Landslide susceptibility zonation method based on C5.0 decision tree and K-means cluster algorithms to improve the efficiency of risk management

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.     

泰青威天然气管道临朐段水毁灾害分布特征与风险评价

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。     

Devensian Late-glacial and early Flandrian environmental history of the Vale of Pickering,Yorkshire, England

Pollen, sedimentological and charcoal particle analyses are presented from Devensian Late-glacial and early- to mid-Flandrian deposits from a former lake in the Vale of Pickering, Yorkshire. The combined analytical methods provide evidence for a short-lived climatic deterioration towards the end of the Late-glacial Interstadial, followed by a brief recovery prior to the Loch Lomond Stadial. This deterioration may be correlated with one of the ‘pre-Younger Dryas’ cooling periods identified not only in other pollen sequences from Britain and Europe, but from such diverse sources as Foraminifera from the Norwegian Sea and electrical conductivity measurements from the Greenland ice sheet. Loss-on-ignition and magnetic susceptibility data suggest that the Loch Lomond Stadial was characterised by an initial prolonged temperature decline, followed by a sudden more severe downturn resulting in particularly intense solifluction. Radiocarbon accelerator dating of the early Flandrian marl deposits illustrates the problem of age determination in calcareous lakes, and an estimate of the magnitude of ‘hard water error’ is obtained. The local population expansion of Alnus glutinosa is dated to 7640 ± 85 yr BP, but there is possible evidence for a Late-glacial presence of the tree, the significance of which is discussed in relation to other sites in east Yorkshire. © 1996 John Wiley & Sons, Ltd.     

磁化率和密度对中国大陆科学钻探主孔100～2000 m岩石类型的判别

为查明磁化率和密度对于中国大陆科学钻探工程(CCSD)主孔100~2000m岩性的响应和判别特征,利用SPSS10.0统计分析软件进行了判别分析.研究结果显示,岩石的密度和体积磁化率主要受岩性的控制.采用迫入法建立全模型,对CCSD主孔100~2000m井段岩心的岩性判别率达84.8%.其中,蛇纹石化橄榄岩、正片麻岩、副片麻岩、榴辉岩、角闪岩和退变质榴辉岩的判别率分别为100%、87.1%、89.7%、89.6%、96.7%和63.7%.该研究表明,密度和磁化率可以为超高压变质岩石的岩性鉴别和区分提供定量约束,有利于地球物理探测成果和测井资料的准确解析.同时,本文也是SPSS统计分析软件在超高压变质岩石类型判别方面的一个应用实例,对于其他岩石类型的判别分析具有借鉴意义.     

陕西镇安西口石炭系-二叠系界线剖面综合地层学研究

对中国海相石炭—二叠系界线典型剖面陕西镇安西口剖面进行了生物地层、层序地层、磁性地层、事件地层多学科综合研究。在石炭—二叠系界线附近建立了4个牙形石生物带,自下而上依次为Streptogna-thoduselegantulus带,S·elongatus带,S·gracilis带和S·isolatus带。将研究区石炭—二叠系界线置于S·isolatus带的底界,较以带Pseudofusulinakrotowisphaeroidea-Dunbarinella(PD)带的底界为标志确定的石炭—二叠系界线层位低3·3m。在西口剖面上石炭统逍遥阶至下二叠统隆林阶,以初始海泛面作为层序界面,识别出12个四级层序(大体相当于副层序组),构成5个Ⅱ型三级层序。这5个三级层序及其对应的海平面变化与贵州独山、罗甸纳水、紫云扁平剖面同期地层中三级层序及海平面变化旋回之间显示出较好的对应关系。除下杨家河阶外,其余各阶的底界,包括逍遥阶、上杨家河阶、范家河阶、垭口阶及隆林阶的底界,基本上都位于沉积相转换点或其附近,即层序地层及海平面变化旋回的关键界面或其附近。表明这5个三级层序的关键界面与年代地层界线的关系相当密切。碳酸盐岩磁化率大小与碳酸盐岩微相存在一定的对应关系,显示相对海平面变化是控制碳酸盐岩磁化率大小的重要因素。另外,在重要地层界线附近常出现磁化率异常高值,说明碳酸盐岩磁化率可能作为地层划分对比的重要依据。西口地区晚石炭世逍遥期至早二叠世隆林期地层中可识别出两次明显的类辐射事件。第一次类辐射事件发生在Occidentoschwagerinaalpina-O·postgallowayi(OS)组合带底部,即下杨家河阶的底部。第二次辐射事件发生在Mccloudiaregularis-Par-aschwagerinafragosa-Robustoschwagerinaxiaodushanica(MPR)组合带底部,即范家河阶的底部。具有三级和三级以上隔壁的四射珊瑚动物群突然大量繁盛,代表四射珊瑚演化进程中一次重大变革。在陕西镇安石炭—二叠系界线附近,这个生物事件首现层位相当于类Pseudofusulinaurdalensi(PU)带下部,高于该带底界不到12m,以Xikouphyllum-Shaannanophyllum-Szechuanophyllum-Wentzellophyllum组合带为代表。在这个层位牙形石也发生了重要变化。各类地质事件记录出现的层位关系密切。在垭口阶底界各类地质事件记录吻合最好,隆林阶底界次之,然后是范家河阶底界。与上述3条界线相比,在镇安西口剖面上,以牙形石Streptognathodusisolatus的首现位置确定的石炭—二叠系界线事件地层特征不明显,既不是一个生物辐射演化面,碳酸盐岩磁化率变化也不太明显,在实际工作中不易使用。     

Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer

As threats of landslide hazards have become gradually more severe in recent decades,studies on landslide prevention and mitigation have attracted widespread attention in relevant domains.A hot research topic has been the ability to predict landslide susceptibility,which can be used to design schemes of land exploitation and urban development in mountainous areas.In this study,the teaching-learning-based optimization(TLBO)and satin bowerbird optimizer(SBO)algorithms were applied to optimize the adaptive neuro-fuzzy inference system(ANFIS)model for landslide susceptibility mapping.In the study area,152 landslides were identified and randomly divided into two groups as training(70%)and validation(30%)dataset.Additionally,a total of fifteen landslide influencing factors were selected.The relative importance and weights of various influencing factors were determined using the step-wise weight assessment ratio analysis(SWARA)method.Finally,the comprehensive performance of the two models was validated and compared using various indexes,such as the root mean square error(RMSE),processing time,convergence,and area under receiver operating characteristic curves(AUROC).The results demonstrated that the AUROC values of the ANFIS,ANFIS-TLBO and ANFIS-SBO models with the training data were 0.808,0.785 and 0.755,respectively.In terms of the validation dataset,the ANFISSBO model exhibited a higher AUROC value of 0.781,while the AUROC value of the ANFIS-TLBO and ANFIS models were 0.749 and 0.681,respectively.Moreover,the ANFIS-SBO model showed lower RMSE values for the validation dataset,indicating that the SBO algorithm had a better optimization capability.Meanwhile,the processing time and convergence of the ANFIS-SBO model were far superior to those of the ANFIS-TLBO model.Therefore,both the ensemble models proposed in this paper can generate adequate results,and the ANFIS-SBO model is recommended as the more suitable model for landslide susceptibility assessment in the study area considered due to its excellent accuracy and efficiency.     

Frost susceptibility of soils——A confusing concept that can misguide geotechnical design in cold regions

Frost susceptibility is a concept widely used in cold region geotechnical design, to quantify the capacity of a soil in generating frost heave and frost damage. The laboratory test used to verify frost susceptibility of a soil is based on the measurement of frost heave generated in the soil under specific conditions. In reality this concept is, however, more related to the soil's potential to thaw weakening than to frost heave. Recent experimental studies show that frost non-susceptible soils like clean sand and clean gavel can also generate much ice segregation and frost heave if the conditions are favourable, hence challenging the usefulness and suitability of soil classification based on frost susceptibility. It is further shown that the concept is not suitable for design scenarios where frost heave itself is a serious hazard, such as in high-speed rail embankments.     

江苏金坛和尚墩旧石器遗址地层的古地磁年代与磁化率研究

北方黄土研究中磁化率分析已越来越多运用到第四纪风尘堆积研究中。采用古地磁极性柱结合磁化率曲线比对定年的方法,初步确定江苏金坛和尚墩遗址750cm厚的地层年龄为330kaBP,对应磁化率曲线判断该区域分别经历了24kaBP左右、110kaBP左右、190—240kaBP左右、300kaBP左右的4个暖湿期,其中间隔有3个干冷时期,具有完整的3个气候旋回。对应地层发育的4个古土壤层、3个黄土层的风尘堆积—古土壤序列。研究表明,虽然古地磁极性定年的方法有一定的局限性,但在以磁化率信息为辅助的条件下,可在一定程度上消除这些局限,获得较为准确的地层年代,多种证据表明这种方法是可靠的。     

临沂市地质灾害现状及易发程度分区评价

2016年,临沂市地质灾害排查共查明了391处地质灾害隐患点,主要类型为崩塌、滑坡、泥石流、采空塌陷和岩溶塌陷,崩塌数量最多,其次为采空塌陷和岩溶塌陷。地质灾害规模以小型为主。该文详细介绍了临沂市地质环境背景条件,各类地质灾害发育现状及分布特征。在此基础上,采用"地质灾害综合危险性指数法"进行地质灾害易发性评价,运用栅格数据处理方法将临沂市划分成1350个面积相等的单元,对影响地质灾害发育的地质条件、地形地貌条件、气候植被条件、地质灾害隐患点、地质灾害规模、分布密度、活动频次和险情等要素进行量化,根据实际情况对地质灾害易发程度分级进行定性修正,将临沂市地质灾害易发程度划分为高易发区、中易发区、低易发区及不易发区4个区。预测了地质灾害发展趋势,划分了地质灾害防治分区,建议完善地质灾害预警预报系统,为临沂市应急管理局的地质灾害应急救援提供地质灾害基础背景资料。     

渭河流域东部全新世黄土-古土壤剖面光释光测年及其记录的土壤侵蚀事件

在渭河流域东部老官台(LGT)全新世黄土-古土壤剖面中,系统采集了15个黄土释光测年样品,应用单片再生剂量法(SAR)对这些样品的细颗粒混合矿物进行了光释光(OSL)测年,测定结果表明:红外之后蓝光释光([post—IR]OSL)的年龄偏大,红外释光(IRSL)的年龄偏小或与蓝光释光(BLSL)的年龄基本一致,应用IRSL和BLSL信号测定的OSL年龄整体偏小可能与测定样品中长石矿物的异常衰退有关,而[post—IR]OSL信号由于很少发生异常衰退问题,使得其年龄可靠性更高。基于测定的[post-IR]OSL年龄,结合该剖面的磁化率和粒度指标,进一步探讨了渭河流域东部自全新世以来发生的两期土壤侵蚀事件,第1期土壤侵蚀事件发生在约12.40～9.34 kaBP,即全新世大暧期来临之前的气候转暖期间;第2期土壤侵蚀事件发生在约4.60～3.76 kaBP,即全新世大暖期即将结束、气候开始出现恶化、黄河中游地区夏文化发展的时期,这为深入探索夏代发生的大洪水事件及其气候背景提供了科学依据,本区两期显著的土壤侵蚀事件的发现,揭示了东亚季风系统的不稳定性,表现为千年到百年尺度上的快速变化。