Forecasting COVID-19 Cases in Morocco: A Deep Learning Approach

The world is severely affected by the COVID-19 pandemic, caused by the SARS-CoV-2 virus. So far, more than 108 million confirmed cases have been recorded, and 2.3 million deaths (according to Statistica data platform). This has created a calamitous situation around the world and fears that the disease will affect everyone in future. Deep learning algorithms could be an effective solution to track COVID-19, predict its growth, and design strategies and policies to manage its spread. Our work applies a mathematical model to analyze and predict the propagation of coronavirus in Morocco by using deep learning techniques applied on time series data. In all tested models, long short-term memory (LSTM) model showed a better performance on predicting daily confirmed cases. The forecasting is based on history of daily confirmed cases recorded from March 2, 2020, the day the first case appeared in Morocco, until February 10, 2020.