COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 Prediction

TL;DR

The paper introduces COURAGE, a deep learning-based method using transformer models to predict 2-week-ahead COVID-19 deaths at the county level in the US, achieving state-of-the-art accuracy.

Contribution

It presents a novel application of transformer-based self-attention models for localized COVID-19 death prediction using diverse public data sources.

Findings

Achieves state-of-the-art prediction accuracy.

Effectively captures temporal dependencies in COVID-19 data.

Utilizes publicly available data for comprehensive modeling.

Abstract

The global spread of COVID-19, the disease caused by the novel coronavirus SARS-CoV-2, has cast a significant threat to mankind. As the COVID-19 situation continues to evolve, predicting localized disease severity is crucial for advanced resource allocation. This paper proposes a method named COURAGE (COUnty aggRegation mixup AuGmEntation) to generate a short-term prediction of 2-week-ahead COVID-19 related deaths for each county in the United States, leveraging modern deep learning techniques. Specifically, our method adopts a self-attention model from Natural Language Processing, known as the transformer model, to capture both short-term and long-term dependencies within the time series while enjoying computational efficiency. Our model fully utilizes publicly available information of COVID-19 related confirmed cases, deaths, community mobility trends and demographic information, and can produce state-level prediction as an aggregation of the corresponding county-level predictions. Our numerical experiments demonstrate that our model achieves the state-of-the-art performance among the publicly available benchmark models.