Landslide susceptibility evaluation considering the importance selection of influencing factors and soil moisture content
-
摘要:
在滑坡易发性评价体系中，尚未形成统一的和科学的筛选影响滑坡发育因子的标准，导致滑坡易发性评价结果的不一致性。为提高滑坡易发性评估体系的准确性，提出一种基于机器学习的考虑因子重要性选择与土壤含水率的滑坡易发性评价体系。以云南省富民县为例，结合遥感数据、辅助数据和现场调查数据，编制滑坡历史记录；利用SAR卫星后向散射系数和从DEM中提取的地表粗糙度提取土壤含水率，通过XGBoost回归和Lasso回归模型对15个评价因子进行重要性排序，并对滑坡影响因子进行多重共线性评估，筛选出最具鉴别性的滑坡影响因子；用轻量级梯度提升机算法和随机森林模型分别在因子重要性选择前与选择后对富民县进行滑坡易发性评价。结果表明，土壤含水率因子对滑坡发育有较大影响；经过因子重要性选择后的滑坡易发性评价结果准确性更高；轻量级梯度提升机算法模型在评估中表现出优越的评估性能(AUC=0.91)，表明LightGBM模型可以较好地应用在滑坡易发性评价中。本研究着重讨论了因子重要性选择对滑坡易发性评价体系的影响，并有效地将面状土壤含水率因子纳入滑坡影响因子中，提高了易发性评价结果的精确性和可靠性，为预防滑坡灾害提供新思路。
-
关键词:
- 机器学习 /
- 轻量级梯度提升机算法 /
- 土壤含水率 /
- 滑坡易发性 /
- 地质灾害
Abstract:The current landslide susceptibility assessment system lacks unified and scientifically grounded standards for selecting factors that influence landslide development, leading to inconsistencies in evaluation results. To improve the accuracy of the landslide susceptibility assessment system, a method based on machine learning (ML) , which innovatively integrates factor importance selection and soil moisture content was proposed. Focusing on landslides in the Fumin County in Yunnan Province, this study integrated remote sensing data, auxiliary data, and field survey data to compile comprehensive landslide history records. Soil moisture content factors were extracted using SAR satellite backscatter coefficients and DEM data, and 15 evaluation factors were ranked for importance using XGBoost and Lasso regression models. Multicollinearity assessments of landslide influencing factors (LIFs) were conducted to identify the most distinctive factors. The landslide susceptibility in the Fumin County was evaluated using LightGBM and Random Forest models, before and after factor importance selection. The results show a significant improvement in assessment accuracy after factor selection, with the LightGBM model exhibiting superior evaluation performance with an AUC value of 0.91, demonstrating its effective application in landslide susceptibility assessment. This study highlights the impact of factor importance selection on the landslide susceptibility assessment system, effectively incorporates areal soil moisture content factors into landslide influencing factors, and optimizes the precision and reliability of susceptibility assessment results, providing new insights for landslide disaster prevention.
-
-
表 1 利用遥感和辅助数据集制备的不同的滑坡影响因子
Table 1. Different landslide impact factors prepared using remote sensing and auxiliary datasets
序号 提取因子 数据源和分辨率 1 坡度 第三次全国土地调查数据库
的DEM数据
（5 m×5 m）2 坡向 3 DEM 4 地面起伏度 5 平面曲率 6 剖面曲率 7 地层岩组 云南省地质局
地质图（1∶50000 ）8 距断层距离 9 归一化植被指数 哨兵-1A卫星数据
（10 m×10 m）10 土壤含水率 11 土地利用 第三次全国土地调查数据库
矢量数据（5 m×5 m）12 距河流距离 13 距道路距离 14 GPA 昆明市地震局（2021年） 15 降雨量 富民县气象站（2022年） 
下载: 导出CSV
表 2 因子重要性筛选前后的富民县滑坡易发性评价频率比
Table 2. Frequency ratio of landslide susceptibility evaluations in the Fumin County before and after factor importance screening
15个影响因子评价结果 12个影响因子评价结果 模型 分级 面积/km2 容积率/% 滑坡点/个 滑坡比率/% 频率比 模型 分级 面积/km2 容积率/% 滑坡点/个 滑坡比率/% 频率比 LightGBM 极低 263.433 26.47 14 6.93 0.26 LightGBM 极低 300.530 30.20 15 7.43 0.25 低 258.143 25.95 33 16.34 0.63 低 297.597 29.91 13 6.44 0.21 中等 123.512 12.42 30 14.85 1.20 中等 111.805 11.24 16 7.92 0.70 高 174.785 17.57 31 15.35 0.87 高 132.138 13.28 40 19.80 1.49 极高 174.982 17.59 94 46.53 2.65 极高 152.785 15.36 118 58.41 3.80 RF 极低 132.207 13.29 6 2.97 0.22 RF 极低 262.435 26.38 19 9.41 0.36 低 227.083 22.83 46 22.77 1.00 低 240.375 24.16 14 6.93 0.28 中等 204.060 20.51 27 13.37 0.65 中等 147.362 14.81 12 5.94 0.40 高 250.513 25.18 58 28.71 1.14 高 189.765 19.07 54 26.73 1.40 极高 180.992 18.19 65 32.18 1.77 极高 154.918 15.57 103 50.99 3.27
