Ganiny Suhail, Nisar Owais
Mechanical Engineering Department, National Institute of Technology Srinagar, Hazratbal, Srinagar, J&K 190006 India.
College of Agricultural Engineering and Technology, Sher-e-Kashmir University of Agricultural Science and Technology, Shalimar, Srinagar, J&K 190025 India.
Model Earth Syst Environ. 2021;7(1):29-40. doi: 10.1007/s40808-020-01080-6. Epub 2021 Jan 19.
India, the second-most populous country in the world is witnessing a daily surge in the COVID-19 infected cases. India is currently among the worst-hit nations worldwide due to the COVID-19 pandemic and ranks just behind Brazil and the USA. The prediction of the future course of the pandemic is thus of utmost importance in order to prevent further worsening of the situation. In this paper, we develop models for the past trajectory (March 01, 2020-July 25, 2020) and also make a month-long (July 26, 2020-August 24, 2020) forecast of the future evolution of the COVID-19 pandemic in India by using an autoregressive integrated moving average (ARIMA) model. We determine the most optimal ARIMA model (ARIMA(7,2,2)) based on the statistical parameters viz. root-mean-squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and the coefficient of determination ( ). Subsequently, the developed model is used to obtain a one month-long forecast for the cumulative cases, active cases, recoveries, and the number of fatalities. According to our forecasting results, India is likely to have 3800,989 cumulative infected cases, 1634,142 cumulative active cases, 2110,697 cumulative recoveries, and 56,150 cumulative deaths by August 24, 2020, if the current trend of the pandemic continues to prevail. The implications of these forecasts are that in the upcoming month, the infection rate of COVID-19 in India is going to escalate, while the rate of recovery and the case-fatality rate is likely to reduce. In order to avert these possible scenarios, the administration and health-care personnel need to formulate and implement robust control measures, while the general public needs to be more responsible and strictly adhere to the established and newly formulated guidelines in order to slow down the spread of the pandemic and prevent it from transforming into a catastrophe.
印度作为世界上人口第二多的国家，新冠肺炎感染病例每日剧增。由于新冠疫情，印度目前是全球受影响最严重的国家之一，仅次于巴西和美国。因此，预测疫情的未来发展趋势对于防止局势进一步恶化至关重要。在本文中，我们通过自回归积分移动平均（ARIMA）模型，建立了过去轨迹（2020年3月1日至2020年7月25日）的模型，并对印度新冠肺炎疫情未来一个月（2020年7月26日至2020年8月24日）的演变进行了预测。我们根据统计参数，即均方根误差（RMSE）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）和决定系数（ ），确定了最优的ARIMA模型（ARIMA(7,2,2)）。随后，利用所建立的模型对累计病例、现存病例、康复病例和死亡病例数进行了为期一个月的预测。根据我们的预测结果，如果疫情当前趋势持续下去，到2020年8月24日，印度可能累计有3800989例感染病例、1634142例现存病例、2110697例康复病例和56150例累计死亡病例。这些预测结果意味着，在接下来的一个月里，印度新冠肺炎的感染率将上升，而康复率和病死率可能会下降。为了避免这些可能的情况，政府和医护人员需要制定并实施强有力的控制措施，而公众需要更加负责，严格遵守既定和新制定的指导方针，以减缓疫情传播，防止其演变成一场灾难。
