(1. Institute of Geological Survey，China University of Geosciences(Wuhan)，Wuhan，Hubei 430074，China；
2. Faculty of Engineering，China University of Geosciences(Wuhan)，Wuhan，Hubei 430074，China)
Abstract：The existing landslide susceptibility analysis methods have the defects of ensemble modelling strategy and false negative errors phenomenon. Firstly the stacking algorithm integrating random forest(RF) and extreme gradient boosting(XGBoost) to predict the spatial probability of landslide occurrence was innovatively proposed in this paper. Then，the small baseline subset interferometry technology was used to measure 104 Sentinel-1A data from January 2018 to September 2021，and the deformation velocity along the line-of-sight(Vlos) was re-projected to a new velocity along the steepest slope direction(Vslope). Finally，the empirical matrix was considered to combine the susceptibility and deformation rate classification to achieve the landslide dynamic susceptibility map. The results indicate that the stacking based RF-XGBoost model has better prediction and generalization ability than the decision tree(DT)，RF，XGBoost，Bayesian Network(BN) model，and multilayer perceptron neural network(MLPNN). The landslide dynamic susceptibility map has a better identification ability on areas with strong deformation，reducing the proportion of low-susceptibility by 3%–8% and increasing the proportion of high- and very-high-susceptibility by about 2%. The field investigation verified that this method could improve landslide susceptibility and reduce false negative errors in areas with strong engineering activities. Real-time monitoring should be strengthened in the very-high dynamic susceptibility area of Dazhou Town (along the Yangtze River and the northern Fenghuang village). It is concluded that the ensemble framework and landslide dynamic susceptibility mapping strategy proposed in this paper has high spatial identification and early warning accuracy and can be used as a new method for regional planning of landslide disasters.
[1] ZENG T，YIN K，JIANG H，et al. Groundwater level prediction based on a combined intelligence method for the Sifangbei landslide in the Three Gorges Reservoir Area[J]. Scientific Reports，2022，12：11108.
[2] 张俊，殷坤龙，王佳佳，等. 三峡库区万州区滑坡灾害易发性评价研究[J]. 岩石力学与工程学报，2016，35(2)：284–296.(ZHANG Jun，YIN Kunlong，WANG Jiajia，et al. Evaluation of landslide susceptibility for wanzhou district of three gorges reservoir[J]. Chinese Journal of Rock Mechanics and Engineering，2016，35(2)：284–296.(in Chinese))
[3] 黄发明，陈佳武，唐志鹏，等. 不同空间分辨率和训练测试集比例下的滑坡易发性预测不确定性[J]. 岩石力学与工程学报，2021，40(6)：1 155–1 169.(HUANG Faming，CHEN Jiawu，TANG Zhipeng，et al. Uncertainties of landslide susceptibility prediction due to different spatial resolutions and different proportions of training and testing datasets[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(6)：1 155–1 169.(in Chinese))
[4] 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))
[5] 黄发明，曹昱，范宣梅，等. 不同滑坡边界及其空间形状对滑坡易发性预测不确定性的影响规律[J]. 岩石力学与工程学报，2021，40(增2)：3 227–3 240.(HUANG Faming，CAO Yu，FAN Xuanmei，et al. Effects of different landslide boundaries and their spatial shapes on the uncertainty of landslide susceptibility prediction[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(Supp.2)：3 227–3 240.(in Chinese))
[6] 王佳佳，殷坤龙，肖莉丽. 基于GIS和信息量的滑坡灾害易发性评价——以三峡库区万州区为例[J]. 岩石力学与工程学报，2014，33(4)：797–808.(WANG Jiajia，YIN Kunlong，XIAO Lili. Landslide susceptibility assessment based on GIS and Weight information value：a case study of Wanzhou District，Three Gorges Reservoir[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(4)：797–808.(in Chinese))
