Spatio-temporal prediction of the COVID-19 pandemic in US counties : modeling with a deep LSTM neural network

Search for this publication on Google Scholar
Thill, J. -C., Nikparvar, B., Rahman, M. M., & Hatami, F. (2021). Spatio-temporal prediction of the COVID-19 pandemic in US counties : modeling with a deep LSTM neural network. Scientific Reports.
Download PDF

Analytics

48 views ◎
4 downloads ⇓


Description

Faculty, Prediction of complex epidemiological systems such as COVID-19 is challenging on many grounds. Commonly used compartmental models struggle to handle an epidemiological process that evolves rapidly and is spatially heterogeneous. On the other hand, machine learning methods are limited at the beginning of the pandemics due to small data size for training. We propose a deep learning approach to predict future COVID-19 infection cases and deaths 1 to 4 weeks ahead at the fine granularity of US counties. The multi-variate Long Short-term Memory (LSTM) recurrent neural network is trained on multiple time series samples at the same time, including a mobility series. Results show that adding mobility as a variable and using multiple samples to train the network improve predictive performance both in terms of bias and of variance of the forecasts. We also show that the predicted results have similar accuracy and spatial patterns with a standard ensemble model used as benchmark. The model is attractive in many respects, including the fine geographic granularity of predictions and great predictive performance several weeks ahead. Furthermore, data requirement and computational intensity are reduced by substituting a single model to multiple models folded in an ensemble model.

Details
Title

Spatio-temporal prediction of the COVID-19 pandemic in US counties : modeling with a deep LSTM neural network

Author(s)

Thill, Jean-Claude
Nikparvar, Behnam
Rahman, Md. Mokhlesur
Hatami, Faizeh

UNC Charlotte Affiliate Type

Faculty

Extent

1 online resource

Date Created

2021

Genre

articles

Resource Type

text

Abstract

Prediction of complex epidemiological systems such as COVID-19 is challenging on many grounds. Commonly used compartmental models struggle to handle an epidemiological process that evolves rapidly and is spatially heterogeneous. On the other hand, machine learning methods are limited at the beginning of the pandemics due to small data size for training. We propose a deep learning approach to predict future COVID-19 infection cases and deaths 1 to 4 weeks ahead at the fine granularity of US counties. The multi-variate Long Short-term Memory (LSTM) recurrent neural network is trained on multiple time series samples at the same time, including a mobility series. Results show that adding mobility as a variable and using multiple samples to train the network improve predictive performance both in terms of bias and of variance of the forecasts. We also show that the predicted results have similar accuracy and spatial patterns with a standard ensemble model used as benchmark. The model is attractive in many respects, including the fine geographic granularity of predictions and great predictive performance several weeks ahead. Furthermore, data requirement and computational intensity are reduced by substituting a single model to multiple models folded in an ensemble model.

Subjects--Topics

Epidemiology
COVID-19 (Disease)

Is Part Of

Scientific reports

Language

English

Publisher's Version

doi:10.1038/s41598-021-01119-3

Permalink

http://hdl.handle.net/20.500.13093/work:964

Rights

This item may be protected by copyright and other related rights. Atkins Library provides access to this item for educational and research purposes only; other uses require the permission of the copyright holder.