such as slope degree, slope aspect, altitude, Topographic Wetness Index (TWI), plan curvature, land use, Normalized Difference Vegetation Index (NDVI), annual rainfall, distance from roads and rivers, wind effect, annual temperature, and soil texture. Using the training dataset and effective factors, LDA, QDA, FR, and WofE models were applied and forest fire susceptibility maps were prepared. Finally, area under the curve (AUC) of receiver operating characteristics (ROC) was implemented for investigating the performance of the models. The results depicted that WofE had the best performance (AUC = 82.2%), followed by FR (AUC = 80.9%), QDA (AUC = 78.3%), and LDA (AUC = 78%), respectively. The results of this study showed the high contribution of altitude, slope degree, and temperature. On the other hand, it was seen that slope aspect and soil had the lowest importance in forest fire susceptibility mapping. From the AUC results, it can be concluded that FR, WofE, LDA, and QDA had acceptable performance and could be used for forest fire susceptibility mapping at the regional scale. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|