Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks     

Husam A.H.Al-Najjar  Biswajeet Pradhan 《地学前缘(英文版)》2021,12(2):625-637

In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.  相似文献   

Landslide susceptibility zonation method based on C5.0 decision tree and K-means cluster algorithms to improve the efficiency of risk management   总被引：1，自引：0，他引：1  

Zizheng Guo  Yu Shi  Faming Huang  Xuanmei Fan  Jinsong Huang 《地学前缘(英文版)》2021,12(6):243-261

Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments,but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT)model and the K-means cluster algorithm to produce a regional landslide susceptibility map.Yanchang County,a typical landslide-prone area located in northwestern China,was taken as the area of interest to introduce the proposed application procedure.A landslide inventory containing 82 landslides was prepared and subse-quently randomly partitioned into two subsets:training data(70％landslide pixels)and validation data(30％landslide pixels).Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means clus-ter algorithm.The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC)curve)of the proposed model was the highest,reaching 0.88,compared with traditional models(support vector machine(SVM)=0.85,Bayesian network(BN)=0.81,frequency ratio(FR)=0.75,weight of evidence(WOE)=0.76).The landslide frequency ratio and fre-quency density of the high susceptibility zones were 6.76/km2 and 0.88/km2,respectively,which were much higher than those of the low susceptibility zones.The top 20％interval of landslide occurrence probability contained 89％of the historical landslides but only accounted for 10.3％of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without contain-ing more"stable"pixels.Therefore,the obtained susceptibility map is suitable for application to landslide risk management practices.  相似文献   

泰青威天然气管道临朐段水毁灾害分布特征与风险评价     

张成信  魏龙飞  唐尧  王艳超  代晓光  任永健 《中国地质调查》2021,8(5):108-114

对泰青威天然气管道临朐段地质灾害发育特征进行调查研究发现,临朐段地质灾害类型主要为水毁灾害,具体可分为坡面水毁、河沟道水毁和台田地水毁。野外地质灾害实地调查临朐段管道沿线共发现地质灾害15处,其中坡面水毁点6处,河沟道水毁点4处,台田地水毁点5处。采用定性与半定量相结合的评价方法对其进行地质灾害风险评价,结果表明: 地质灾害风险等级较高的有1处,占6.66%; 风险等级中等的有4处,占26.67%; 风险等级较低的有10处,占66.67%。根据管道沿线地形地貌、地质灾害发育密度、风险等级等因素,划分地质灾害中易发区61 km,低易发区10 km,管道沿线以地质灾害中易发区为主。最后,针对不同类型、不同风险等级地质灾害提出了相应的防治消减措施,为后期管道安全运营和风险整治决策提供了有效的技术依据。  相似文献   

Establishment of modern circulation pattern at c. 6000 cal a BP in Disko Bugt,central West Greenland: opening of the Vaigat Strait     

KERSTIN PERNER  MATTHIAS MOROS  IAN SNOWBALL  JEREMY M. LLOYD  ANTOON KUIJPERS  THOMAS RICHTER 《第四纪科学杂志》2013,28(5):480-489

  相似文献   

Anisotropy of magnetic susceptibility parameters: Guidelines for their rational selection     

Edgardo Cañón-Tapia 《Pure and Applied Geophysics》1994,142(2):365-382

Twenty-eight parameters used to characterize measurements of the anisotropy of magnetic susceptibility are compared theoretically in this work by introducing the concept of the field of susceptibility tensors, which allows the representation of parameters as families of lines in a plane. It is demonstrated that the foliation and lineation parameters are but a special case of the shape parameters, implying that the resolution of these two rock fabric elements using AMS measurements alone is more an artifact of the numerical range of definition of some parameters than a quantification of two physically independent features. Also, it is shown that parameters presumably of the same type do not necessarily yield equivalent interpretation of results in a qualitative sense, and therefore, caution should be strongly exercised when parameters are to be selected. Paramters quantifying the degree of anisotropy are, in general, equivalent to each other because of the very small departure observed in natural rocks from the isotropic case. However, a final consideration of the possible ability to differentiate rock types and a convenient range of values allowing expression of the degree of anisotropy in a well-defined percentage are pointed out as the main factors to be considered before selecting one parameter within this class.  相似文献   

