.png){kind=icon}
.png){kind=icon}
Return
Wildfire susceptibility mapping using two empowered machine learning algorithms
.png){kind=icon}
PRE
AI
DOI：10.1007/s00477-022-02273-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the importance of the forest fire susceptibility zonation for proper management of this environmental hazard, this study presents two different hybrids of artificial neural network (ANN) for spatial analysis of forest fire in northern Iran. To this end, ant colony optimization (ACO) and biogeography-based optimization (BBO) evolutionary algorithms are synthesized with ANN to optimize its computational parameters. In this work, slope aspect, elevation, land use, wind speed, soil type, plan curvature, temperature, distance to river, distance from road, distance from village, slope degree, topographic wetness index, annual mean evaporation, annual mean rainfall, and normalized difference vegetation index are considered as the forest fire ignition factors. Notably, the frequency ratio model is used to demonstrate the spatial interaction between the forest fire and ignition factors. The findings showed that the BBO and ACO could improve the accuracy of the ANN from 81.3% to 84.0 and 83.9%, respectively. Moreover, the ranking results (obtained by applying mean square error, area under the curve, and mean absolute error indices) revealed the superiority of the BBO-ANN.
Keywords:
Metaheuristic optimization
Neural network
Forest fire susceptibility analysis
Remote sensing
Journal
IF:
3.6
Papers:
3.5K
Citations:
6.9K