主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2023, Vol. 42 ›› Issue (11): 1567-1571.

• • 上一篇    下一篇

基于LightGBM和SHAP的云南省森林火灾预测研究

汪祖民1, 王恺锋1, 李艳志2,3,4, 李国辉2,3,4   

  1. （1. 大连大学 信息工程学院，辽宁 大连 116622；2. 应急管理部天津消防研究所，天津 300381；3. 工业与公共建筑火灾防控技术应急管理部重点实验室，天津 300381；4. 天津市消防安全技术重点实验室，天津 300381）
  • 出版日期:2023-11-15 发布日期:2023-11-15
  • 作者简介:汪祖民（1975- ），男，河南信阳人，大连大学信息工程学院教授，博士，主要从事智慧城市、物联网等研究，辽宁省大连市经济技术开发区学府大街10号，116622。
  • 基金资助:
    大连市科技创新基金（2018J12GX049）

Research on forest fire prediction in Yunnan province based on LightGBM and SHAP

Wang Zumin1, Wang Kaifeng1, Li Yanzhi2,3,4, Li Guohui2,3,4   

  1. (1. College of Information Engineering,Dalian University,Liaoning Dalian 116622, China; 2. Tianjin Fire Science and Technology Research Institute of MEM, Tianjin 300381, China; 3. Laboratory of Fire Protection Technology for Industry and Public Building, Ministry of Emergency Management, Tianjin 300381, China; 4. Tianjin Key Laboratory of Fire Safety Technology, Tianjin 300381, China)
  • Online:2023-11-15 Published:2023-11-15

摘要： 针对当前森林火灾预测研究中存在准确性不足和缺乏模型可解释性的问题，选择云南省为研究区域，提出融合LightGBM机器学习模型和SHAP可解释模型的森林火灾预测方法。结果表明，与已有的多种机器学习模型相比，LightGBM表现出更高的准确率（90.5%），在高易发区域大部分火点被准确识别。通过引入SHAP模型，增强了LightGBM模型的可解释性。其中，全局可解释方法可以帮助使用者理解各个特征在模型中的响应趋势，而局部可解释方法则可以解释特定森林火灾实例的预测过程。本文提出的基于LightGBM和SHAP可解释机器学习方法不仅有助于云南省森林火灾预测，还对其他灾害预测领域的风险预测建模具有启示意义。

关键词: 森林火灾, 预测模型, 机器学习, 可解释性

Abstract: This research paper tackles the challenges of accuracy and interpretability in forest fire prediction studies. The study focuses on the Yunnan province as the geographical area of interest and proposes an innovative approach that combines the LightGBM machine learning model with the SHAP (Shapley Additive explanations) interpretable model for forest fire prediction. The findings indicate that compared to other existing machine learning models, LightGBM demonstrates superior accuracy, achieving a rate of 90.5% in accurately identifying most fire incidents within high?risk zones. By incorporating the SHAP model, the interpretability of the LightGBM model is enhanced. The global interpretability method aids users in comprehending the response patterns of various features within the model, while the local interpretability method elucidates the prediction process for specific instances of forest fires. The proposed methodology, utilizing LightGBM and SHAP, not only advances forest fire prediction in Yunnan province but also offers valuable insights for risk prediction modeling in other domains of disaster forecasting.

Key words: forest fires, predictive models, machine learning, interpretability