Predicting Precipitation Events Using Gaussian Mixture Model

• 作者: Haitian Ling Kunping Zhu
• 来源期刊: 数据分析和信息处理(英文)
• 学科: 医学
• 关键词: GAUSSIAN MIXTURE Model CLASSIFICATION EM Algorithm PRECIPITATION EVENT
• 年，卷（期）: sjfxhxxclyw_2017,（4）
• 页码范围: 131-139
• 页数: 9页
• 分类号: R73

摘要

In this paper, a Gaussian mixture model (GMM) based classifier is described to tell whether precipitation events will happen on a certain day at a certain time from historical meteorological data. The classifier deals with a two-class classification problem where one class represents precipitation events and the other represents non-precipitation events. The concept of ambiguity is introduced to represent cases where weather conditions between the two classes like drizzles, intermittent or overcast are more likely to happen. Six groups of experiments are carried out to evaluate the performance of the classifier using different configurations based on the observation data released by Shanghai Baoshan weather station. Specifically, a typical classification performance of about 75% accuracy, 30% precision and 80% recall is achieved for prediction tasks with a time span of 12 hours.