Spatio-Temporal Neural Network for Fitting and Forecasting COVID-19

TL;DR

This paper introduces a novel Spatio-Temporal Neural Network (STNN) for forecasting COVID-19 spread, integrating spatial and temporal data, and demonstrates its superior accuracy over classical models through numerical simulations.

Contribution

The paper proposes a new STNN architecture with variants that improve predictability and flexibility for epidemic forecasting.

Findings

STNN outperforms classical models in accuracy.

Variants STNN-A and STNN-I enhance model flexibility.

Models effectively handle spatial and temporal data.

Abstract

We established a Spatio-Temporal Neural Network, namely STNN, to forecast the spread of the coronavirus COVID-19 outbreak worldwide in 2020. The basic structure of STNN is similar to the Recurrent Neural Network (RNN) incorporating with not only temporal data but also spatial features. Two improved STNN architectures, namely the STNN with Augmented Spatial States (STNN-A) and the STNN with Input Gate (STNN-I), are proposed, which ensure more predictability and flexibility. STNN and its variants can be trained using Stochastic Gradient Descent (SGD) algorithm and its improved variants (e.g., Adam, AdaGrad and RMSProp). Our STNN models are compared with several classical epidemic prediction models, including the fully-connected neural network (BPNN), and the recurrent neural network (RNN), the classical curve fitting models, as well as the SEIR dynamical system model. Numerical simulations demonstrate that STNN models outperform many others by providing more accurate fitting and prediction, and by handling both spatial and temporal data.