多元素与大骨节病关系的稳定性研究     

侯少范  王卫中 《地理研究》1994,13(4):28-35

对内蒙古三个典型大骨节病区<15岁人群发中21个元素和病情进行了三年连续定期观察,统计分析结果表明:(1)病区食物对人体元素含量的影响可以分为二种情况,一是元素在食物链中含量过低,食物的变化虽可使机体该元素发生变化,但变幅甚小,致使其代谢处于缺乏状态;另一类是机体内这些元素的含量因食物的改变而发生较大变化,显示这些元素与病情无内在联系.(2)对发中硒等2l个元素与病情分别作单相关和多元逐步回归分析,结果证明,硒缺乏是导致大骨节病早期病变的基本因素,而其它元素与病情的关系具有不确定性.  相似文献   

Magnetic pore fabric analysis: a rapid method for estimating permeability anisotropy   总被引：1，自引：0，他引：1  

S. Pfleiderer  H. C. Halls 《Geophysical Journal International》1994,116(1):39-45

  相似文献   

北疆阿巴宫-库尔提断裂带显微组构的运动学和动力学分析   总被引：3，自引：0，他引：3  

杨新岳 《大地构造与成矿学》1990,14(1):29-42

研究了阿尔泰地区NW走向高角度冲断构造中主干的阿巴宫—库尔提断裂带。详细研究了断裂构造岩的变形构造和组构及其所显示的运动学和动力学特征。结果表明:存在早、晚更替且性质不同的变形显微构造。早期以糜棱岩中的韧性变形构造为主,发育有递进变形的不对称构造(压力影、旋转变斑晶、S—C构造等),是断裂中剪切变形运动指向的主要判据。晚期为脆性破裂构造,与早期变形组构具继承、叠加关系。研究了石英光轴的组构形式,证实存在:早期共轴纯剪变形的小圆环带组构和非共轴简单剪切变形中,呈递变关系的点极密—大圆环带—交叉大圆环带组构型式。对变形构造和组构所作的运动学和动力学分析结果表明:阿—库断裂带的形成和变形历史为:①地壳早期NE挤压收缩环境,形成劈理化带;②在持续NE向挤压作用下,大规模剪切、逆冲叠置,和地壳加厚,产生重熔岩浆和流体再分配效应,促使糜棱岩带形成和发展;③晚期地壳NE向挤压下,以垂直差异抬升和大量碎裂岩化高角度逆冲断裂的继承、叠加为特征。在区域大地构造的关系上:①、②对应于地槽褶皱、封闭的地槽体制(海西期),③对应于地洼体制(后海西期)。  相似文献   

安徽安庆月山岩体的磁组构及古地磁特征   总被引：3，自引：0，他引：3  

阎桂林  张鸣 《地球科学》1990,15(6):667-673

  相似文献   

KDX-87型甚低频宽带定向接收与微机分析系统     

田茂  徐继生 《地球物理学报》1991,34(1):11-19,T001

本文介绍了武汉大学哨声组研制的KDX-87型甚低频宽带定向接收与微机分析系统.该系统适用于测量与分析哨声波传播路径出口、偏振和动态谱.此系统具有以下优点:1.设计制造了小型化天线和便携式接收机,便于携带和架设;合理设计了输入耦合与平衡电路,加上有效的标定方法,使接收系统具有良好的频率响应和通道间性能的一致性.2.实现了数字化宽频带定向分析,有利于减小多路径效应误差,并可获得哨声路径出口与波频率之间的关系.3.利用微机进行哨声动态谱分析,采取了有效的抑制干扰处理,所得谱图分辨率优于普通声图仪制作的谱图.该系统在1988年中日联合哨声定向实验中使用,取得了满意的结果.  相似文献