Deep learning model for forecasting COVID-19 outbreak in Egypt

Mohamed Marzouk; Nehal Elshaboury; Amr Abdel-Latif; Shimaa Azab

doi:10.1016/j.psep.2021.07.034

Deep learning model for forecasting COVID-19 outbreak in Egypt

Process Saf Environ Prot. 2021 Sep:153:363-375. doi: 10.1016/j.psep.2021.07.034. Epub 2021 Jul 24.

Authors

Mohamed Marzouk¹, Nehal Elshaboury², Amr Abdel-Latif³, Shimaa Azab⁴

Affiliations

¹ Structural Engineering Department, Faculty of Engineering, Cairo University, Egypt.
² Construction and Project Management Research Institute, Housing and Building National Research Center, Giza, Egypt.
³ Project Management Division, Alsafa Real Estate Development Inc., Cairo, Egypt.
⁴ Environmental Planning and Development Center, Institute of National Planning, (INP), Cairo, Egypt.

Abstract

The World Health Organization has declared COVID-19 as a global pandemic in early 2020. A comprehensive understanding of the epidemiological characteristics of this virus is crucial to limit its spreading. Therefore, this research applies artificial intelligence-based models to predict the prevalence of the COVID-19 outbreak in Egypt. These models are long short-term memory network (LSTM), convolutional neural network, and multilayer perceptron neural network. They are trained and validated using the dataset records from 14 February 2020 to 15 August 2020. The results of the models are evaluated using the determination coefficient and root mean square error. The LSTM model exhibits the best performance in forecasting the cumulative infections for one week and one month ahead. Finally, the LSTM model with the optimal parameter values is applied to forecast the spread of this epidemic for one month ahead using the data from 14 February 2020 to 30 June 2021. The total size of infections, recoveries, and deaths is estimated to be 285,939, 234,747, and 17,251 cases on 31 July 2021. This study could assist the decision-makers in developing and monitoring policies to confront this disease.

Keywords: COVID-19; Deep learning; Egypt; Epidemic model; Long short-term memory network.