Deep COVID-19 Forecasting for Multiple States with Data Augmentation
This work addresses the need for accurate COVID-19 forecasting at the state level, which is incremental as it applies existing methods like transformers with enhancements to a specific domain.
The authors tackled the problem of forecasting state-level COVID-19 trends for weekly cumulative deaths in the US and incident cases in Germany using a deep learning approach, achieving some of the best results on the COVID-19 Forecast Hub.
In this work, we propose a deep learning approach to forecasting state-level COVID-19 trends of weekly cumulative death in the United States (US) and incident cases in Germany. This approach includes a transformer model, an ensemble method, and a data augmentation technique for time series. We arrange the inputs of the transformer in such a way that predictions for different states can attend to the trends of the others. To overcome the issue of scarcity of training data for this COVID-19 pandemic, we have developed a novel data augmentation technique to generate useful data for training. More importantly, the generated data can also be used for model validation. As such, it has a two-fold advantage: 1) more actual observations can be used for training, and 2) the model can be validated on data which has distribution closer to the expected situation. Our model has achieved some of the best state-level results on the COVID-19 Forecast Hub for the US and for Germany.