数据与计算发展前沿 ›› 2025, Vol. 7 ›› Issue (1): 186-202.

CSTR: 32002.14.jfdc.CN10-1649/TP.2025.01.014

doi: 10.11871/jfdc.issn.2096-742X.2025.01.014

• 技术与应用 • 上一篇    

滑坡数据不完整对易发性建模的影响及改进建议

何一飞1,2,3(),张耀南1,3,4,*()   

  1. 1.中国科学院西北生态环境资源研究院，甘肃 兰州 730000
    2.中国科学院大学，北京 100049
    3.国家冰川冻土沙漠科学数据中心，甘肃 兰州 730000
    4.甘肃省资源环境科学数据工程技术研究中心，甘肃 兰州 730000
  • 收稿日期:2023-03-27 出版日期:2025-02-20 发布日期:2025-02-21
  • 通讯作者: *张耀南（E-mail: yaonan@lzb.ac.cn）
  • 作者简介:何一飞，中国科学院西北生态环境资源研究院，硕士研究生，研究方向为GIS和遥感在地质灾害中的应用。
    本文中负责模型实现和论文撰写。
    HE Yifei is a master’s student at the Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences. His research interest covers the application of GIS and remote sensing in geological hazards.
    In this paper, he is responsible for model implementation and paper writing.
    E-mail: heyifei20@mails.ucas.ac.cn|张耀南，中国科学院西北生态环境资源研究院大数据中心主任，国家冰川冻土沙漠科学数据中心主任，博士，研究员，博士生导师。主要研究方向为环境科学数据工程、基于高性能计算环境的地学模型模拟、遥感图像处理及多元数据融合。
    本文中负责论文框架，设计指导和论文修订。
    ZHANG Yaonan, PH.D., is a professor and the dean of Big Data Center of the Northwest Institute of Eco-Environment and Resources. He is also the director of the National Cryosphere Desert Data Center. His current research interests include integrated modeling environment, remote sensing image processing, and multi-source heterogeneous data fusion.
    In this work, he is responsible for the framework of the paper, design guidance, and revision of the paper.
    E-mail: yaonan@lzb.ac.cn
  • 基金资助:
    国家重点研发计划(2022YFF0711700)

Influence of Incomplete Landslide Data on Susceptibility Modeling and Suggestions for Improvement

HE Yifei1,2,3(),ZHANG Yaonan1,3,4,*()   

  1. 1. Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, Gansu 730000, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
    3. National Cryosphere Desert Data Center, Lanzhou, Gansu 730000, China
    4. Gansu Data Engineering and Technology Research Center for Resources and Environment, Lanzhou, Gansu 730000, China
  • Received:2023-03-27 Online:2025-02-20 Published:2025-02-21

RichHTML

6

PDF

65

摘要：

【目的】中国是世界上滑坡最频发的国家之一。建立一个可靠的全国范围内的滑坡易发性模型，以确定滑坡高易发地区、制定适当的防灾减灾策略、减少对人民生命财产损失显得非常必要。【方法】鉴于在我国这样大的区域上很难获得完全无偏的滑坡数据，本研究选择了坡度、坡向、剖面曲率、平面曲率、道路密度、河流密度、土壤湿度、岩性、土地利用和地质环境分区等10个影响因素作为驱动数据，设计了基于轻量级梯度提升机（LightGBM）并忽略滑坡数据不完整影响的模型方案一、基于LightGBM并排除与滑坡数据不完整相关因素的模型方案二和基于提升树混合效应模型（TBMM）并将描述滑坡数据不完整的变量（即土地利用和地质环境分区）作为随机效应项的模型方案三来分别评估滑坡灾害的易发性，以探索不完整滑坡数据对我国滑坡易发性建模的影响以及如何抵消这种偏差影响。【结果】研究表明，在大区域易发性建模的背景下；（1）尽管简单地忽略或排除与现有滑坡数据缺陷相关因素的模型方案具有更高的统计性能，但会导致预测的滑坡易发性结果在地貌上不合理；（2）应用混合效应模型可以有效降低滑坡数据的不完整性带来的偏差影响。【结论】本研究为滑坡数据不完整背景下的滑坡易发性制图提供了新思路，并有助于了解全国整体的滑坡灾害易发性状况，可协助决策者进行总体规划以降低灾害风险。

关键词: 滑坡, 易发性制图, 数据偏差, LightGBM, TBMM

Abstract:

[Objective] China is one of the countries with the most frequent landslide disasters in the world. It is necessary to establish a reliable landslide susceptibility model suitable for the whole country to determine the areas with high landslide hazards, formulate appropriate disaster prevention and reduction strategies, and reduce the loss of people's lives and property. [Methods] Given the difficulty in obtaining completely unbiased landslide data in such a large area of China, this study selected 10 influencing factors such as slope, aspect, profile curvature, plan curvature, road density, river density, soil moisture, lithology, land use, and geological environment division as the driving data and designed Model Scheme 1 (Based on LightGBM and ignoring the effects of incomplete landslide data), Model Scheme 2 (Based on LightGBM and excluding factors associated with landslide incompleteness) and Model Scheme 3 (Based on TBMM and including the variables describing landslide incompleteness, i.e. land use and geological environment division, as random effect terms) to assess landslide susceptibility separately to explore the impact of incomplete landslide data on the modelling of landslide susceptibility in China, the impact of incomplete landslide data on the modelling of landslide susceptibility in China, and the measure to counteract the effect of such bias. [Results] The results show that, in the context of large regional susceptibility modeling, (1) although the model schemes that simply ignore or exclude the factors associated with existing landslide data deficiencies have higher statistical performance, they will lead to geomorphically incoherent landslide susceptibility prediction results; (2) the mixed effects model can effectively reduce the bias impact caused by incomplete landslide data. [Conclusions] This study provides a new idea for landslide susceptibility mapping under the background of incomplete landslide data and contributes to assessing China’s overall mass movement susceptibility situation and assisting policymakers in master planning for risk mitigation.

Key words: landslide, susceptibility map, inventory bias, LightGBM, TBMM