Non-stationary spatio-temporal point process modeling for high-resolution COVID-19 data
Non-stationary spatio-temporal point process modeling for high-resolution COVID-19 data
复制标题
DOI：
10.1093/jrsssc/qlad013
复制
发表时间：
2023-03-28
影响因子：
1.6
通讯作者：
Rodriguez-Cortes，Francisco J.
中科院分区：
文献类型：
--
作者：
Dong，Zheng;Zhu，Shixiang;Rodriguez-Cortes，Francisco J.
大多数COVID-19研究通常报告州或县一级的总感染数字。这种聚合往往会忽略病毒传播的细节。在本文中，我们分析了哥伦比亚卡利的高分辨率COVID-19数据集，该数据集记录了每个确诊病例的精确时间和地点。我们开发了一个非平稳时空点过程，配备了基于神经网络的核，以捕获COVID-19病例之间的异质相关性。内核经过精心设计，以增强表达性，同时保持模型的可解释性。我们还纳入了城市地标所施加的一些外部影响。我们的方法在预测新冠肺炎病例方面优于最先进的方法，能够提供有关疾病在大都市传播的个体之间时空相互作用的重要见解。
Most COVID-19 studies commonly report figures of the overall infection at a state- or county-level. This aggregation tends to miss out on fine details of virus propagation. In this paper, we analyze a high-resolution COVID-19 dataset in Cali, Colombia, that records the precise time and location of every confirmed case. We develop a non-stationary spatio-temporal point process equipped with a neural network-based kernel to capture the heterogeneous correlations among COVID-19 cases. The kernel is carefully crafted to enhance expressiveness while maintaining model interpretability. We also incorporate some exogenous influences imposed by city landmarks. Our approach outperforms the state-of-the-art in forecasting new COVID-19 cases with the capability to offer vital insights into the spatio-temporal interaction between individuals concerning the disease spread in a metropolis.