Deep Learning Weather Forecasting Techniques: Literature Survey

Different deep learning architectures have been developed to accommodate the non-linearity of time series datasets in the weather forecasting domain. This paper surveys the state-of-the-art studies of deep-learning-based weather forecasting according to the aspects of the design of Neural Network architectures, spatial and temporal scales, as well as the datasets and benchmarks. Then, it highlights the obtained results while focusing on the reported accuracy and the scale of prediction in terms of model generalization; i.e., whether the model is suitable for a local or a regional area, and also if it can be used for short-term or long-term predictions. Lastly, the paper outlines the independent and dependent variables for weather forecasting in each study and evaluates algorithms used for training the dataset based on their time efficiency.