[7] 罗路广，裴向军，崔圣华，等. 九寨沟地震滑坡易发性评价因子组合选取研究[J]. 岩石力学与工程学报，2021，40(11)：2 306–2 319. (LUO Luguang，PEI Xiangjun，CUI Shenghua，et al. Combined selection of susceptibility assessment factors for Jiuzhaigou earthquake-induced landslides[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(11)：2 306–2 319.(in Chinese))
[8] 黄发明，陈彬，毛达雄，等. 基于自筛选深度学习的滑坡易发性预测建模及其可解释性[J]. 地球科学，2022，48(5)：1 696–1 710. (HUANG Faming，CHEN Bin，MAO Daxiong，et al. Landslide susceptibility prediction modeling and interpretability based on self-screening deep learning model[J]. Earth Science，2022，48(5)：1 696–1 710.(in Chinese))
[9] 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)：1 595–1 610. (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)：1 595–1 610.(in Chinese))
[10] 宋宇飞，曹琰波，范文，等. 基于贝叶斯方法的降雨诱发滑坡概率型预警模型研究[J]. 岩石力学与工程学报，2023，42(3)：558–574.(SONG Yufei，CAO Yanbo，FAN Wen，et al. Probabilistic early warning model for rainfall-induced landslide based on Bayesian approach[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(03)：558–574.(in Chinese))
[11] 吴雨辰，周晗旭，车爱兰. 基于粗糙集–神经网络的IBURI地震滑坡易发性研究[J]. 岩石力学与工程学报，2021，40(6)：1 226–1 235. (WU Yuchen，ZHOU Hanxu，CHE Ailan. Susceptibility of landslides caused by IBURI earthquake based on rough set-neural network[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(6)：1 226–1 235.(in Chinese))
[12] 金必晶，殷坤龙，桂蕾，等. 基于遥感解译的盐湖地区输电线路杆塔地面沉降易发性评价[J]. 地球科学，2022：1–13.(JIN Bijing，YIN Kunlong，GUI Lei，et al. Based on remote sensing interpretation of transmission line tower land subsidence susceptibility evaluation in salt lake area[J]. Earth science，2022：1–13.(in Chinese))
[13] MERGHADI A，ABDERRAHMANE B，TIEN B D. Landslide susceptibility assessment at mila basin(Algeria)：a comparative assessment of prediction capability of advanced machine learning methods[J]. ISPRS International Journal of Geo-information，2018，7(7)：268.
[14] DI NAPOLI M，CAROTENUTO F，CEVASCO A，et al. Machine learning ensemble modelling as a tool to improve landslide susceptibility mapping reliability[J]. Landslides，2020，17(8)：1 897–1 914.
[15] 刘海知，徐辉，包红军，等. 基于集成学习的山区中小流域滑坡易发区早期识别优化试验[J]. 工程科学与技术，2022，54(6)：12–20.(LIU Haizhi，XU Hui，BAO Hongjun，et al. Optimization experiment of early identification of landslides susceptibility areas in medium and small mountainous catchment based on ensemble learning[J]. Advanced Engineering Sciences，2022，54(6)：12–20.(in Chinese))
[16] MERGHADI A，YUNUS A P，DOU J，et al. Machine learning methods for landslide susceptibility studies：a comparative overview of algorithm performance[J]. Earth-science Reviews，2020，207：103225.
[17] AKINCI H，ZEYBEK M. Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin)，Turkey[J]. Natural Hazards，2021，108(2)：1 515–1 543.
[18] ZHANG T，FU Q，WANG H，et al. Bagging-based machine learning algorithms for landslide susceptibility modeling[J]. Natural Hazards(Dordrecht)，2021，110(2)：823–846.
[19] 高秉海，何毅，张立峰，等. 顾及InSAR形变的CNN滑坡易发性动态评估——以刘家峡水库区域为例[J]. 岩石力学与工程学报，2023，42(2)：450–465.(GAO Binghai，HE Yi，ZHANG Lifeng，et al. Dynamic evaluation of landslide susceptibility by CNN considering InSAR deformation：A case study of Liujiaxia reservoir[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(2)：450–465.(in Chinese))
[20] FRATTINI P，CROSTA G，CARRARA A. Techniques for evaluating the performance of landslide susceptibility models[J]. Engineering Geology，2010，111(1/4)：62–72.
[21] PIACENTINI D，DEVOTO S，MANTOVANI M，et al. Landslide susceptibility modeling assisted by Persistent Scatterers Interferometry(PSI)：an example from the northwestern coast of Malta[J]. Natural Hazards，2015，78(1)：681–697.
[22] CIAMPALINI A，RASPINI F，LAGOMARSINO D，et al. Landslide susceptibility map refinement using PSInSAR data[J]. Remote Sensing of Environment，2016，184：302–315.
