Examining Deep Learning Models with Multiple Data Sources for COVID-19 Forecasting

TL;DR

This paper develops and analyzes deep learning models using multiple data sources and clustering techniques for accurate COVID-19 forecasting at various geographic levels, demonstrating competitive performance.

Contribution

It introduces a stacking ensemble of RNN models with clustering-based training to incorporate multiple data sources for improved COVID-19 prediction accuracy.

Findings

Simple deep learning models perform comparably or better than complex ones.

Clustering-based training enhances high-resolution forecasting.

Multi-source data improves epidemic trend predictions.

Abstract

The COVID-19 pandemic represents the most significant public health disaster since the 1918 influenza pandemic. During pandemics such as COVID-19, timely and reliable spatio-temporal forecasting of epidemic dynamics is crucial. Deep learning-based time series models for forecasting have recently gained popularity and have been successfully used for epidemic forecasting. Here we focus on the design and analysis of deep learning-based models for COVID-19 forecasting. We implement multiple recurrent neural network-based deep learning models and combine them using the stacking ensemble technique. In order to incorporate the effects of multiple factors in COVID-19 spread, we consider multiple sources such as COVID-19 confirmed and death case count data and testing data for better predictions. To overcome the sparsity of training data and to address the dynamic correlation of the disease, we propose clustering-based training for high-resolution forecasting. The methods help us to identify the similar trends of certain groups of regions due to various spatio-temporal effects. We examine the proposed method for forecasting weekly COVID-19 new confirmed cases at county-, state-, and country-level. A comprehensive comparison between different time series models in COVID-19 context is conducted and analyzed. The results show that simple deep learning models can achieve comparable or better performance when compared with more complicated models. We are currently integrating our methods as a part of our weekly forecasts that we provide state and federal authorities.