Forecasting COVID-19 Transmission in India Using Deep Learning Models

Abstract

In the past 6 months, the world has come to a standstill due to an escalation in the number of cases of COVID-19. COVID-19 is an infectious disease that was formerly called as 2019-nCoV or the novel Coronavirus 2019. COVID-19 first originated in Wuhan, China, in late December 2019, and subsequently, the World Health Organization declared it as a pandemic on 11th March, 2020. Lack of preparedness for the COVID-19 pandemic has put colossal stress on the healthcare systems of the world’s largest economies. In a short period, the disease has spread to an unexpected number of people due to its high transmission rate and doesn’t show a sign of slowing down in the near future. Estimating the rising number of cases via predictive modeling can help gauge the quantity of various medical amenities required for the treatment of patients as well as protective apparatus for essential workers and susceptible populations. In this paper, we have performed time series forecasting on the publicly available COVID-19 datasets of India using RNNs with LSTM and GRU. Additionally, we also employ the final models for analyzing similar data from different countries.