下载: 导出CSV
-
[1] 陈涛,钟子颖,牛瑞卿,等. 利用深度信念网络进行滑坡易发性评价[J]. 武汉大学学报(信息科学版),2020,45(11):1809 − 1817. [CHEN Tao,ZHONG Ziying,NIU Ruiqing,et al. Mapping landslide susceptibility based on deep belief network[J]. Geomatics and Information Science of Wuhan University,2020,45(11):1809 − 1817. (in Chinese with English abstract)]
CHEN Tao, ZHONG Ziying, NIU Ruiqing, et al. Mapping landslide susceptibility based on deep belief network[J]. Geomatics and Information Science of Wuhan University, 2020, 45（11）: 1809 − 1817. （in Chinese with English abstract）
[2] 张玘恺,凌斯祥,李晓宁,等. 九寨沟县滑坡灾害易发性快速评估模型对比研究[J]. 岩石力学与工程学报,2020,39(8):1595 − 1610. [ZHANG Qikai,LING Sixiang,LI Xiaoning,et al. Comparison of landslide susceptibility mapping rapid assessment models in Jiuzhaigou County,Sichuan province,China[J]. Chinese Journal of Rock Mechanics and Engineering,2020,39(8):1595 − 1610. (in Chinese with English abstract)]
ZHANG Qikai, LING Sixiang, LI Xiaoning, et al. Comparison of landslide susceptibility mapping rapid assessment models in Jiuzhaigou County, Sichuan province, China[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39（8）: 1595 − 1610. （in Chinese with English abstract）
[3] 杜国梁,杨志华,袁颖,等. 基于逻辑回归–信息量的川藏交通廊道滑坡易发性评价[J]. 水文地质工程地质,2021,48(5):102 − 111. [DU Guoliang,YANG Zhihua,YUAN Ying,et al. Landslide susceptibility mapping in the Sichuan-Tibet traffic corridor using logistic regression-information value method[J]. Hydrogeology & Engineering Geology,2021,48(5):102 − 111. (in Chinese with English abstract)]
DU Guoliang, YANG Zhihua, YUAN Ying, et al. Landslide susceptibility mapping in the Sichuan-Tibet traffic corridor using logistic regression-information value method[J]. Hydrogeology & Engineering Geology, 2021, 48（5）: 102 − 111. （in Chinese with English abstract）
[4] 唐鸿磊,陈菊,沈春颖,等. 饱和导水率异质性对黄土高原浅层滑坡的影响[J]. 清华大学学报(自然科学版),2023,63(12):1946 − 1960. [TANG Honglei,CHEN Ju,SHEN Chunying,et al. Impacts of heterogeneity of saturated hydraulic conductivity on the shallow landslides on the Loess plateau[J]. Journal of Tsinghua University (Science and Technology),2023,63(12):1946 − 1960. (in Chinese with English abstract)]
TANG Honglei, CHEN Ju, SHEN Chunying, et al. Impacts of heterogeneity of saturated hydraulic conductivity on the shallow landslides on the Loess plateau[J]. Journal of Tsinghua University （Science and Technology）, 2023, 63（12）: 1946 − 1960. （in Chinese with English abstract）
[5] 赵彬如,陈恩泽,戴强,等. 基于水文-气象阈值的区域降雨型滑坡预测研究[J]. 测绘学报,2022,51(10):2216 − 2225. [ZHAO Binru,CHEN Enze,DAI Qiang,et al. Study on prediction of regional rainfall-induced landslides based on hydro-meteorological threshold[J]. Acta Geodaetica et Cartographica Sinica,2022,51(10):2216 − 2225. (in Chinese with English abstract)]
ZHAO Binru, CHEN Enze, DAI Qiang, et al. Study on prediction of regional rainfall-induced landslides based on hydro-meteorological threshold[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51（10）: 2216 − 2225. （in Chinese with English abstract）
[6] BUI D T,PRADHAN B,REVHAUG I,et al. A novel hybrid evidential belief function-based fuzzy logic model in spatial prediction of rainfall-induced shallow landslides in the Lang Son city area (Vietnam)[J]. Geomatics,Natural Hazards and Risk,2015,6(3):243 − 271. doi: 10.1080/19475705.2013.843206
[7] LEE S. Application of logistic regression model and its validation for landslide susceptibility mapping using GIS and remote sensing data[J]. International Journal of Remote Sensing,2005,26(7):1477 − 1491. doi: 10.1080/01431160412331331012
