Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China

The Support Vector Machine (SVM) is an increasingly popular learning procedure based on statistical learning theory, and involves a training phase in which the model is trained by a training dataset of associated input and target output values. The trained model is then used to evaluate a separate set of testing data. There are two main ideas underlying the SVM for discriminant-type problems. The first is an optimum linear separating hyperplane that separates the data patterns. The second is the use of kernel functions to convert the original non-linear data patterns into the format that is linearly separable in a high-dimensional feature space. In this paper, an overview of the SVM, both one-class and two-class SVM methods, is first presented followed by its use in landslide susceptibility mapping. A study area was selected from the natural terrain of Hong Kong, and slope angle, slope aspect, elevation, profile curvature of slope, lithology, vegetation cover and topographic wetness index (TWI) were used as environmental parameters which influence the occurrence of landslides. One-class and two-class SVM models were trained and then used to map landslide susceptibility respectively. The resulting susceptibility maps obtained by the methods were compared to that obtained by the logistic regression (LR) method. It is concluded that two-class SVM possesses better prediction efficiency than logistic regression and one-class SVM. However, one-class SVM, which only requires failed cases, has an advantage over the other two methods as only “failed” case information is usually available in landslide susceptibility mapping.     

A sapping erosion susceptibility model for the southern Cantabrian Range, North Spain

A susceptibility model of sapping-related depressions has been produced by analysing the statistical relationship between the location of depressions and topographical variables. Sapping erosion plays an important role in the growth of gullies developed over poorly-consolidated quartzite conglomerates in the northern sector of the Duero Tertiary Basin (the Cantabrian Mountain Range of Spain). Gullies, topsoil subsidence depressions related to sapping processes, and shallow slides have been identified over sandy soils in an area of 37 km². This area underwent major changes in land use during the 20th century, leading to the expansion of gully erosion processes. On the surface, depressions of several meters in diameter, caused by internal erosion related to sapping processes, can be identified. Using the topographical location of these topsoil depressions and several topographical variables, 14 discriminate functions were derived to provide information about the influence of topography on the development of sapping erosion processes. The functions have accuracy levels varying from 56 to 81%. The most accurate function was regionalized by means of a Geographical Information System and was used to complete a land classification method which is based on the Mahalanobis distance to the multivariate average (centroid) of a sapping erosion form group. The classification of this model allows the identification of areas with different relative probabilities of sapping processes and the resultant growth of gullies.     

Landslide susceptibility mapping for a part of tectonic Kelkit Valley (Eastern Black Sea region of Turkey)

Considering damage to man-made structures by natural hazards in Turkey, landslides are the second most important hazard after earthquakes. For this reason, a large-scale study titled Turkish Landslide Inventory Project, has been carried out since 1998. During this project, some special, susceptibility, hazard and risk assessments have been performed. In this study, a landslide susceptibility map of a part of tectonic Kelkit Valley in the north of central Turkey was produced, employing binary logistic regression analyses. To achieve the most appropriate results some sensitivity analyses were also carried out. For this purpose, four different data sets were constructed considering conditioning factors used and sampling strategies applied for the training data sets in this study. As a consequence of the analyses, the most proper outcomes were obtained by using the data set in which continuous topographical parameters and lithological dummy variables were implemented together and 50% of training data set was taken from seed cells at random. Correct classification percentage and Root Mean Square Error (RMSE) values for the validation data for that case were estimated as 84.16% and 0.36, respectively. This prediction capability shows that the landslide susceptibility map produced in this research paper can be used for the planning of protective and mitigation measures in the region.     

影响中国黄土磁化率差异的多因素评述

 通过查阅最近30 a来对黄土古土壤磁化率与气候的关系等方面的研究结果,认为：成壤作用过程中由生物作用和风化作用产生的超顺磁粒级的磁铁矿、磁赤铁矿等强磁性矿物是导致古土壤磁化率增强的主要原因。另外,磁化率值高低也不容忽视其他因素的影响,如黄土古土壤本底值的区别、淋溶作用、有机质对磁性矿物老化的阻碍及其本身的磁化率等。因此,黄土古土壤磁化率的高低是在气候条件为主导的作用下多种因素参与的结果。     

