Method, device and equipment for forecasting tropical cyclone generation frequency and storage medium

Abstract

The embodiment of the invention discloses a method and device for forecasting tropical cyclone generation frequency, equipment and a storage medium, and the method comprises the steps: carrying out the stepwise regression analysis of the characteristic value of a variable which may influence the tropical cyclone generation and the generation frequency of the tropical cyclone generation, carrying out the inspection, and keeping the variable if the inspection is passed; and forecasting by using a neural network method by using the reserved variable as a characteristic value and the generation frequency generated by the tropical cyclone as a forecast quantity. According to the method for forecasting the tropical cyclone generation frequency provided by the embodiment of the invention, the influence of atmosphere and ocean on tropical cyclones is considered. The mapping relation between the characteristic values and the forecast quantity does not need to be considered, and the nonlinear relation between tropical cyclone generation and the climate background field does not need to be considered. A forecasting model is optimized, and the forecasting accuracy is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method for forecasting the generation frequency of tropical cyclones; it also relates to a device, equipment and computer-readable storage medium for forecasting the generation frequency of tropical cyclones. Background technique [0002] Many tropical cyclones (Tropical cyclones; TC) are generated around the world every year, and the Northwest Pacific is a major source of tropical cyclones. In the Northwest Pacific, the stronger tropical cyclones are collectively called tropical cyclones. Tropical cyclone is a kind of severe storm that occurs in the tropical ocean. It is one of the most powerful natural disasters on the earth. At the same time, my country is also one of the few countries in the world that are most seriously affected by tropical cyclones. The typhoon in the Northwest Pacific landed in the southeast coastal area of ​​my country. The strong wind, heavy ...

AI Technical Summary

Problems solved by technology

[0007] At present, the potential generation index of tropical cyclones is based on a certain physical process. In a statistical sense, it is an index obtained by log regression analysis. It is a statistical result of all known results, and the used The index form is almost fixed, and the accuracy rate for future forecasting is not high

Images