基于信息量-机器学习耦合的野火灾害易发性评估

消防科学与技术 ›› 2023, Vol. 42 ›› Issue (10): 1444-1452.

基于信息量-机器学习耦合的野火灾害易发性评估

岳韦霆1, 任超1,2, 梁月吉1,2

（1. 桂林理工大学测绘地理信息学院，广西桂林 541006；2. 广西空间信息与测绘重点实验室，广西桂林 541006）

出版日期:2023-10-15 发布日期:2023-10-15
作者简介:岳韦霆（1998- ），男，山西阳泉人，桂林理工大学测绘与地理信息学院硕士研究生，主要从事野火灾害易发性评估方面的研究，广西桂林市雁山区雁山街319号，541006。
基金资助:
基金项目：国家自然科学基金项目（42064003）；广西自然科学基金项目（2021GXNSFBA220046）

Wildfire hazard susceptibility assessment based on coupled information value⁃machine learning

Yue Weiting1, Ren Chao1,2, Liang Yueji1,2

(1. College of Geomatics and Geoinformation, Guilin University of Technology, Guangxi Guilin 541006, China;2. Guangxi Key Laboratory of Spatial Information and Geomatics, Guangxi Guilin 541006, China)

Online:2023-10-15 Published:2023-10-15

摘要/Abstract

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。

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

Abstract: In order to give full play to the advantages of statistics and machine learning model in the analysis and evaluation of wildfire disaster susceptibility, Guilin, which is rich in forest resources and deeply troubled by wildfire disaster, was taken as the research area, and 16 evaluation factors were selected from the aspects of climate, topography, hydrology and humanities. Based on the information value （IV） model, 4 machine learning （ML） models, including logistic regression （LR）, artificial neural network （ANN）, random forest （RF）, and extreme gradient boosting （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 provide valuable insights for local wildfire prevention and control.

Key words: wildfire susceptibility assessment, information value model, machine learning model, wildfire disaster, factor importance analysis

岳韦霆, 任超, 梁月吉, . 基于信息量-机器学习耦合的野火灾害易发性评估[J]. 消防科学与技术, 2023, 42(10): 1444-1452.

Yue Weiting, Ren Chao, Liang Yueji, . Wildfire hazard susceptibility assessment based on coupled information value⁃machine learning[J]. Fire Science and Technology, 2023, 42(10): 1444-1452.