滇东北拱王山地区全新世以来的气候环境变化

对滇北拱王山狐狸房峰南侧老碳房村附近冰蚀湖相沉积剖面进行粒度、磁化率分析,结合^14C年代,建立了8．4ka至今的古气候环境变化序列。全新世早期以来经历5次较明显的气候波动：8．4—7．7ka,磁化率（xlf）变化在1．62-3．88μm^3kg^-1,粒度平均值为5．46φ,气候凉湿;7．7～6．5ka,粒度均值为5．83φ,磁化率降低,变化在1．44-2．28μm^3kg^-1。之间,气候冷湿;6．5-4．7ka,粒度均值为5．95φ,磁化率值变化在1．53—3．65μm^3kg^-1之间,气候冷干;4．7-2．1ka,粒度均值为5．91φ,磁化率增加,变化在2．0—5．2μm^3kg^-1。之间,气候凉湿;2．1ka以来,粒径平均值为5．63φ,磁化率值显著增加,介于3．44-6．33μm^3kg^-1。之间,平均值为4．80μm^3kg^-1,气候以暖湿为主。     

海南岛双池玛珥湖全新世磁化率及其环境意义

海南岛双池玛珥湖沉积物磁化率高分辨率的时间序列分析表明,磁化率与粒度指标和粘土矿物含量存在相关关系,磁化率突变往往对应于沉积物的突变界面,因此与沉积相变化可以对比.磁化率与碳、氮含量呈负相关,表明湖泊的有机质生产力高时磁化率较低.多指标的对比分析进一步证明了中国热带全新世高温期为:7 200～2 700aBP,高温期从炎热而降雨量相对低的稳定时期过渡到频繁变动的气候不稳定阶段;晚全新世,尤其在2 700aBP左右,气候模式发生了重大转折,波动幅度变大,可能与厄尔尼诺-南方涛动(ENSO)活动性增强有关.海     

Pressure Instability of Magnetic Susceptibility of Pyrrhotite Bearing Rocks from the KTB Borehole

Experimental results of pressure-induced changes in mean magnetic susceptibility of rock samples from the main KTB borehole are reported. It was found that susceptibility values of rocks from depths between 5200 and 7000 m show unstable behaviour upon application of pressure, showing an increase in susceptibility of between 20 and 120%. This unstable behaviour was only detected in samples from the above mentioned depth interval, which contain both ferrimagnetic and antiferromagnetic phases of pyrrhotite. On the basis of thermomagnetic analysis, magnetic field treatment, optical microscopy and domain observations of undeformed and deformed samples, reasons for this instability are discussed and interpreted in relation to redistribution of internal stresses within the ferrimagnetic phase, resulting in changes in domain wall mobility.     

Modification of the liquefaction potential index and liquefaction susceptibility mapping for a liquefaction-prone area (Inegol,Turkey)

Although some liquefaction assessment methods were proposed to evaluate the liquefaction potential of sandy soils, the conventional method based on the standard penetration test (SPT) has been commonly used in most countries and in Turkey. However, it alone is not a sufficient tool for the evaluation of liquefaction potential. The liquefaction potential index was proposed to quantify the severity of liquefaction. Nevertheless, the liquefaction potential index and the severity categories do not answer the question: "Which areas will not liquify?" Besides, the categories do not include a "moderate" category; on the other hand, the "high" and "low" categories are included. This situation is also contrary to the nature of classification schemes. In this study, the liquefaction potential index and the liquefaction potential categories were modified by considering the existing form of the categories based on the liquefaction potential index. While the category of low was omitted, the categories of moderate and "non-liquefied" were adopted. A factor of safety of 1.2 was assumed as the lowest value for the liquefaction potential category of non-liquefied. In addition, the town of Inegol in the Marmara region became the case study for checking the performance of the liquefaction potential categories suggested in this study.     

用质子磁力仪测定岩(矿)石标本磁参数时应注意的问题

岩(矿)石标本磁参数测定结果的精确性直接影响磁异常反演精度,对正确推断地质结论具有特别重要的意义。在进行高精度磁测磁参数测定过程中,发现利用质子磁力仪测定岩(矿)石标本磁参数时,按过去介绍的方法测定、计算的磁化率、剩余磁化强度普遍比实际值偏大一到十几倍,在分析和确定引起误差的原因后,提出了改进的方法,即要用岩(矿)石标本所产生的磁感应强度代替其梯度进行磁参数的计算而不能用其梯度值来求磁参数。并应注意如避开探头中级化场对标本磁化的影响,用第一位置测定以减少位置不准所产生的计算误差等问题。将改进方法用于后续研究的岩(矿)石标本磁参数测定,用其结果进行磁异常反演,求得磁性体埋藏深度、产状等与实际情况相符合。