Search

• A model for the expansion of COVID-19 in Italy, Spain and the USA is considered. • Predictions on cumulative deaths due to COVID-19 are provided. • The effect of favourable seasonal conditions is assessed in the expansion of COVID-19 in different countries. • The effect of the relaxation of lockdown is assessed in the expansion of COVID- 19 in different countries. It is well-known that the classical SIR model is unable to make accurate predictions on the course of illnesses such as COVID-19. In this paper, we show that the official data released by the authorities of several countries (Italy, Spain and The USA) regarding the expansion of COVID-19 are compatible with a non-autonomous SIR type model with vital dynamics and non-constant population, calibrated according to exponentially decaying infection and death rates. Using this calibration we construct a model whose outcomes for most relevant epidemiological paramenters, such as the number of active cases, cumulative deaths, daily new deaths and daily new cases (among others) fit available real data about the first and successive waves of COVID-19. In addition to this, we also provide predictions on the evolution of this pandemic in Italy and the USA in several plausible scenarios. [ABSTRACT FROM AUTHOR]

• Developed deep learning methods to forecast the COVID19 spread. • Five deep learning models have been compared for COVID-19 forecasting. • Time-series COVID19 data from Italy, Spain, France, China, the USA, and Australia are used. • Results demonstrate the potential of deep learning models to forecast COVID19 data. • Results show the superior performance of the Variational AutoEncoder model. The novel coronavirus (COVID-19) has significantly spread over the world and comes up with new challenges to the research community. Although governments imposing numerous containment and social distancing measures, the need for the healthcare systems has dramatically increased and the effective management of infected patients becomes a challenging problem for hospitals. Thus, accurate short-term forecasting of the number of new contaminated and recovered cases is crucial for optimizing the available resources and arresting or slowing down the progression of such diseases. Recently, deep learning models demonstrated important improvements when handling time-series data in different applications. This paper presents a comparative study of five deep learning methods to forecast the number of new cases and recovered cases. Specifically, simple Recurrent Neural Network (RNN), Long short-term memory (LSTM), Bidirectional LSTM (BiLSTM), Gated recurrent units (GRUs) and Variational AutoEncoder (VAE) algorithms have been applied for global forecasting of COVID-19 cases based on a small volume of data. This study is based on daily confirmed and recovered cases collected from six countries namely Italy, Spain, France, China, USA, and Australia. Results demonstrate the promising potential of the deep learning model in forecasting COVID-19 cases and highlight the superior performance of the VAE compared to the other algorithms. [ABSTRACT FROM AUTHOR]