[23] CALVELLO M，PEDUTO D，ARENA L. Combined use of statistical and DInSAR data analyses to define the state of activity of slow-moving landslides[J]. Landslides，2017，14(2)：473–489.
[24] ZHOU C，CAO Y，HU X，et al. Enhanced dynamic landslide hazard mapping using MT-InSAR method in the Three Gorges Reservoir Area[J]. Landslides，2022，19(7)：1 585–1 597.
[25] 郭子正，殷坤龙，黄发明，等. 基于滑坡分类和加权频率比模型的滑坡易发性评价[J]. 岩石力学与工程学报，2019，38(2)：287–300.(GUO Zizheng，YIN Kunlong，HUANG Faming，et al. Evaluation of landslide susceptibility based on landslide classification and weighted frequency ratio model[J]. Chinese Journal of Rock Mechanics and Engineering，2019，38(2)：287–300.(in Chinese))
[26] HUANG F，YAO C，LIU W，et al. Landslide susceptibility assessment in the Nantian area of China：a comparison of frequency ratio model and support vector machine[J]. Geomatics，Natural Hazards and Risk，2018，9(1)：919–938.
[27] MOORE I D，GRAYSON R D，LADSON A R. Digital terrain modelling；a review of hydrological，geomorphological and biological applications[J]. Hydrological Processes，1991，5(1)：3–30.
[28] 黄发明，陈佳武，范宣梅，等. 降雨型滑坡时间概率的逻辑回归拟合及连续概率滑坡危险性建模[J]. 地球科学，2022，47(12)：4 609–4 628.(HUANG Faming，CHEN Jiawu，FAN Xuanmei，et al. Logistic regression fitting of rainfall-induced landslide occurrence probability and continuous landslide hazard prediction modelling[J]. Earth Science，2022，47(12)：4 609–4 628.(in Chinese))
[29] FREUND Y，SCHAPIRE R E. A desicion-theoretic generalization of on-line learning and an application to boosting[M]. Berlin，Heidelberg：Springer Berlin Heidelberg，1997：23–37.
[30] CHEN T，GUESTRIN C. XGBOOST：A scalable tree boosting system[C]// Proceedings of the 22nd Acm Sigkdd International Conference On Knowledge Discovery and Data Mining. New York，NY，USA：Association for Computing Machinery，2016：785–794.
[31] BREIMAN L. Random Forests[J]. Machine Learning，2001，45：5–32.
[32] ?WOLPERT D. Stacked Generalization[J]. Neural networks，1992，5(2)：241–259.
[33] BERARDINO P，FORNARO G，LANARI R，et al. A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms[J]. IEEE Transactions on Geoscience and Remote Sensing，2002，40(11)：2 375–2 383.
[34] CASCINI L，PEDUTO D，PISCIOTTA G，et al. The combination of DInSAR and facility damage data for the updating of slow-moving landslide inventory maps at medium scale[J]. Natural Hazards and Earth System Sciences，2013，13(6)：1 527–1 549.
[35] MANDREKAR J N. Receiver operating characteristic curve in diagnostic test assessment[J]. Journal of Thoracic Oncology，2010，5(9)：1 315–1 316.
[36] DOU J，YUNUS A P，BUI D T，et al. Improved landslide assessment using support vector machine with bagging，boosting，and stacking ensemble machine learning framework in a mountainous watershed，Japan[J]. Landslides，2020，17(3)：641–658.
[37] CASCINI L，FORNARO G，PEDUTO D. Advanced low- and full-resolution DInSAR map generation for slow-moving landslide analysis at different scales[J]. Engineering Geology，2010，112(1/4)：29–42.
[38] CRIPPA C，VALBUZZI E，FRATTINI P，et al. Semi-automated regional classification of the style of activity of slow rock-slope deformations using PS InSAR and SqueeSAR velocity data[J]. Landslides，2021，18(7)：2 445–2 463.
[39] 曾韬睿，殷坤龙，桂蕾等.基于滑坡致灾强度预测的建筑物易损性定量评价[J]. 地球科学，2023，48(5)：1 807–1 824.(ZENG Taorui，YIN Kunlong，GUI Lei，et al. Quantitative vulnerability analysis of buildings based on landslide intensity prediction[J]. Earth Science，2023，48(5)：1 807–1 824.(in Chinese))
2023, Vol. 42 
