| 972 | 0 | 51 |
| 下载次数 | 被引频次 | 阅读次数 |
董志塬地区位于黄土高原中心地带，滑坡灾害频发，亟需明确滑坡易发性分区，以支持该区域滑坡隐患的科学防控。因此，本文以董志塬为研究区，选取高程、坡向和NDVI等12个影响因素作为评价因子，基于频率比(frequency ratio,FR)模型，结合随机森林(random forest,RF)与人工神经网络(artificial neural network,ANN)模型开展滑坡静态易发性评价，并分析各因子对评价精度的贡献。结果表明，FRRF和FR-ANN模型的曲线下面积(area under the curve,AUC)值分别为0.922和0.918，表明FR-RF模型在董志塬滑坡易发性评价中的精度更高。坡度、坡向和道路密度对滑坡易发性的贡献率分别为16.7%、15.3%和1.4%。为克服地形复杂和数据更新滞后的问题，本文将FR-RF模型的易发性结果与InSAR Stacking结果相结合，将静态滑坡易发性评价精度由6.9%提升到8.1%。动态易发性结果表明，董志塬滑坡高易发区主要分布于河流沿岸，占总面积的6.5%，该区域的滑坡数量占总滑坡数的23.6%，滑坡密度15.7个/km2。低易发区主要位于远离河流的中部区域，占总面积的81.7%，滑坡数量占总滑坡数的57.8%，滑坡密度4.7个/km2。本研究通过融合InSAR Stacking方法，解决了静态滑坡易发性评价数据更新滞后问题，减少了假阴性错误，为传统滑坡易发性评价赋予了时效性，可以实现董志塬滑坡易发性动态评价，为灾害防治提供了重要数据支持。
Abstract：Dongzhiyuan, located in the heart of Loess Plateau, is prone to frequent landslides, making it crucial to identify landslide susceptibility zones for better disaster prevention.This study focuses on the Dongzhi Plateau as the research area, selecting 12 influencing factors including elevation, slope aspect, and NDVI as evaluation indicators.Based on the Frequency Ratio(FR) model, a static landslide susceptibility assessment combined with Random Forest(RF) and Artificial Neural Network(ANN) models is conducted.The contribution of each factor to the evaluation accuracy is analyzed.The FR-RF model showes higher accuracy, with AUC values of 0.922 compared to 0.918 for the FR-ANN model.The integration of InSAR Stacking technology improves evaluation precision of the FR-RF model by 6.9%-8.1%, highlighting high susceptibility areas along riverbanks.By improving the FR-RF model and incorporating dynamic updates, the study reduces false-negative errors and increased the reliability of susceptibility maps.This dynamic approach offers valuable data support for landslide risk management in the Dongzhiyuan region.
[1]Huo Aidi, Peng Jianbing, Cheng Yuxiang, et al. Hydrological Analysis of Loess Plateau Highland Control Schemes in Dongzhi Plateau[J]. Frontiers in Earth Science, 2020, 8:528632
[2]Kou Pinglang, Xu Qiang, Yunus A P, et al. Landslide-Controlled Soil Erosion Rate in the Largest Tableland on the Loess Plateau, China[J]. Human and Ecological Risk Assessment:An International Journal,2020, 26(9):2 478-2 499
[3]Lee S, Min K. Statistical Analysis of Landslide Susceptibility at Yongin, Korea[J]. Environmental Geology, 2001, 40(9):1 095-1 113
[4]Choi J, Oh H J, Lee Hongjin, et al. Combining Landslide Susceptibility Maps Obtained from Frequency Ratio, Logistic Regression, and Artificial Neural Network Models Using ASTER Images and GIS[J]. Engineering Geology, 2012, 124:12-23
[5]Guo Changbao, Montgomery D R, Zhang Yongshuang,et al. Quantitative Assessment of Landslide Susceptibility Along the Xianshuihe Fault Zone, Tibetan Plateau,China[J]. Geomorphology, 2015, 248:93-110
[6]Lee S, Pradhan B. Landslide Hazard Mapping at Selangor, Malaysia Using Frequency Ratio and logistic Regression Models[J]. Landslides,2007, 4:33-41
[7]李郎平，兰恒星，郭长宝，等.基于改进频率比法的川藏铁路沿线及邻区地质灾害易发性分区评价[J].现代地质，2017, 31(5):911-929
[8]Breiman L. Random Forests[J]. Machine Learning,2001, 45(1):5-32
[9]周萍，邓辉，张文江，等.基于信息量模型和机器学习方法的滑坡易发性评价研究——以四川理县为例[J].地理科学，2022, 42(9):1 665-1 675
