Granger causal weather time series forecasting simulation combined with mutual information

Abstract

Meteorological science is becoming more and more familiar. The internal driving relationship of weather, timing sequence and its accurate prediction are hot topics in the field of meteorology. This paper proposes a granger weather, timing sequence causal prediction method combining mutual information. In this paper, the information entropy characteristic matrix of the Granger feature set is calculated through mutual information. It while verifying the causal relationship of the weather, timing variables such as temperature, humidity and wind speed, it mines the effective input variables to achieve the purpose of reducing the dimension of time-series data features and improves the prediction accuracy of the target model. Finally, the open source weather data set is used to make a comparative experiment between qualitative and quantitative analysis of the proposed algorithm. The simulation results show that the method is feasible and effective.