A novel pyramid temporal causal network for weather prediction

In the field of deep learning, sequence prediction methods have been proposed to address the weather prediction issue by using discrete weather data over a period of time to predict future weather. However, extracting and utilizing feature information of different time scales from historical meteorological data for weather prediction remains a challenge. In this paper, we propose a novel model called the Pyramid Temporal Causal Network (PTCN), which consists of a stack of multiple causal dilated blocks that can utilize multi-scale temporal features. By collecting features from all the causal dilated blocks, PTCN can utilize feature information of different time scales. We evaluate PTCN on the Weather Forecasting Dataset 2018 (WFD2018) and show that it benefits from multi-scale features. Additionally, we propose a multivariate loss function (MVLoss) for multivariate prediction. The MVLoss is able to accurately fit small variance variables, unlike the mean square error (MSE) loss function. Experiments on multiple prediction tasks demonstrate that the proposed MVLoss not only significantly improves the prediction accuracy of small variance variables, but also improves the average prediction accuracy of the model.