Robust LS-SVM regression for ore grade estimation in a seafloor hydrothermal sulphide deposit

Due to the geological complexities of ore body formation and limited borehole sampling, this paper proposes a robust weighted least square support vectormachine (LS-SVM) regression model to solve the ore grade estimation for a seafloor hydrothermal sulphide deposit in Solwara 1, which consists of a large proportion of incomplete samples without ore types and grade values. The standard LS-SVM classification model is applied to identify the ore type for each in complete sample. Then, a weighted K-nearest neighbor (WKNN) algorithm is proposed to interpolate the missing values. Prior to modeling, the particle swarm optimization (PSO) algorithm is used to obtain an appropriate splitting for the training and test data sets so as to eliminate the large discrepancies caused by randomdivision. Coupled simulated annealing (CSA) and grid search using 10-fold cross validation techniques are adopted to determine the optimal tuning parameters in the LS-SVM models. The effectiveness of the proposed model by comparing with other well-known techniques such as inverse distance weight (IDW), ordinary kriging (OK), and back propagation (BP) neural network is demonstrated. The experimental results show that the robust weighted LS-SVM outperforms the othermethods, and has strong predictive and generalization ability.     

SMOS卫星遥感海表盐度资料处理应用研究进展

土壤湿度和海洋盐度卫星首次提供了覆盖全球的高频率、高精度、业务化的海表盐度产品,但其处理和延伸应用仍处于初级阶段,后续校准校正工作还将持续数年,如何及时把握其发展轨迹成为一个重要的科学问题.本研究从SMOS计划、数据概况、盐度反演算法、格点产品制作、多源数据融合和产品应用等方面,介绍和评述了SMOS计划及其海表盐度产品应用研究进展,着重分析了反演算法中的各种误差来源,对在轨2 a的运行情况进行了回顾、对未来的发展重点进行了展望,旨在为开发和应用SMOS产品提供参考.     

平均大潮高潮面的计算方法与比较

平均大潮高潮面在我国用作海洋测绘净空信息表示的参考面。论证了该特征潮面的定义,扩充了其含义范围,将回归潮高高潮位应用为平均大潮高潮位。分析描述了实测潮位和预报潮位统计计算方法,比较了统计方法与潮汐特征值算法的符合度,计算了平均大潮高潮位与理论最高潮位的比率。基本研究结论是:对规则半日潮和规则日潮海域,统计算法和特征值算法的结果较为一致,而混合潮海域,两种特征潮位之间存在明显差异,平均大潮高潮位计算的相关问题需深入系统论证。     

基于模糊聚类的海水水质监测技术研究

海水水质监测数据纷繁复杂,为了在海量的数据中提取有效数据进行分析,采用模糊聚类实现对监测数据的分析处 理。对监测数据分析结构做了简要说明,接着分析模糊聚类C 聚类均值算法（FCM） 不足之处,提出了基于不完整数据样本 的FCM 算法,最后采用海水赤潮数据不完整样本进行实例仿真,实验证明,该算法在处理不完整样本数据时有一定的优势。     

本刊启用DOI国际标准编码 欢迎关注使用

正本刊讯自2014年第1期起,本刊将为在《海洋学研究》中发表的每篇论文免费注册DOI号,以提高所刊载论文的全球传播面和学术影响力,推动期刊迈向全球标准化步伐。DOI是数字对象标识符(Digital Object Identifier)的缩写,为数字信息的全球唯一的永久性的身份标识,被形象地称为数字资源的身份证,具有对资源进行永久命名标识、动态解析链接的特性。文章拥有了DOI号,如     

结合速度障碍法的无人艇编队控制策略研究

在实际的工程运用中,领航者–跟随者算法无法解决无人艇在编队形成过程中的相互碰撞问题,往往需要提前确定编队初始状态,避免编队无人艇之间的相互碰撞。针对该缺陷,将速度障碍法引入领航者–跟随者算法,并将威胁评价引入速度障碍法中,以解决无人艇在编队过程中的相互碰撞问题。建立了无人艇的运动仿真平台,并对提出的无人艇编队控制策略进行了仿真试验。试验表明：该算法提高了编队控制的稳定性,降低了编队形成过程中的碰撞风险。     

海底声学底质分类的ELM-AdaBoost方法

基于自适应增强算法（AdaBoost）结合极限学习机（ELM）,通过迭代、调整、优化ELM分类器之间的权值,从而构建了具有强鲁棒性、高精度的ELM-AdaBoost强分类器,增强了现有的ELM分类器的稳定性。以珠江口海区侧扫声呐图像为实验数据,对礁石、砂、泥3类典型底质进行分类识别,该方法的平均分类精度超过90%,优于单一ELM分类器的平均分类精度85.95%,也优于LVQ、BP等传统分类器,且在分类所耗时间上也远少于传统分类器。实验结果表明,本文构建的ELM-AdaBoost方法可有效应用于海底声学底质分类,可满足实时底质分类的需求。     

Analytical method of radiation by a wave energy device with dual rectangular floating bodies

The system with one floating rectangular body on the free surface and one submerged rectangular body has been applied to a wave energy conversion device in water of finite depth. The radiation problem by this device on a plane incident wave is solved by the use of an eigenfunction expansion method, and a new analytical expression for the radiation velocity potential is obtained. The wave excitation force is calculated via the known incident wave potential and the radiation potential with a theorem of Haskind employed. To verify the correctness of this method, an example is computed respectively through the bound element method and analytical method. Results show that two numerical methods. are in good agreement, which shows that the present method is applicable. In addition, the trends of hydrodynamic coefficients and wave force are analyzed under different conditions by use of the present analytical method.