Spatial-Temporal Convolutional Network for Spread Prediction of COVID-19

TL;DR

This paper introduces a spatial-temporal convolutional neural network that predicts future COVID-19 symptom severity across regions using survey data, aiding in resource allocation and containment strategies.

Contribution

It presents a novel CNN model combining regional survey profiles with spatial-temporal data for COVID-19 spread prediction.

Findings

Accurately predicts regional symptom severity daily

Enables better hospital and lockdown planning

Uses survey data for real-time forecasting

Abstract

In this work we present a spatial-temporal convolutional neural network for predicting future COVID-19 related symptoms severity among a population, per region, given its past reported symptoms. This can help approximate the number of future Covid-19 patients in each region, thus enabling a faster response, e.g., preparing the local hospital or declaring a local lockdown where necessary. Our model is based on a national symptom survey distributed in Israel and can predict symptoms severity for different regions daily. The model includes two main parts - (1) learned region-based survey responders profiles used for aggregating questionnaires data into features (2) Spatial-Temporal 3D convolutional neural network which uses the above features to predict symptoms progression.