聚类算法在气象数据分析中的应用(论文11300字)
摘要：随着中国气象行业的发展，气象站也越来越多，每个气象站每天都在观测新的数据，随着时间的推移，气象数据变得越来越多，如何在大量的气象数据中发现数据之间的特征，将大量的气象数据变得更有价值，是准确来预测天气、深刻理解气象变化的总规律、更加有效地预防灾害性天气，以及推动气象服务水平再上新台阶的基础和关键 。
数据挖掘技术能够很好地来处理海量的数据。本文将聚类技术用于处理气象数据。以江苏省69个气象站的地面累年值月值数据集(1981-2010年）为研究对象，对气象数据进行数据预处理，利用K-means算法对江苏的气象数据来进行聚类分析，对聚类的结果按照地区来划分并将其可视化，最后对聚类结果作出分析，对城市建设、农业种植以及气象设备的规划和建设提出了相应的建议。
关键字：数据挖掘，聚类分析，气象数据分析
The Application of Clustering Algorithm in Meteorological Data Analysis
Fanchao，School of Electronic&Information Engineering,NUIST,Nanjing 210044,China
Abstract：Nowadays, with the development of China's meteorological industry, there are more and more weather stations. Every weather station observes new data every day. As time goes by, more and more meteorological data become available. How to find the characteristics between data in a large number of meteorological data and to make a great deal of meteorological data more valuable is the foundation and key to accurately predict weather, understand the general laws of meteorological changes, prevent disasters more effectively, and promote weather services to a new level.
Data mining technology can handle a great deal of data well. This article uses clustering techniques to process weather data. Based on the data set of ground-based annual value of 1989-2010 from 69 meteorological stations in Jiangsu Province, the weather data were preprocessed, and the K-means algorithm was used to analyze the weather data in Jiangsu. The results of clustering are divided according to regions and visualized. Finally, the clustering results are analyzed, and corresponding suggestions are made for urban construction, agricultural planting, and meteorological equipment planning and construction.
Key words:Data minging,Cluster analysis,Weather data analysis
目录
一绪论 1
1.1 研究背景与意义 1
1.2 国内外研究现状 1
1.3 论文研究内容 1
1.4论文构成 1
二聚类分析 1
2.1 数据挖掘简介 1
2.2 聚类技术 3
2.2.1聚类分析的简介 3
2.2.2聚类的过程 3
2.2.3聚类算法的分类 3
2.3 K-means算法 4
三聚类在气象数据分析中的应用 5
3.1 气象数据简介 5
3.1.1气象要素 5
3.1.2气象数据的特点 5
3.2气象数据预处理 6
3.3气象数据聚类 6
3.3.1月均降水量聚类 6
3.3.2月均风速聚类 9
3.3.3月均气温聚类 12
3.4聚类结果的总结与分析 15
四总结与展望 16
参考文献 18
致谢 19 |