[8] 黄发明,曹中山,姚池,等. 基于决策树和有效降雨强度的滑坡危险性预警[J]. 浙江大学学报(工学版),2021,55(3):472 − 482. [HUANG Faming,CAO Zhongshan,YAO Chi,et al. Landslides hazard warning based on decision tree and effective rainfall intensity[J]. Journal of Zhejiang University (Engineering Science),2021,55(3):472 − 482. (in Chinese with English abstract)]
HUANG Faming, CAO Zhongshan, YAO Chi, et al. Landslides hazard warning based on decision tree and effective rainfall intensity[J]. Journal of Zhejiang University （Engineering Science）, 2021, 55（3）: 472 − 482. （in Chinese with English abstract）
[9] 李铁锋,丛威青. 基于Logistic回归及前期有效雨量的降雨诱发型滑坡预测方法[J]. 中国地质灾害与防治学报,2006,17(1):33 − 35. [LI Tiefeng,CONG Weiqing. A method for rainfall-induced landslides prediction based on Logistic regression and effective antecedent rainfall[J]. The Chinese Journal of Geological Hazard and Control,2006,17(1):33 − 35. (in Chinese with English abstract)]
LI Tiefeng, CONG Weiqing. A method for rainfall-induced landslides prediction based on Logistic regression and effective antecedent rainfall[J]. The Chinese Journal of Geological Hazard and Control, 2006, 17（1）: 33 − 35. （in Chinese with English abstract）
[10] 李文彦,王喜乐. 频率比与信息量模型在黄土沟壑区滑坡易发性评价中的应用与比较[J]. 自然灾害学报,2020,29(4):213 − 220. [LI Wenyan,WANG Xile. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess Gully Region[J]. Journal of Natural Disasters,2020,29(4):213 − 220. (in Chinese with English abstract)]
LI Wenyan, WANG Xile. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess Gully Region[J]. Journal of Natural Disasters, 2020, 29（4）: 213 − 220. （in Chinese with English abstract）
[11] 齐信,黄波林,刘广宁,等. 基于GIS技术和频率比模型的三峡地区秭归向斜盆地滑坡敏感性评价[J]. 地质力学学报,2017,23(1):97 − 104. [QI Xin,HUANG Bolin,LIU Guangning,et al. Landslide susceptibility assessment in the Three Gorges area,China,Zigui synclinal basin,using GIS technology and frequency ratio model[J]. Journal of Geomechanics,2017,23(1):97 − 104. (in Chinese with English abstract)]
QI Xin, HUANG Bolin, LIU Guangning, et al. Landslide susceptibility assessment in the Three Gorges area, China, Zigui synclinal basin, using GIS technology and frequency ratio model[J]. Journal of Geomechanics, 2017, 23（1）: 97 − 104. （in Chinese with English abstract）
[12] 刘福臻,王灵,肖东升. 机器学习模型在滑坡易发性评价中的应用[J]. 中国地质灾害与防治学报,2021,32(6):98 − 106. [LIU Fuzhen,WANG Ling,XIAO Dongsheng. Application of machine learning model in landslide susceptibility evaluation[J]. The Chinese Journal of Geological Hazard and Control,2021,32(6):98 − 106. (in Chinese with English abstract)]
LIU Fuzhen, WANG Ling, XIAO Dongsheng. Application of machine learning model in landslide susceptibility evaluation[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32（6）: 98 − 106. （in Chinese with English abstract）
[13] 杨兰芳,李跃琼,董晓霞,等. 富民县发展山区农业的思考——以永定街道为例[J]. 中国农技推广,2023,39(1):12 − 13. [YANG Lanfang,LI Yueqiong,DONG Xiaoxia,et al. Thoughts on developing mountain agriculture in Fumin County—taking Yongding street as an example[J]. China Agricultural Technology Extension,2023,39(1):12 − 13. (in Chinese)]
YANG Lanfang, LI Yueqiong, DONG Xiaoxia, et al. Thoughts on developing mountain agriculture in Fumin County—taking Yongding street as an example[J]. China Agricultural Technology Extension, 2023, 39（1）: 12 − 13. （in Chinese）
[14] 张洪,陈凤娇. 低丘缓坡山地建设开发景观生态规划研究——以云南省富民县哨箐区块为例[J]. 中国市场,2016(4):156 − 165. [ZHANG Hong,CHEN Fengjiao. Study on landscape ecological planning of construction and development in low hills and gentle slopes:A case study of shaoqing block in Fumin County,Yunnan Province[J]. China Market,2016(4):156 − 165. (in Chinese)]
