A method and apparatus for predicting dangerous weather events based on a multiple incremental regression tree model

Abstract

The invention relates to a method and a device for predicting dangerous weather events based on a multiple incremental regression tree model. The method comprises the following steps: 1) reading the historical meteorological observation data and taking the meteorological characteristic data and the dangerous weather event record as the sample data set; 2) establish a training data matrix and a verification data matrix according to that sample data set; 3) setting model parameters of the multiple incremental regression tree model; 4) input a training data matrix and a verification data matrix,training that multiple incremental regression tree model to obtain a trained multiple incremental regression tree model; 5) inputting the prediction data matrix to the trained multiple incremental regression tree model to obtain the occurrence probability of the future dangerous weather event. The invention can significantly improve the prediction accuracy rate of the dangerous weather event.

Description

technical field [0001] The invention relates to the field of meteorological science and the field of computer technology, in particular to a method and device for predicting dangerous weather events based on a multiple incremental regression tree model. Background technique [0002] Hazardous weather refers to weather processes that may endanger the safety of flight and ground facilities, generally including: poor visibility, low clouds, cloud cover, high winds, hail, cumulonimbus, thunderstorms, tornadoes or hurricanes. These hazardous weather conditions often lead to catastrophic accidents in aircraft flight. Accurate prediction of dangerous weather events can provide decision-making basis for dangerous weather warnings, ensure flight safety, and reduce casualties and economic losses. [0003] Numerical weather forecasting and dynamic-statistical methods based on numerical forecasting are commonly used in the existing forecasting methods of hazardous weather events. [0...

AI Technical Summary

Problems solved by technology

[0007] The above numerical forecasting methods need to use a lot of computing resources and time, and rely on the manual analysis of forecasters

However, dynamical-statistical methods, support vector machines, and neural network methods currently need to use the results of numerical forecasting to calculate multiple parameters based on empirical formulas, and build models by manually selecting predictors, and their prediction accuracy is not high.

Images