基于DTW与K-means算法的河北场雨及雨型分区特征研究

Research on the Characteristics of Rainfall Events and Rain Pattern Zoning in Hebei based on Data Mining Technology

深入挖掘气象站点的观测降雨数据,研究区域降雨的雨型规律,对于洪涝灾害预警和减灾措施制订有重要意义。本文基于河北省2005—2017年3189个站点逐小时降雨观测数据,进行"场雨"的划定,进而提取历史上各场雨的累积雨量、时长指标。采用数据挖掘技术中的DTW相似性算法进行场雨雨型的自动归类,将场雨分成Ⅰ—Ⅶ共7种雨型,包括峰值在前、中、后期的3种单峰型降雨,以及3种双峰型降雨和均匀型降雨,结果显示:河北降雨过程以Ⅰ型前期单峰值降雨、Ⅲ型中期单峰值降雨居多,二者占总降雨场次的70%以上,但空间分布上存在差异;通过K-means聚类,将河北地区分成3个雨型区:(1)区,Ⅰ型和Ⅲ型降雨为主,分布在燕山丘陵气候区、冀东平原气候区和山前平原气候区。(2)区,Ⅲ型、Ⅰ型、Ⅵ型、Ⅶ型降雨并重,在冀北高原气候区,承德市南部等分散分布。(3)区,Ⅲ型降雨为主,主要分布在石家庄市南部、邯郸市、邢台市大部分地区。本文将DTW相似性算法和K-means聚类方法相结合的数据挖掘技术,可以在未来的气象大数据分析中得到更多的应用。

In-depth data mining of rainfall data and characterizing the rainfall events from meteorological records play an important role in formulation of flood disaster warning and mitigation measures.This paper analyzed a large number of hourly rainfall observations to quantify the rainfall pattern,cumulative rainfall,duration,and other indicators of rainfall events in Hebei province.First,we generated independent rainfall events based on the hourly precipitation data of 3189 stations in Hebei from 2005 to 2017.We counted the rainfall events for each station by calculating the time interval between rainfall events.Rainfall events with time interval less than 6 h were counted as a single rainfall event.Otherwise,they were regarded as independent rainfall events.Then,we calculated the occurrence time,end time,duration,hourly accumulation,and total accumulation of each rainfall event.Finally,rainfall events were divided into seven types(I-Ⅶ),including three types of single-peak rainfall(i.e.single peak in the front,middle,and end),three types of double-peak rainfall,and uniform rainfall.The Dynamic Time Warping(DTW)algorithm was used for rainfall events classification.The results show that the rainfall in Hebei province was dominated by typeⅠ(single-peak rainfall in the front)and typeⅢ(single-peak rainfall in the middle),which accounted for more than 70%of the total rainfall events with a significant spatial variation.The typeⅣ(uniform rainfall)was the least with a proportion of less than 5%.The typeⅡ(single-peak rainfall in the end)and three types of double-peak rainfall accounted for less than 25%.Through K-means clustering,the Hebei province was divided into 3 rain-type regions:district A,with type I and typeⅢrainfall mainly distributed in the Yanshan hilly climate region,the eastern Hebei plain climate region,and the piedmont plain climate region;district B,with typeⅢ,typeⅠ,typeⅥ,and typeⅦrainfall scattered in the northern Hebei plateau climate zone and southern Chengde city;and district C,with typeⅢrainfall dominated in the southern part of Shijiazhuang City,Handan City,and most of Xingtai City.In this paper,the data mining method that combines DTW similarity algorithm and K-means clustering can be applied in future meteorological big data analysis.