RAIN, SNOW, AND HAIL CLASSIFICATION MONITORING METHOD BASED ON SEMI-SUPERVISED DOMAIN ADAPTATION

摘要

A rain, snow, and hail classification monitoring method based on semi-supervised domain adaptation, comprising: using radar to measure the radar reflectivity of electromagnetic waves in weathers in the case of various types of precipitation water particles, wherein the various types of water particle precipitation comprise rain, snow, and hail (S10); obtaining preprocessed data in weathers in the case of various types of precipitation water particles according to the radar reflectivity in weathers in the case of various types of precipitation water particles (S20); constructing a first data set with labels and a second data set without labels according to the preprocessed data, calculating a first covariance matrix of the first data set and a second covariance matrix of the second data set, determining a first feature subspace according to the first covariance matrix, and determining a second feature subspace according to the second covariance matrix (S30); determining a kernel function according to the first feature subspace and the second feature subspace (S40); training an initial classifier according to the kernel function by using the first data set as a training sample set (S50); selecting a subset from the second data set to perform unsupervised learning of the initial classifier, so that the selected subset can provide the initial classifier with incremental knowledge to adapt to a target domain (S60); and obtaining an objective function of the initial classifier after unsupervised learning, determining an adjacency graph according to the first data set and the second data set, optimizing the objective function according to the adjacency graph to determine a final classifier, and classifying rain, snow, and hail using the final classifier (S70). The rain, snow, and hail can be accurately classified according to the present method, such that corresponding classification monitoring plans can be more accurate.