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.     

基于VTK的医学图像系统研究

医学三维数据场可视化是当前科学计算可视化应用的重点。本文论述了可视化工具包VisualizationToolkit(VTK)的主要特点,介绍了三维医学可视化系统实现的原理和方法。根据一系列人体断面图像,应用VTK实现了三维医学图像重构,对重构后的三维图像进行解剖分析;并实现对人体的二维图像逐帧浏览及柱状统计。实验结果表明,VTK具有使用灵活,功能强大的优点,是医学三维数据场可视化的有力工具。     

0302号(鲸鱼)台风降水和水粒子空间分布的三维结构特征

由于缺乏关于台风结构信息的高分辨率资料,即探测台风云系内部结构特征的技术限制,造成了进一步理解台风的动力传送特征的困难.作者用热带测雨卫星(TRMM,Tropical Rainfall Measuring Mission)的测雨雷达(PR,Precipitation Radar)和TRMM微波图像仪(TMI,TRMM Microwave Imager)资料详细研究了"鲸鱼"台风(0302号)于2003年4月16日1105 UTC的降水和降水云系中各种水粒子的三维结构特征.通过分析发现该时刻:(1)台风降水中大部分区域为层性降水(占总降水面积的85.5%),对流性降水占总降水面积的13.1%,但对流性降水的贡献却达到41.8%,所以,虽然对流性降水所占面积比例很少,但是它对总降水量的贡献却很大.(2)60%降水主要集中在距离台风中心100 km以内的区域,约占总降水量的60%.(3)各种水粒子含量随着与台风中心距离的增加而减少.降水云系中水粒子最大含量出现高度与水粒子的种类和与台风中心的距离有关.最后,分析了台风降水和降水云系中三维分布的成因.     

虚拟现实技术在城市规划中的应用研究与实践

从虚拟现实的概念出发,分析了虚拟现实的3个特征,论述了虚拟现实技术涉及到的关键技术及虚拟现实技术在城市规划中的应用。最后,我们以小区为研究对象,将3D数据作为数据源,采用VRMap软件平台进行将VR技术应用于城市规划中的研究与试验。     

"3S"技术在城市规划专业的应用与教学改革

信息技术的发展,城市规划专业教育逐步将定量和数字技术方法引入教育体系,文章对“3S”技术特别是“GIS”、“RS”和数字城市技术在城市规划领域的广泛应用和课程体系的教学改革进行探讨和建议。     

伽师近场观测地震资料的三维Q值成像

为了研究震源区介质的物性特征,利用振幅谱拟合和有限差分三维Q值成像方法处理了伽师地震区临时台网的地震波形资料,获得了该地震区上地壳的S波三维Q值图像。结果表明:不同深度的Q值图像都存在低Q值带,主要展布方向为EW向、NNE向和NNW向,与研究区的柯坪断裂、羊达曼断裂和麦盖提断裂有一定的对应关系,并且NNE向的低Q值带与强震群分布和余震分布的条带位置接近,推测低Q值带可能是震源区的几条深部断裂。     

坐标转换模型在盾构姿态计算中的应用

在附有条件的间接平差模型的基础上,提出用归一化大角度坐标转换模型计算盾构机姿态,并从其原理、方法以及精度上进行了分析。应用结果表明:利用坐标转换法计算盾构机姿态,与常规解方程法相比较更能有效利用参考点的所有信息,计算过程简明,且便于程序实现。     

Soil moisture retrieval from satellite images and its application to heavy rainfall simulation in eastern China

The soil water index (SWI) from satellite remote sensing and the observational soil moisture from agricultural meteorological stations in eastern China are used to retrieve soil moisture. The analysis of correlation coefficient (CORR), root-mean-square-error (RMSE) and bias (BIAS) shows that the retrieved soil moisture is convincible and close to the observation. The method can overcome the difficulties in soil moisture observation on a large scale and the retrieved soil moisture may reflect the distribution of the real soil moisture objectively. The retrieved soil moisture is used as an initial scheme to replace initial conditions of soil moisture (NCEP) in the model MM5V3 to simulate the heavy rainfall in 1998. Three heavy rainfall processes during 13–14 June, 18–22 June, and 21–26 July 1998 in the Yangtze River valley are analyzed. The first two processes show that the intensity and location of simulated precipitation from SWI are better than those from NCEP and closer to the observed values. The simulated heavy rainfall for 21–26 July shows that the update of soil moisture initial conditions can improve the model’s performance. The relationship between soil moisture and rainfall may explain that the stronger rainfall intensity for SWI in the Yangtze River valley is the result of the greater simulated soil moisture from SWI prior to the heavy rainfall date than that from NCEP, and leads to the decline of temperature in the corresponding area in the heavy rainfall days. Detailed analysis of the heavy rainfall on 13–14 June shows that both land-atmosphere interactions and atmospheric circulation were responsible for the heavy rainfall, and it shows how the SWI simulation improves the simulation. The development of mesoscale systems plays an important role in the simulation regarding the change of initial soil moisture for SWI.     

周家湾地区前侏罗纪古地貌恢复及油气富集规律

前侏罗纪古地貌控制着中下侏罗统沉积发育及油气的富集规律, 精确恢复刻画古地貌形态对于侏罗系油气勘探至关重要.以鄂尔多斯盆地周家湾地区为例, 在沉积相、砂体展布、古流向物源、古厚度恢复、古水深校正等分析的基础上, 结合地质、钻井、测井等解释资料, 应用三维储层建模技术, 定性定量地对前侏罗纪古地貌进行了恢复.同时建立了三维砂体、孔隙度、渗透率模型, 从生、储、盖、圈、运、保等油气成藏条件, 直观地解释了古地貌油气富集规律.依据以上模型, 预测出油气有利储集区分布在三大斜坡储集带的河流边滩砂体和河谷内的心滩处, 为勘探开发提供了可靠依据.      

中国大陆科学钻探孔区全观式三维地震采集

大陆科学钻探不仅是打一口钻,而是深部钻探同地球物理遥测结合起来的相互反馈系统,这里地球物理遥测主要是指三维深反射地震. 中国大陆科学钻探孔区三维地震调查是大陆科学钻探工程的一项重要内容. 在数据采集中提出了全观式三维地震调查新技术,它是指排列不滚动的三维地震调查,即将地震检波器铺满全部测区的一种地震采集方法,尤其适合于有限面积的三维地震工作. 这种方法的优点是：(1)快速高效; (2)叠加次数高; (3)与常规三维地震相比成本大幅度减少. 在中国大陆科学钻探孔区内进行的全观式三维地震测量,全面实现了预期目标,包括：(1) 配合钻探查明孔区地质构造,将钻探的一孔之见扩展到深6000m、长宽超过3000m的三维岩柱;(2)提供高精度定位的地壳反射体以供标定;(3)发现中、下地壳及地幔内的反射体等.