摘要
为充分发挥统计学和机器学习模型在野火灾害易发性分析和评估中的优势,以森林资源丰富且深受野火灾害困扰的桂林市为研究区,分别从气候、地形、水文以及人文等方面选取16个评价因子。将信息量(IV)模型分别与逻辑回归(LR)、人工神经网络(ANN)、随机森林(RF)和极致梯度提升(XGBoost)4种机器学习(ML)模型相耦合,对桂林市野火灾害易发性进行评价分析。结果表明,IV-XGBoost模型的AUC和准确率分别为0.957和0.921,具有最佳的预测性能,能够有效评估野火灾害的易发性,并为当地野火灾害的防治提供有价值的参考。
In order to give full play to the advantages of statistics and machine learning model in the analysis and evaluation of wild-fire disaster susceptibility,Guilin,which is rich in forest re-sources and deeply troubled by wildfire disaster,was taken as the research area,and 16 evaluation factors were selected from the as-pects of climate,topography,hydrology and humanities.Based on the information value(IV)model,4 machine learning(ML)models,including logistic regression(LR),artificial neural net-work(ANN),random forest(RF),and extreme gradient boost-ing(XGBoost),were coupled to evaluate the susceptibility of wildfire hazards in Guilin City.The results indicate that the IV-XGBoost model achieved an AUC of 0.957 and an accuracy of 0.921,demonstrating its superior predictive performance.It can effectively assess the susceptibility of wildfire disasters and pro-vide valuable insights for local wildfire prevention and control.
作者
岳韦霆
任超
梁月吉
Yue Weiting;Ren Chao;Liang Yueji(College of Geomatics and Geoinformation,Guilin Uni-versity of Technology,Guangxi Guilin 541006,China;Guangxi Key Laboratory of Spatial Information and Geomatics,Guangxi Guilin 541006,China)
出处
《消防科学与技术》
CAS
北大核心
2023年第10期1444-1452,共9页
Fire Science and Technology
基金
国家自然科学基金项目(42064003)
广西自然科学基金项目(2021GXNSFBA220046)。
关键词
野火易发性评价
信息量模型
机器学习模型
野火灾害
因子重要性分析
wildfire susceptibility assessment
information value model
machine learning model
wildfire disaster
factor impor-tance analysis