Removal of cloud cover on the satellite remote sensing image can effectively improve the availability of remote sensing images. For thin cloud cover, support vector value contourlet transform is used to achieve multi-...Removal of cloud cover on the satellite remote sensing image can effectively improve the availability of remote sensing images. For thin cloud cover, support vector value contourlet transform is used to achieve multi-scale decomposition of the area of thin cloud cover on remote sensing images. Through enhancing coefficients of high frequency and suppressing coefficients of low frequency, the thin cloud is removed. For thick cloud cover, if the areas of thick cloud cover on multi-source or multi-temporal remote sensing images do not overlap, the multi-output support vector regression learning method is used to remove this kind of thick clouds. If the thick cloud cover areas overlap, by using the multi-output learning of the surrounding areas to predict the surface features of the overlapped thick cloud cover areas, this kind of thick cloud is removed. Experimental results show that the proposed cloud removal method can effectively solve the problems of the cloud overlapping and radiation difference among multi-source images. The cloud removal image is clear and smooth.展开更多
The operational cloud-motion tracking technique fails to retrieve atmospheric motion vectors （AMVs） in areas lacking cloud; and while water vapor shown in water vapor imagery can be used, the heights assigned to the...The operational cloud-motion tracking technique fails to retrieve atmospheric motion vectors （AMVs） in areas lacking cloud; and while water vapor shown in water vapor imagery can be used, the heights assigned to the retrieved AMVs are mostly in the upper troposphere. As the noise-equivalent temperature difference （NEdT） performance of FY-2E split win- dow （10.3-11.5 μm, 11.6-12.8 μm） channels has been improved, the weak signals representing the spatial texture of water vapor and aerosols in cloud-free areas can be strengthened with algorithms based on the difference principle, and applied in calculating AMVs in the lower troposphere. This paper is a preliminary summary for this purpose, in which the principles and algorithm schemes for the temporal difference, split window difference and second-order difference （SD） methods are introduced. Results from simulation and cases experiments are reported in order to verify and evaluate the methods, based on comparison among retrievals and the ＂truth＂. The results show that all three algorithms, though not perfect in some cases, generally work well. Moreover, the SD method appears to be the best in suppressing the surface temperature influence and clarifying the spatial texture of water vapor and aerosols. The accuracy with respect to NCEP 800 hPa reanalysis data was found to be acceptable, as compared with the accuracy of the cloud motion vectors.展开更多
针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首...针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首先,提取云服务器老化数据的统计特征指标,并采用支持向量回归(Support vector regression,SVR)对统计特征指标进行数据稀疏化处理,得到支持向量(Support vectors,SVs)序列数据;然后,建立基于密度聚类的高斯函数拟合(Gaussian function fitting,GFF)模型,对不同核函数下的支持向量序列数据进行老化曲线拟合,并采用Fréchet距离优化算法选取最优老化曲线;最后,基于最优老化曲线,评估系统到达老化阈值前的RUL,以预测系统何时发生老化.在OpenStack云服务器4个老化数据集上的实验结果表明,基于RUL和SVs-GFF的云服务器老化预测方法与传统预测方法相比,具有更高的预测精度和更快的收敛速度.展开更多
基金supported by the National Natural Science Foundation of China(61172127)the Natural Science Foundation of Anhui Province(1408085MF121)
文摘Removal of cloud cover on the satellite remote sensing image can effectively improve the availability of remote sensing images. For thin cloud cover, support vector value contourlet transform is used to achieve multi-scale decomposition of the area of thin cloud cover on remote sensing images. Through enhancing coefficients of high frequency and suppressing coefficients of low frequency, the thin cloud is removed. For thick cloud cover, if the areas of thick cloud cover on multi-source or multi-temporal remote sensing images do not overlap, the multi-output support vector regression learning method is used to remove this kind of thick clouds. If the thick cloud cover areas overlap, by using the multi-output learning of the surrounding areas to predict the surface features of the overlapped thick cloud cover areas, this kind of thick cloud is removed. Experimental results show that the proposed cloud removal method can effectively solve the problems of the cloud overlapping and radiation difference among multi-source images. The cloud removal image is clear and smooth.
基金supported by the National Natural Science Foundation of China(Grant Nos.41175035 and 40475018)the National Basic Research Program of China(Grant No.2009CB421502)a project funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘The operational cloud-motion tracking technique fails to retrieve atmospheric motion vectors （AMVs） in areas lacking cloud; and while water vapor shown in water vapor imagery can be used, the heights assigned to the retrieved AMVs are mostly in the upper troposphere. As the noise-equivalent temperature difference （NEdT） performance of FY-2E split win- dow （10.3-11.5 μm, 11.6-12.8 μm） channels has been improved, the weak signals representing the spatial texture of water vapor and aerosols in cloud-free areas can be strengthened with algorithms based on the difference principle, and applied in calculating AMVs in the lower troposphere. This paper is a preliminary summary for this purpose, in which the principles and algorithm schemes for the temporal difference, split window difference and second-order difference （SD） methods are introduced. Results from simulation and cases experiments are reported in order to verify and evaluate the methods, based on comparison among retrievals and the ＂truth＂. The results show that all three algorithms, though not perfect in some cases, generally work well. Moreover, the SD method appears to be the best in suppressing the surface temperature influence and clarifying the spatial texture of water vapor and aerosols. The accuracy with respect to NCEP 800 hPa reanalysis data was found to be acceptable, as compared with the accuracy of the cloud motion vectors.
文摘针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首先,提取云服务器老化数据的统计特征指标,并采用支持向量回归(Support vector regression,SVR)对统计特征指标进行数据稀疏化处理,得到支持向量(Support vectors,SVs)序列数据;然后,建立基于密度聚类的高斯函数拟合(Gaussian function fitting,GFF)模型,对不同核函数下的支持向量序列数据进行老化曲线拟合,并采用Fréchet距离优化算法选取最优老化曲线;最后,基于最优老化曲线,评估系统到达老化阈值前的RUL,以预测系统何时发生老化.在OpenStack云服务器4个老化数据集上的实验结果表明,基于RUL和SVs-GFF的云服务器老化预测方法与传统预测方法相比,具有更高的预测精度和更快的收敛速度.
