Predicting the distribution of COVID-19 through CGAN—Taking Macau as an example(Training set for machine learning)

Machine learning (ML) is an innovative method that is widely used in data prediction. Predicting the COVID-19 distribution using ML is essential for urban security risk assessment and governance. This study uses conditional generative adversarial network (CGAN) to construct a method to predict the COVID-19 hotspot distribution through urban texture and business formats and establishes a relationship between urban elements and COVID-19 so that machines can automatically predict the epidemic hotspots in cities. Taking Macau as an example, this method is used to determine the correlation between the urban texture and business hotspots of Macau and the new epidemic hotspot clusters. Different types of samples afforded different epidemic prediction accuracies. The results show the following: (1) CGAN can accurately predict the distribution area of COVID-19, and the accuracy can exceed 70%. (2) The results of predicting the COVID-19 distribution through urban texture and POI data of hospitals and stations are the best, with an accuracy of more than 60% in experiments in different regions of Macau. (3) The proposed method can also predict other areas in the city that may be at risk of COVID-19 and help urban epidemic prevention and control.

机器学习（ML）作为一种创新的方法，被广泛应用于数据预测领域。利用机器学习预测COVID-19的分布对于城市安全风险评估与治理至关重要。本研究采用条件生成对抗网络（CGAN）构建了一种预测COVID-19热点分布的方法，通过分析城市纹理和商业形态，建立了城市要素与COVID-19之间的关联，使机器能够自动预测城市中的疫情热点。以澳门为例，该方法被用于确定澳门城市纹理与商业热点以及新疫情热点簇之间的相关性。不同类型的样本提供了不同的疫情预测准确性。研究结果如下：（1）CGAN能够准确预测COVID-19的分布区域，其准确率可超过70%。（2）通过分析城市纹理及医院和车站的POI数据预测COVID-19分布的结果最佳，在澳门不同区域的实验中，准确率超过60%。（3）所提出的方法还可以预测城市中可能存在COVID-19风险的其他区域，并有助于城市疫情的预防和控制。