论文信息 - CLOUD MODEL AND HIERARCHICAL CLUSTERING BASED SPATIAL DATA MINING METHOD AND APPLICATION

CLOUD MODEL AND HIERARCHICAL CLUSTERING BASED SPATIAL DATA MINING METHOD AND APPLICATION

The paper proposed a method of weather classification based on cloud model and hierarchical clustering. Firstly, according to the weather sampling data from FY-2C images, cluster the brightness values of five wave bands by hierarchical clustering approach based on cloud model, and generate the centres and the parameters of clusters of image features in different rainy weather types. Secondly, through the precondition cloud generator, compute the membership degree of each pixel of FY-2C images to each cluster which represented by cloud model. Lastly, determinate the precipitation weather type of corresponding weather stations. The experiments validate the proposed method. * Kun Qin, email: qinkun163@163.com

K. Qina | Min Xua | Y. Dub | Shuying Yuea

[1] R. Koffler,et al. A Procedure for Estimating Cloud Amount and Height From Satellite Infrared Radiation Data , 1973 .

[2] Michel Desbois,et al. Automatic classification of clouds on Meteosat imagery - Application to high-level clouds , 1982 .

[3] Deyi Li,et al. Artificial Intelligence with Uncertainty , 2004, CIT.

[4] Wang Yan-lei. Modification of Cloud Picture Sample and Automatic Identification of Cloud Type Based on Fuzzy Clustering Method , 2005 .

[5] Hong Mei,et al. A High-dimension Feature Spaces Clustering and Corresponding Weather Classification for Multi-spectral Satellite Images , 2006 .

[6] Hui Lin,et al. A data mining approach for heavy rainfall forecasting based on satellite image sequence analysis , 2007, Comput. Geosci..