Typhoon forecasting method and device

Abstract

The invention discloses a typhoon forecasting method and device. The method comprises the steps of determining the geographic coordinate information of a typhoon center at a to-be-inverted moment, and obtaining a cloud picture of satellites at the to-be-inverted moment; reading geographic coordinate information in the satellite cloud picture and brightness temperature data of a plurality of preset wavebands; determining a coordinate point of the center position of the typhoon in the satellite cloud picture, and constructing a three-dimensional matrix based on waveband brightness temperature data by taking the coordinate point as a center; loading eight trained dichotomy CNN models based on a focal_loss function; 5, inputting the three-dimensional matrix data into the eight dichotomy CNN models, obtaining and outputting corresponding numerical values, wherein the typhoon grade corresponding to the maximum numerical value is the typhoon intensity category at the moment; and calculating the maximum wind speed of the typhoon at the moment according to the obtained numerical value. By adopting the technical scheme of the invention, typhoon forecasting can be carried out more effectively.

Description

technical field [0001] The invention belongs to the technical field of weather forecasting, and in particular relates to a typhoon forecasting method and device. Background technique [0002] As a serious natural disaster that occurs frequently every year, typhoon has seriously affected the production and life of our country. As an important part of typhoon disaster assessment, the prediction and simulation of typhoon is the basis for decision-making in disaster prevention and mitigation. [0003] Most of the existing typhoon cloud system prediction methods are based on numerical models. These methods only use a limited amount of data information to assimilate typhoon cloud system prediction models, and do not make full use of the full spatial information of typhoons. Therefore, these methods cannot comprehensively describe the time-varying situation of typhoons, and can only tend to predict the typhoon's level and impact. [0004] Satellite cloud images are an effective ...

AI Technical Summary

Problems solved by technology

However, these methods only utilize local visual information instead of global visual information and spatio-temporal information

Images