测绘通报 ›› 2024, Vol. 0 ›› Issue (12): 170-177.doi: 10.13474/j.cnki.11-2246.2024.1229

• 技术交流 • 上一篇    下一篇

区域统计约束的滑坡易发性评估与制图

徐刚1,2, 刘青豪2   

  1. 1. 浙江安防职业技术学院, 浙江 温州 325016;
    2. 中南大学地球科学与信息物理学院, 湖南 长沙 410083
  • 收稿日期:2024-04-02 发布日期:2024-12-27
  • 通讯作者: 刘青豪,E-mail:235001015@csu.edu.cn E-mail:235001015@csu.edu.cn
  • 作者简介:徐刚(1982-),男,博士,教授,主要从事地质灾害遥感监测预警分析。E-mail:20096342@zjcst.edu.cn
  • 基金资助:
    浙江省自然资源厅2021年科技项目(2021-38);2021年温州市基础性科研项目(S20210013)

Landslide susceptibility assessment and cartography with regional statistical constraints

XU Gang1,2, LIU Qinghao2   

  1. 1. Zhejiang College of Security Technology, Wenzhou 325016, China;
    2. School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
  • Received:2024-04-02 Published:2024-12-27

摘要: 受限于滑坡灾害监测数据的完备性及滑坡灾害知识利用率低的难题,如何准确耦合多源异构环境数据,以综合评估滑坡易发程度是当前研究的重要挑战。本文提出了一种区域统计约束的滑坡易发性评估方法。首先,根据专家知识选择地形地貌、地质构造、气象水文、人类活动等环境因素,并对相关数据进行清洗、归一化等预处理;其次,从“机理-地理-物理-数理”层面构建灾害数据特征映射,面向历史灾害点及非灾害点进行正负样本均衡采样;然后,在此基础上,借助多尺度空间单元区域划分方法进行行政单元的自适应聚合,将研究区域按照坡度和年均降雨划分为一系列均质子区;最后,在区域统计约束下搭建随机森林模型进行样本训练与易发性制图。试验表明,本文所提方法将滑坡灾害易发性评估精度至少提高了9%。

关键词: 滑坡, 易发性评估, 环境因素, 区域统计, 随机森林

Abstract: Due to the limitations of poor data completeness and low knowledge utilization, it remains a challenge to accurately integrate multiple sources of heterogeneous disaster information to comprehensively evaluate the susceptibility of landslides. Therefore,a mixed framework for mapping the susceptibility of landslides with regional statistical constraints is proposed. Firstly,environmental factors such as topography,geomorphology,geological structure,meteorology and hydrology,and human activities were selected based on expert knowledge,and the relevant data is pre-processed such as cleaning and normalization. Then,from the perspective of “mechanism-geography-physics-mathematics”,the feature mapping of disaster data is constructed,and a balanced sampling of positive and negative samples is carried out for historical disaster sites and non-disaster sites. On this basis,the administrative units are adaptively aggregated using a multi-scale spatial unit division method,and the study area is divided into a series of homogeneous sub-regions according to slope and average annual rainfall. Finally,under the constraint of regional statistics,a random forest model is constructed for sample training and susceptibility mapping. The experiments show that the proposed hybrid framework improves the accuracy of landslide susceptibility assessment by at least 9%.

Key words: landslides, susceptibility assessment, environmental factors, regional statistics, random forests

中图分类号: