Epidemic Dynamics via Wavelet Theory and Machine Learning, with Applications to Covid-19

TL;DR

This paper introduces epidemic-fitted wavelets and a novel wavelet-based model selection method combined with machine learning to model and forecast Covid-19 epidemic dynamics across multiple regions.

Contribution

It presents a new wavelet theory tailored for epidemic modeling and integrates machine learning for curve fitting, enabling accurate epidemic forecasting.

Findings

Effective modeling of Covid-19 spread in multiple regions.

Accurate short-term epidemic forecasts using wavelet-based models.

Demonstrated applicability to real-world Covid-19 data.

Abstract

We introduce the concept of epidemic-fitted wavelets which comprise, in particular, as special cases the number $I(t)$ of infectious individuals at time $t$ in classical SIR models and their derivatives. We present a novel method for modelling epidemic dynamics by a model selection method using wavelet theory and, for its applications, machine learning based curve fitting techniques. Our universal models are functions that are finite linear combinations of epidemic-fitted wavelets. We apply our method by modelling and forecasting, based on the John Hopkins University dataset, the spread of the current Covid-19 (SARS-CoV-2) epidemic in France, Germany, Italy and the Czech Republic, as well as in the US federal states New York and Florida.