| 杨淑香,杨 柳,丁书萍,包兴华.Logistic 回归模型和决策树分析在夏季森林火灾风险预警中的应用[J].林业调查规划,2025,50(5):158-162 |
| Logistic 回归模型和决策树分析在夏季森林火灾风险预警中的应用 |
| Application of Logistic Regression Model and Decision Tree Analysis inSummer Forest Fire Risk Early Warning |
| |
| DOI： |
| 中文关键词: 森林火灾 风险预警 Logistic 回归模型 决策树模型 |
| 英文关键词: forest fire risk early warning Logistic regression model decision tree model |
| 基金项目:国家自然基金项目(42230604);内蒙古自然科学基金项目(2025LHMS04022);内蒙古自治区气象局科技创新项目(nmqxkjcx202305);
呼伦贝尔市气象局项目(hlbeqx202501). |
|
| 摘要点击次数: 895 |
| 全文下载次数: 485 |
| 中文摘要: |
| 为分析内蒙古大兴安岭地区夏季森林火灾风险预警指标情况,建立了预警指标模型。选用
Logistic回归模型和决策树模型分析夏季林火风险预警指标,并利用受试者工作曲线评价2种模型的预测效果。结果表明,最高温和连续无降水日数是林火预警的有效预警指标(P<0.05)。Logistic回归模型拟合曲线下面积大于决策树模型。在夏季林火风险预警中,Logistic回归模型预测能力优
于决策树模型。在实际运用中,可通过Logistic回归模型筛选有实际意义的预警指标,再通过决策树模型分析指标的交互作用,为夏季森林火灾的防控提供参考依据。 |
| 英文摘要: |
| This study analyzed the early warning indicators for summer forest fire risks in the Greater Khingan
Mountains region of Inner Mongolia and established an early warning indicator model. The Logistic
regression model and decision tree model were used to analyze the summer forest fire risk early warning indicators,
and the receiver operating characteristic curve was employed to evaluate the predictive performance
of the two models. The results indicated that maximum temperature and consecutive days without precipitation
were effective early warning indicators for forest fires (P<0.05). The area under the curve of
the Logistic regression model was larger than that of the decision tree model. In summer forest fire risk early warning, the Logistic regression model demonstrated superior predictive capability compared to the
decision tree model. In practical applications, the Logistic regression model can be used to screen practically
significant early warning indicators, followed by the decision tree model to analyze the interactions
among these indicators, providing a reference for the prevention and control of summer forest fires. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
