Sea fog identification method based on support vector machine

Abstract

The invention provides a sea fog recognition method based on a support vector machine, and the method comprises the following steps: S1, obtaining satellite channel disc projection data and ship observation original data in a period of time; S2, decoding is carried out, and satellite channel grid point data x, visibility observation data y and ship position information at the corresponding time are obtained; S3, obtaining satellite channel standardization data xstd and observation point visibility binarization data ystd; and S4, generating a training and testing sample set, and training a support vector machine model; and performing sea fog recognition on to-be-detected data through the trained support vector machine model. According to the method, a new-generation static meteorological satellite sunflower No.8 is adopted as model input data, compared with a traditional threshold method in the prior art, the support vector machine has great advantages in solving the problems of small sample, nonlinearity and high-dimensional mode recognition, and the accuracy of satellite sea fog recognition can be improved.

Description

technical field [0001] The invention belongs to the technical field of meteorological prediction, in particular to a sea fog identification method based on a support vector machine. Background technique [0002] Sea fog refers to the dangerous weather in which the horizontal visibility is less than 1km due to a large number of water droplets or ice crystals produced by condensation of water vapor in the lower atmosphere at sea, shore and islands. The reduced visibility caused by sea fog has a serious impact on the navigation of ships, and is an important cause of various accidents at sea and in coastal areas. The movement and landing of sea fog also have an important impact on coastal areas, easily causing flight delays, train delays, and even serious consequences such as flight take-off and landing accidents and highway traffic accidents. Sea fog has a serious impact on production and life in offshore and coastal areas, so it is necessary to accurately identify and monitor...

AI Technical Summary

Problems solved by technology

[0005] With the continuous improvement of satellite observation technology, the number of channels of satellite-mounted sensors is increasing, and the limitations of statistical analysis methods in finding high-dimensional thresholds are gradually reflected, and the accuracy of sea fog recognition is greatly restricted.

Images