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

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.     

惠州城区供电量与气象要素的关系及其预测模型

基于惠州城区2015年11月—2018年10月逐日供电量、日最高负荷和同期气象观测资料,采用相关分析和回归分析等方法,分析了城区供电量变化特征及其与气象要素的关系,建立了基于气象要素的供电量预测模型。结果表明:惠州城区夏季平均供电量和日最高负荷最多、冬季最少,4个季节供电量有显著性差异(P<0.05)。日最高负荷出现主要在10:00—12:00,但冬季仍有21.2%的概率出现在18:00—19:00。气温、相对湿度和日照时数与供电量有显著的相关关系,但不同月份相关性不同。12月—次年3月日平均气温、日最高气温和日最低气温与供电量呈显著的负相关,4—9月气温与供电量呈显著的正相关。3—4月相对湿度和供电量呈显著的正相关,而5—8月呈显著的负相关。日照时数与供电量的关系和相对湿度与供电量呈相反的相关。最后建立了3—9月和12月—次年2月气象电量和总供电量预测模型。     

高密度聚乙烯/纳米辉钼矿复合材料性能研究

以径厚为30~45 nm的辉钼矿作为导电填料,采用熔融共混法制备高密度聚乙烯/纳米辉钼矿复合材料,应用高阻计ZC-36、SEM、XRD、TG等研究复合材料的电性能、晶体结构、界面微观形貌、热性能等。研究结果表明:当纳米辉钼矿含量为25%,复合材料的体积电阻率为5.1×109Ωcm,纳米辉钼矿高定向排列,呈链状集合体;复合材料tonset分解温度提高了35℃;辉钼矿的晶体结构发生变化,(002)晶面2θ右移了1.12°,面间距缩小0.257 nm。     

Diagnosis of trace metal contamination in sediments: the example of Ensenada and El Sauzal, two harbors in Baja California, Mexico

Total metal concentrations in sediments from within Ensenada and El Sauzal Harbors are generally higher than at the mouths. Grain-size analyses suggested that this enrichment could be due to the presence of fine-grained sediments in the inner part of the harbors rather than to anthropogenic perturbations. The (Me/Al)(sample) ratios for Pb, Co, Ni and Fe were significantly higher for Ensenada Harbor relative to El Sauzal Harbor, whereas the ratios for Cd, Mn, Zn and Cu were statistically equivalent for both harbors. Calculated enrichment factors [EF(Me)=(Me/Al)(sample)/(Me/Al)(shale)] indicated that the metals showing slight enrichment were those associated with anthropogenic contamination (Pb, Zn), or probably related to primary productivity in the water column (Cd, Co). The levels of most of the metals were not greatly enriched, a consideration that is of the utmost importance when contamination issues are at stake.     

古城劲吹法治风——葫芦岛市开展县（市）、乡（镇）、村级干部国土资源法律知识宣教培训活动纪实

2008年3月,辽西大地,乍寒还暖.在葫芦岛1.04万平方公里的土地上,128个乡(镇),1276个行政村(居委会)三级干部国土资源法律知识宣教培训活动,就像冬天里的一把火,点燃了学习国土资源法律法规的热潮.     

省国土资源厅副厅长李志民在郏县检查耕地保护工作

4月15日上午,省国土资源厅副厅长李志民一行3人在郏县对耕地保护责任目标履行情况及黏土砖瓦窑厂整治情况进行了检查。     

名人读书趣闻

闻一多醉书,华罗庚猜书,侯宝林抄书,张广厚吃书,高尔基救书     

郏县国土资源局化解一起军属宅基地纠纷

11月12日上午,伴随着一阵“噼噼啪啪”的鞭炮声和喧闹的锣鼓声,3名年轻军人来到郏县国土资源局,将一面锦旗赠送给了该局领导。锦旗上书写着“军地携手共筑长城,情系国防为兵解忧”,落款是济南军区铁军师抗震救灾指挥部。     

沟道偏转地形对滑坡碎屑流运动的影响研究

在沟谷地形中,滑坡碎屑流的运动常受到地形的影响,导致其运动方向发生改变,进而影响到滑坡运动速度和堆积特征。本文利用三维离散元素法,对四川都江堰三溪村高速远程滑坡进行模拟,研究滑坡体不同部位的块体失稳后,在沟道偏转地形主导下的滑坡碎屑流前缘的运动速度、各部位滑体的速度变化过程和堆积特征,并提出沟道偏转地形耗能模型分析了地形偏转造成的动能消耗。研究结果显示:滑坡前缘在地形偏转位置运动方向发生变化,导致运动速度突降;由于滑坡不同部位的滑块相对于地形偏转点具有不同的撞击角度,导致其撞击后产生不同的偏转角度,滑块的偏转角度越大,速度变化越大;由沟道偏转地形导致的滑坡运动速度减小反映了偏转地形对滑坡的动能产生的耗散,动能耗散率与cos2θ(θ为偏转地形在水平面上的偏转角度)成反比;不同部位滑块的堆积长度随偏转角度的增大而减小。本研究分析了沟谷地形偏转对滑坡碎屑流运动速度作用机制及不同部位岩土体堆积范围的影响,可为该类地形条件下滑坡的运动机制研究和防灾减灾工作提供参考。     

工程养护海滩对"803"风暴潮的响应过程研究

研究养护海滩对风暴潮的响应过程在人工养滩工程设计与施工中具有重要意义。老龙头养护海滩在竣工半个月后遭遇“803”风暴潮,导致岸滩滩肩最大蚀退 6.5 m,沙坝坝顶最大下蚀 1.2 m。在现场测量的基础上,利用 XBeach 建立风暴潮过程 的老龙头海滩海床演变模型,研究结果表明： （1） XBeach 模拟结果与实际地形变化侵淤趋势一致,风暴潮期间人工沙坝均向岸移动,但模拟结果的侵蚀程度更大,海滩响应更加剧烈; （2） 强浪条件下人工沙坝的透射系数为 0.29~0.42,常浪条件下透射系数为 0.45~0.95,因而人工沙坝在大浪条件下掩护作用更佳; （3） 风暴潮期间人工沙坝附近破波显著,坝顶流速明显增大,最大可达 1.21 m/s,是无人工沙坝情况下的 2.3 倍,而在人工沙坝向岸侧,因波能提前耗散,流速减为 0.28 m/s,是无人工沙坝时的 0.4 倍,且没有产生离岸流。老龙头养护工程整体泥沙损失较少,易于恢复.