Research on meteorological temperature prediction based on machine learning

Abstract

Predicting temperature has been a great challenge in meteorology. Accurate temperature prediction is more conducive to human production and life. This study investigated the ability of artificial neural network (ANN) and random forest (RF) methods to predict short-term monthly temperatures. The study data has been processed from the global surface temperature change estimated by NASA Goddard Institute for Space Studies. The average temperature from three months ago, the average temperature two months ago, and the average temperature one month ago were used as inputs to the application model. Both the models gave comparable results, but the superiority of the artificial neural network model over the random forest model in the present study.