基于集合经验模态分解的土壤重金属Cd定量反演

针对高光谱定量反演土壤重金属含量的模型精度不足的问题,本文从时频空间的角度引入时频分析法——集合经验模态分解（EEMD）。采用EEMD法分解土壤高光谱,获得不同频率的本征模态（IMF）分量,通过分析IMF分量与重金属含量的相关性,提取特征光谱,构建EEMD-SVM定量反演模型。研究结果表明,通过EEMD法分解土壤光谱,可有效地提取土壤光谱中的微弱信息;构建EEMD-SVM模型可较好地反演土壤重金属Cd含量,模型的决定系数R²为0.920 3,明显高于基于一阶微分处理光谱数据后构建的SVM模型的R²（0.786 6）。即说明在土壤重金属定量反演领域,EEMD可作为一种新的光谱处理方法。     

基于小波分解的沙尘天气发生日数预测组合模型研究——以2008—2016年策勒沙漠绿洲过渡带沙尘天气发生时序为例

新疆南疆地区是扬沙浮尘的主要高发区,风沙对当地生产生活影响严重。为揭示当地风沙天气变化特征并预测未来变化趋势,通过小波分解方法,将塔克拉玛干沙漠南缘的策勒沙漠 绿洲过渡带2008—2016年沙尘天气发生时序分解为平稳性波动项和非线性趋势项,根据两项数据的特性,针对性选取自回归(AR)模型和最小二乘支持向量机(LSSVM)进行变化趋势预测,最后利用加法原则重构实现沙尘天气发生日数时序预测。结果表明：研究区沙尘天气发生属于典型的春夏型,主要集中在3—9月,峰值出现在5月。组合模型预测值与实测值基本吻合,具有较高的预测精度（绝对误差为4.00 d, 均方根误差为3.76 d）,同时,其结果与AR模型、LSSVM模型预测结果相比较也显示出一定的优越性（组合模型相关系数相比AR、LSSVM分别提高了0.12、0.31）,具有较好的应用前景,可为研究区预防风沙灾害及指导实际生产生活提供科学依据。     

基于SVM的煤岩破裂与失稳预测模型

煤岩破裂与失稳的定量化实验是准确预测预报采空区动力学灾害的基础研究。基于采空区上覆煤岩破裂与动力学失稳相似材料模拟实验,利用支持向量机方法对煤岩破裂的不同阶段进行预测,找出大尺度采空区煤岩介质断裂与突然失稳的应力-位移-声发射“预警值(区)”,对开采中诱发动力灾害的危险源辨识及预警提供了定量化的依据,为工程现场准确、及时预报采空区煤岩断裂失稳规律提供了有效依据。     

基于地面激光技术的隧道变形监测技术

研究了将地面激光技术应用于地铁隧道变形监测,运用基于点云法向量差异的点云分割算法对点云数据进行抽稀,使用抽稀后点云数据构建地铁隧道模型,对隧道进行整体变形分析,构建地铁隧道三维模型不仅提高了变形监测精度,而且能够反映隧道整体变形趋势。将此方法应用于天津地铁一号线隧道变形监测,通过与光纤位移计结果对比,变形监测精度在4 mm以内,能够满足地铁隧道变形监测的需要。     

GIS-based groundwater potential mapping using artificial neural network and support vector machine models: the case of Boryeong city in Korea

Groundwater productivity-potential (GPP) was analysed using the data mining models of an artificial neural network (ANN) and a support vector machine (SVM) in Boryeong city, Korea. The groundwater-productivity data with specific capacity (SPC) is strongly related to hydrogeological factors, and hence the relation may allow for groundwater potential mapping from hydrogeological factors through the ANN and SVM models. A back-propagation algorithm was used for the ANN model while a polynomial kernel was adopted for the SVM model. For the validation of the GPP maps generated from the ANN and SVM models, the area-under-the-curve analysis was performed using the SPC values of well data. The accuracies achieved from the ANN and SVM models are about 83.57 and 80.83%, respectively. It proves that the ANN and SVM models will be highly conducive to developing useful groundwater resources.     

矢量分析法在福建两次飑线天气过程分析中的应用

简要介绍了准地转Q矢量分析方法,并用NCEP 1°×1°格点资料计算了Q矢量、Q矢量散度场及Q矢量锋生函数等物理量.从Q矢量流场、Q矢量散度场水平和垂直分布,及Q矢量锋生函数场分布等方面,对2005年5月5日福建前后两次飑线天气过程进行了分析.其结果表明Q矢量分析方法对强对流天气的预报具有指示作用.     

河北及周边地区岩石圈磁场变化及震前异常特征

利用2019年度大华北秋季复测156个测点的流动地磁矢量资料,获得河北及周边地区岩石圈磁场半年变化图,分析归纳河北及周边地区岩石圈磁场的总体变化特征,并研究测区内2019年12月3日河北怀安M_S3.4地震和2019年12月5日河北丰南M_S4.5地震前岩石圈磁场局部变化和异常特征。结果表明:丰南M_S4.5地震发生在H矢量的转向区,总强度F负异常的高值区,D要素负异常的高梯度带和Z值变化的高值区;怀安M_S3.4地震则发生在H矢量幅值弱化且转向区,D要素零值线附近的正值区和Z值变化的低值区。     

Ballast water as a vector of coral pathogens in the Gulf of Mexico: the case of the Cayo Arcas coral reef

The discharge of nutrients, phytoplankton and pathogenic bacteria through ballast water may threaten the Cayo Arcas reef system. To assess this threat, the quality of ballast water and presence of coral reef pathogenic bacteria in 30 oil tankers loaded at the PEMEX Cayo Arcas crude oil terminal were determined. The water transported in the ships originated from coastal, oceanic or riverine regions. Statistical associations among quality parameters and bacteria were tested using redundancy analysis (RDA). In contrast with coastal or oceanic water, the riverine water had high concentrations of coliforms, including Vibrio cholerae 01 and, Serratia marcescens and Sphingomona spp., which are frequently associated with “white pox” and “white plague type II” coral diseases. There were also high nutrient concentrations and low water quality index values (WQI and TRIX). The presence of V. cholerae 01 highlights the need for testing ballast water coming from endemic regions into Mexican ports.     

Statistical downscaling of GCM simulations to streamflow using relevance vector machine

General circulation models (GCMs), the climate models often used in assessing the impact of climate change, operate on a coarse scale and thus the simulation results obtained from GCMs are not particularly useful in a comparatively smaller river basin scale hydrology. The article presents a methodology of statistical downscaling based on sparse Bayesian learning and Relevance Vector Machine (RVM) to model streamflow at river basin scale for monsoon period (June, July, August, September) using GCM simulated climatic variables. NCEP/NCAR reanalysis data have been used for training the model to establish a statistical relationship between streamflow and climatic variables. The relationship thus obtained is used to project the future streamflow from GCM simulations. The statistical methodology involves principal component analysis, fuzzy clustering and RVM. Different kernel functions are used for comparison purpose. The model is applied to Mahanadi river basin in India. The results obtained using RVM are compared with those of state-of-the-art Support Vector Machine (SVM) to present the advantages of RVMs over SVMs. A decreasing trend is observed for monsoon streamflow of Mahanadi due to high surface warming in future, with the CCSR/NIES GCM and B2 scenario.