ZHANG Hong, CHEN Fengjiao. Study on landscape ecological planning of construction and development in low hills and gentle slopes: A case study of shaoqing block in Fumin County, Yunnan Province[J]. China Market, 2016（4）: 156 − 165. （in Chinese）
[15] 刘勇,魏良帅,黄安邦,等. 气候变化下长江源土壤水时空演化及其环境响应[J]. 水文地质工程地质,2023,50(5):39 − 52. [LIU Yong,WEI Liangshuai,HUANG Anbang,et al. Spatial and temporal evolution of soil water and its response to the environment in the Yangtze River source area under climate change[J]. Hydrogeology & Engineering Geology,2023,50(5):39 − 52. (in Chinese with English abstract)]
LIU Yong, WEI Liangshuai, HUANG Anbang, et al. Spatial and temporal evolution of soil water and its response to the environment in the Yangtze River source area under climate change[J]. Hydrogeology & Engineering Geology, 2023, 50（5）: 39 − 52. （in Chinese with English abstract）
[16] 陈庭轩,李素敏,袁利伟. InSAR在云南德钦县一中河泥石流物源汇集及失稳模式中的探究[J]. 大地测量与地球动力学,2022,42(2):158 − 164. [CHEN Tingxuan,LI Sumin,YUAN Liwei. InSAR study on substance source collection and instability mode of Yizhong River debris flow in Deqin,Yunnan Province[J]. Journal of Geodesy and Geodynamics,2022,42(2):158 − 164. (in Chinese with English abstract)]
CHEN Tingxuan, LI Sumin, YUAN Liwei. InSAR study on substance source collection and instability mode of Yizhong River debris flow in Deqin, Yunnan Province[J]. Journal of Geodesy and Geodynamics, 2022, 42（2）: 158 − 164. （in Chinese with English abstract）
[17] 陈晓东,郭金运,孙明智,等. 青藏高原区域不同地表类型对应后向散射系数的时变分析[J]. 武汉大学学报(信息科学版),2023,48(5):730 − 740. [CHEN Xiaodong,GUO Jinyun,SUN Mingzhi,et al. Time-varying analysis of backscatter coefficient corresponding to different surface types in the Tibetan Plateau[J]. Geomatics and Information Science of Wuhan University,2023,48(5):730 − 740. (in Chinese with English abstract)]
CHEN Xiaodong, GUO Jinyun, SUN Mingzhi, et al. Time-varying analysis of backscatter coefficient corresponding to different surface types in the Tibetan Plateau[J]. Geomatics and Information Science of Wuhan University, 2023, 48（5）: 730 − 740. （in Chinese with English abstract）
[18] 张钟远,邓明国,徐世光,等. 镇康县滑坡易发性评价模型对比研究[J]. 岩石力学与工程学报,2022,41(1):157 − 171. [ZHANG Zhongyuan,DENG Mingguo,XU Shiguang,et al. Comparison of landslide susceptibility assessment models in Zhenkang County,Yunnan Province,China[J]. Chinese Journal of Rock Mechanics and Engineering,2022,41(1):157 − 171. (in Chinese with English abstract)]
ZHANG Zhongyuan, DENG Mingguo, XU Shiguang, et al. Comparison of landslide susceptibility assessment models in Zhenkang County, Yunnan Province, China[J]. Chinese Journal of Rock Mechanics and Engineering, 2022, 41（1）: 157 − 171. （in Chinese with English abstract）
[19] YAO Xin,THAM L G,DAI F C. Landslide susceptibility mapping based on support vector machine:A case study on natural slopes of Hong Kong,China[J]. Geomorphology,2008,101(4):572 − 582. doi: 10.1016/j.geomorph.2008.02.011
[20] 贾雨霏,魏文豪,陈稳,等. 基于SOM-I-SVM耦合模型的滑坡易发性评价[J]. 水文地质工程地质,2023,50(3):125 − 137. [JIA Yufei,WEI Wenhao,CHEN Wen,et al. Landslide susceptibility assessment based on the SOM-I-SVM model[J]. Hydrogeology & Engineering Geology,2023,50(3):125 − 137. (in Chinese with English abstract)]
JIA Yufei, WEI Wenhao, CHEN Wen, et al. Landslide susceptibility assessment based on the SOM-I-SVM model[J]. Hydrogeology & Engineering Geology, 2023, 50（3）: 125 − 137. （in Chinese with English abstract）
-
图(8)
表(2)
计量
- 文章访问数: 27
- PDF下载数: 5
- 施引文献: 0