[10]李文彬，范宣梅，黄发明，等.不同环境因子联接和预测模型的滑坡易发性建模不确定性[J].地球科学，2021, 46(10):3 777-3 795
[11]Xu Chong, Xu Xiwei, Dai Fuchu, et al. Comparison of Different Models for Susceptibility Mapping of Earthquake Triggered Landslides Related with the 2008 Wenchuan Earthquake in China[J]. Computers&Geosciences, 2012, 46:317-329
[12]Yilmaz I. Landslide Susceptibility Mapping Using Frequency Ratio, Logistic Regression, Artificial Neural Networks and Their Comparison:A Case Study from Kat Landslides(Tokat-Turkey)[J]. Computers&Geosciences, 2009, 35(6):1 125-1 138
[13]Wang Liangjie, Guo Min, Sawada K, et al. A Comparative Study of Landslide Susceptibility Maps Using Logistic Regression, Frequency Ratio, Decision Tree,Weights of Evidence and Artificial Neural Network[J].Geosciences Journal, 2016, 20(1):117-136
[14]Yilmaz I. Comparison of Landslide Susceptibility Mapping Methodologies for Koyulhisar, Turkey:Conditional Probability, Logistic Regression, Artificial Neural Networks, and Support Vector Machine[J]. Environmental Earth Sciences, 2010, 61(4):821-836
[15]Pradhan B ,Lee S. Delineation of Landslide Hazard Areas on Penang Island, Malaysia, by Using Frequency Ratio, Logistic Regression, and Artificial Neural Network Models[J]. Environmental Earth Sciences, 2010, 60(5):1 037-1 054
[16]Pradhan B, Lee S. Landslide Susceptibility Assessment and Factor Effect Analysis:Backpropagation Artificial Neural Networks and Their Comparison with Frequency Ratio and Bivariate Logistic Regression Modelling[J]. Environmental Modelling&Software, 2010,25(6):747-759
[17]Selamat S N, Majid N A, Taha M R, et al. Landslide Susceptibility Model Using Artificial Neural Network(ANN)Approach in Langat River Basin, Selangor,Malaysia[J]. Land, 2022, 11(6):833
[18]Sandwell D T, Price E J. Phase Gradient Approach to Stacking Interferograms[J]. Journal of Geophysical Research:Solid Earth, 1998, 103(B12):30 183-30 204
[19]Xiao Ruya , Yu Chen , Li Zhenhong , et al. General Survey of Large-Scale Land Subsidence by GACOSCorrected InSAR Stacking:Case Study in North China Plain[J]. Proceedings of the International Association of Hydrological Sciences , 2020 , 382:213-218
[20]Ciampalini A, Raspini F, Lagomarsino D, et al. Landslide Susceptibility Map Refinement Using PSInSAR Data[J].Remote Sensing of Environment, 2016, 184:302-315
[21]Wu Xueling, Qi Xiaoshuai, Peng Bo, et al. Optimized Landslide Susceptibility Mapping and Modelling Using the SBAS-InSAR Coupling Model[J]. Remote Sensing, 2024, 16(16):2873
[22]张茂省，李同录.黄土滑坡诱发因素及其形成机理研究[J].工程地质学报，2011, 19(4):530-540
[23]Roy J, Saha S, Arabameri A, et al. A Novel Ensemble Approach for Landslide Susceptibility Mapping(LSM)in Darjeeling and Kalimpong Districts , West Bengal,India[J]. Remote Sensing, 2019, 11(23):2866
基本信息:
DOI：10.14188/j.2095-6045.20250252
中图分类号:P237;P642.22
引用信息:
[1]王向辉,张成龙,李振洪,等.融合InSAR Stacking的董志塬滑坡动态易发性评价[J].测绘地理信息,2026,51(01):33-43.DOI:10.14188/j.2095-6045.20250252.
基金信息:
陕西省地学大数据与地质灾害防治创新团队（2022）; 陕西省科技创新团队项目（2021TD-51）; 中央高校基本科研业务费专项（300102264718,300102261308,300102264302,300102264901）; 国家自然科学基金（42404020）; 陕西省影像大地测量共性技术研发平台（2024ZG-GXPT-07）