Temperature Prediction Algorithm based on Spatio-temporal Prediction

Abstract

Timely and accurate temperature prediction is crucial to human production and life. However, due to the highly nonlinear nature of temperature prediction, traditional methods cannot meet the medium- and long-term temperature prediction tasks. To address the problems of large prediction errors and inadequate extraction of spatio-temporal features in existing temperature prediction algorithms, an improved deep learning framework: graph convolutional recurrent neural network (GCRNN) is proposed to solve the time series prediction problem in the field of temperature prediction. Specifically, GCRNN uses graph convolution to capture spatial correlation, and uses Encoder-Decoder architecture to capture temporal correlation. In the specific implementation process, the matrix multiplication in recurrent neural network is replaced by graph convolution operator, so as to realize the fusion and extraction of spatio- temporal features. The model is evaluated on three real temperature datasets, and the results show that GCRNN is able to effectively capture the spatio-temporal correlations of real-time temperature datasets, Compared with the existing baseline model, the prediction effect of GCRNN has achieved better results.