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.     

北京市城近郊区地下水的环境同位素研究

应用环境同位素方法,研究北京城近郊区地下水演化规律。沿北京市永定河冲洪积扇地下水流动方向取样15组(D、18O、T、14C及全分析),对所取水样进行D、18O、T、14C分析,并确定地下水同位素年龄。运用地下水14C和T含量在垂向和水平方向变化的结果,验证了地下水的流向并计算了地下水的流速变化范围为5·02~62·63m/a,从山前至平原浅层地下水径流速度逐渐变小,反映了地下水水平径流强度逐渐减弱,地下水交替逐渐变差;浅层孔隙水以垂向交替为主,深层孔隙水以水平径流为主。对地下水D、18O之间的关系进行分析,从而判断地下水的补给来源等。     

Sedimentary facies and paleoenvironmental interpretation of a Holocene marsh in the Gironde Estuary in France

1Introduction Since the last glacial maximum, the Holocenehas been marked by a rapid rise in sea level. After6 000 a BP, the present-day level was reached andthe rate of sea-level rise (SLR) decreased rapidly(Morzadec -Kerfourn, 1974; Kidson, 1986 ).These…     

基于GPU加速的Boussinesq类波浪传播变形数值模型

Boussinesq波浪模型是一类相位解析模型,在时域内求解需要较高的空间和时间分辨率以保证计算精度。为提高计算效率,有必要针对该类模型开展并行算法的研究。与传统的中央处理器(CPU)相比,图形处理器(GPU)有大量的运算器,可显著提高计算效率。基于统一计算设备架构CUDA C语言和图形处理器,实现了Boussinesq模型的并行运算。将本模型的计算结果同CPU数值模拟结果和解析解相比较,发现得到的结果基本一致。同时也比较了CPU端与GPU端的计算效率,结果表明,GPU数值模型的计算效率有明显提升,并且伴随数值网格的增多,提升效果更为明显。     

FY-3C/VIRR中红外图像太阳光污染订正

风云三号C星(FY-3C)上搭载的可见光红外扫描辐射计VIRR (Visible and Infra-Red Radiometer)是继承风云一号卫星光学成像仪器,它在高纬度昼夜交替区域附近由于地平线附近太阳光照射,导致仪器扫描镜和其他部件产生杂散光,导致对地观测图像被污染,尤其VIRR中红外第3通道(3.7 μm)图...     

Jenniferann.com,regional development,and realising the aspirations of mana whenua in Pōkeno

During the 1990s, the township of Pōkeno was held up as an example of a declining rural Aotearoa/New Zealand. By‐passed from the national state highway, it lost its status as a service hub and drastic measures were introduced to revitalise the town, including renaming the town “ Jenniferann.com .” Pōkeno has since undergone an unlikely transformation, with foreign investment and its location within an extended Auckland commuter zone meaning that the township has grown exponentially. This article describes the transformation of Pōkeno and uncovers what has been missing from discussions about Pōkeno's reinvention, namely, the place of mana whenua.     

Mid-late Holocene anthropogenic and natural variations in geochemistry and sedimentation in the Yazoo Basin: Clark Lake,Sharkey County,Mississippi

A 4000-yr history at Clark Lake reveals natural variations in sediment geochemistry and nutrient levels and anthropogenic influence on twentieth century sedimentation rates. Sediment texture and ridge and swale topography indicate that the channel system creating Clark Lake is now occupied by the Yazoo River. Between 1.24 and 0.60 m (2522–865 cal yr BP), total carbon percentages and the C/N ratio average 42% and 17, respectively. The base of the 1650-yr interval and onset of high organic activity in the lake coincides with the abandonment of the Yazoo Meander Belt. The top of the interval is marked by a drop in C/N ratio to 11 and a geochemical transition zone. No change in the rate of sediment accumulation or clay mineralogy was observed despite increased cumulative percentages of Al, Fe, K, Mg, Mn, Ca, and Na. The decrease in organic activity at 865 cal yr BP is attributed to unfavorable growth conditions related to the entrenchment of the Yazoo River and changes in the hydroperiod of the area. Significant floodplain alteration was completed in 1978, but the only major effect was increased sedimentation in the late twentieth century due to the completion of the Whittington Auxiliary Channel.     

"资源一号"02C卫星影像土地利用变化检测能力分析

“资源一号”02C卫星自成功发射以来,被广泛应用于土地资源、矿产资源、地质环境调查,以及国土资源、地质灾害应急监测等应用领域。“资源一号”02C卫星是一颗填补我国高分辨率遥感数据空白的卫星,是根据国土资源主体业务需求定制的第一颗国产高分辨率业务卫星。本文以吉林省和浙江省某试验区“资源一号”02C卫星数据为例,对“资源一号”02C卫星数据融合影像进行了土地利用遥感监测变化信息检测能力的方法试验。根据试验区数据变化信息提取试验结果,对“资源一号”02C卫星影像在土地利用动态遥感监测中的变化检测能力和适用性开展了试验、分析和评价工作。     

中国半干旱草原施氮梯度下的土壤激发效应（英文）

为了探究施氮对土壤有机质(SOM)的激发效应,本研究在施氮梯度样地(0、4和16 g N m^–2 yr^–1)上进行了¹³C标记葡萄糖的原位添加实验,并对土壤CO_2排放量和磷脂脂肪酸(PLFA)含量进行了测定。研究发现施氮降低了土壤CO_2排放、土壤PLFA含量以及土壤真菌细菌比。在0 g N m^–2 yr^–1样地上葡萄糖添加导致的正向激发效应最强,同时4 g N m^–2 yr^–1样地释放的葡萄糖来源的碳最多。因此,施氮减少了土壤中SOM转化产生的CO_2,微生物碳的来源由SOM转变为添加的易分解碳。本研究采样早期土壤微生物生物量和群落结构稳定,表明该草原存在"表观激发效应",因此未来研究应着重对微生物功能的多样性进行探讨。     

大地水准面高的计算及其在海底地形反演中的应用

为充分挖掘海洋重力数据在反演海底地形中的应用潜力,尝试探索利用大地水准面高反演海底地形的技术途径,并以夏威夷—皇帝海山链拐点所在海区作为反演试验区进行验证。首先采用Belikov列推法计算伴随(缔和)勒让德函数,利用EIGEN-6C4地球重力场模型解算获取了分辨率为1'的大地水准面高格网数值模型;然后通过综合分析反演比例函数和转换函数特点、研究海区大地水准面高与海底地形的相干特性以及大地水准面高本身尺度特征,获得了利用大地水准面高反演海底地形的频段范围;最终以试验海区大地水准面高为数据输入,构建了相应的海底地形模型(BNT模型),并与ETOPO1等海深模型进行比对分析。试验结果表明:BNT模型检核差值在一倍均方差范围检核点数量占比70.60%,相比正态分布更加集中;BNT模型检核精度低于ETOPO1等海深模型;海深模型检核精度随着水深增加不断提升,水深小于1 000 m时,海深模型相对误差出现较大发散现象;计算海域ETOPO1模型精度最高,GEBCO模型和DTU10模型检核精度相当。