Samsun University, Faculty of Engineering, Industrial Engineering Department, 55420 Samsun, Turkey.
Sci Total Environ. 2020 Aug 10;729:138817. doi: 10.1016/j.scitotenv.2020.138817. Epub 2020 Apr 22.
At the end of December 2019, coronavirus disease 2019 (COVID-19) appeared in Wuhan city, China. As of April 15, 2020, >1.9 million COVID-19 cases were confirmed worldwide, including >120,000 deaths. There is an urgent need to monitor and predict COVID-19 prevalence to control this spread more effectively. Time series models are significant in predicting the impact of the COVID-19 outbreak and taking the necessary measures to respond to this crisis. In this study, Auto-Regressive Integrated Moving Average (ARIMA) models were developed to predict the epidemiological trend of COVID-19 prevalence of Italy, Spain, and France, the most affected countries of Europe. The prevalence data of COVID-19 from 21 February 2020 to 15 April 2020 were collected from the World Health Organization website. Several ARIMA models were formulated with different ARIMA parameters. ARIMA (0,2,1), ARIMA (1,2,0), and ARIMA (0,2,1) models with the lowest MAPE values (4.7520, 5.8486, and 5.6335) were selected as the best models for Italy, Spain, and France, respectively. This study shows that ARIMA models are suitable for predicting the prevalence of COVID-19 in the future. The results of the analysis can shed light on understanding the trends of the outbreak and give an idea of the epidemiological stage of these regions. Besides, the prediction of COVID-19 prevalence trends of Italy, Spain, and France can help take precautions and policy formulation for this epidemic in other countries.
2019 年 12 月底，新型冠状病毒疾病（COVID-19）在中国武汉市出现。截至 2020 年 4 月 15 日，全球已确诊超过 190 万例 COVID-19 病例，其中包括超过 12 万人死亡。迫切需要监测和预测 COVID-19 的流行情况，以更有效地控制这种传播。时间序列模型在预测 COVID-19 爆发的影响和采取必要措施应对这一危机方面具有重要意义。在这项研究中，开发了自回归综合移动平均（ARIMA）模型，以预测欧洲受影响最严重的国家意大利、西班牙和法国 COVID-19 流行的流行病学趋势。从 2020 年 2 月 21 日至 2020 年 4 月 15 日，从世界卫生组织网站收集了 COVID-19 的流行数据。制定了几个具有不同 ARIMA 参数的 ARIMA 模型。具有最低平均绝对百分比误差（MAPE）值（4.7520、5.8486 和 5.6335）的 ARIMA（0,2,1）、ARIMA（1,2,0）和 ARIMA（0,2,1）模型分别被选为意大利、西班牙和法国的最佳模型。这项研究表明，ARIMA 模型适合预测 COVID-19 的未来流行情况。分析结果可以帮助了解疫情的趋势，并了解这些地区的流行病学阶段。此外，对意大利、西班牙和法国 COVID-19 流行趋势的预测，可以帮助其他国家为这一流行病做好预防和政策制定工作。
