Method for predicting lightning motion by space density clustering

Abstract

The invention relates to a method for predicting lightning motion by space density clustering. The method comprises the following steps of: processing automatic lightning monitoring data through a computer, establishing a clustering analysis database, combining a geographic information system (GIS) to establish an analysis platform, performing clustering analysis on lightning data at different moments by establishing a density clustering algorithm model, setting lightning data sample screening conditions in the database, describing basic parameters of lightning density to acquire lightning sample data according to a time sequence and classifying according to a time period; establishing a lightning data space position relationship table through lightning data points and distance values; determining position characteristic points of different lightning storms; and calculating motion direction and speed along with displacement change during time lapse according to the position characteristic points of the lightning storms, and predicting positions of lightning storms to be generated in the next time period. The invention has the advantages that: the method has novel conception, a method for processing the lightning data is advanced and reasonable, and the authenticity of the lightning motion can be reflected.

Description

technical field [0001] The invention belongs to the technical field of lightning prediction and early warning, in particular to a method for predicting lightning movement by using space density clustering, which is a method for predicting lightning movement trends by using space density clustering. Background technique [0002] At present, the prediction of lightning movement is usually based on real-time lightning monitoring data to find the activity law of the time and place of lightning occurrence, and predict the future development of lightning through this law. As far as the applicant knows, because lightning activities are too discrete, independent, and have random characteristics, there has been no good way to study the law of lightning activities for a long time, and no one has found an effective means of predicting lightning movements. For the study of lightning activities It is limited to the statistics of lightning parameters and the study of lightning distributio...

AI Technical Summary

Problems solved by technology

However, the applicant found through research that there are some problems in this method: first, the thunderstorm cluster obtained by the K-Means clustering method is a regular circular shape in space, while in the natural environment, the thunderstorm cluster should be composed of a charged large area The shape of the cloud should be irregular, so the experimental results of the cluster analysis cannot truly reflect the actual distribution of the thunderstorm cluster; secondly, the K-Means clustering method must artificially specify the number of classifications, thus It can be seen that the selection of the number of classifications will seriously affect the clustering effect of lightning data, and the artificially defined factors of the algorithm adopted are too large

Finally, because the K-Means clustering method clusters according to the geometric center point of the thunderstorm group after continuous optimization and classification, its classification characteristics determine that the classification result data contains all sample data, and some isolated points that seriously affect the classification effect cannot be clustered. Elimination, will eventually lead to poor prediction of thunderstorm movement

Images