Ensemble forecasting of the Zika space‐time spread with topological data analysis
Ensemble forecasting of the Zika space‐time spread with topological data analysis
复制标题
DOI：
10.1002/env.2629
复制
发表时间：
2020-05
期刊：
影响因子：
1.7
通讯作者：
M. Soliman;V. Lyubchich;Y. Gel
中科院分区：
文献类型：
--
作者：
M. Soliman;V. Lyubchich;Y. Gel
根据世界卫生组织的记录，2015年5月，巴西首次正式报告寨卡病毒发病。随后该病迅速蔓延至美洲和东亚其他国家，影响超过100万人。寨卡病毒主要通过被感染的伊蚊（埃及伊蚊和白纹伊蚊）蚊子叮咬传播。在降水多、气温高、人口密度高的地区，蚊子大量繁殖，寨卡病毒感染流行。此类数据的非线性时空依赖性以及历史公共卫生记录的缺乏使得对病毒传播的预测特别具有挑战性。在本文中，我们通过将拓扑数据分析的概念（特别是大气变量的持久同源性）引入到病毒传播模型中来增强寨卡病毒的预测。拓扑摘要允许捕获大气变量之间的高阶依赖关系，否则这些依赖关系可能无法通过基于欧几里得距离评估的地理接近度的传统时空建模方法进行评估。我们引入了累积贝蒂数的新概念，然后将累积贝蒂数作为拓扑描述符集成到三个预测机器学习模型中：随机森林、广义提升回归和深度神经网络。此外，为了更好地量化各种不确定性来源，我们使用贝叶斯模型平均将所得的单个模型预测合并为寨卡传播预测的集合。所提出的方法被应用于预测 2018 年巴西寨卡病毒时空传播。
As per the records of the World Health Organization, the first formally reported incidence of Zika virus occurred in Brazil in May 2015. The disease then rapidly spread to other countries in Americas and East Asia, affecting more than 1,000,000 people. Zika virus is primarily transmitted through bites of infected mosquitoes of the species Aedes (Aedes aegypti and Aedes albopictus). The abundance of mosquitoes and, as a result, the prevalence of Zika virus infections are common in areas which have high precipitation, high temperature, and high population density. Nonlinear spatio‐temporal dependency of such data and lack of historical public health records make prediction of the virus spread particularly challenging. In this article, we enhance Zika forecasting by introducing the concepts of topological data analysis and, specifically, persistent homology of atmospheric variables, into the virus spread modeling. The topological summaries allow for capturing higher order dependencies among atmospheric variables that otherwise might be unassessable via conventional spatio‐temporal modeling approaches based on geographical proximity assessed via Euclidean distance. We introduce a new concept of cumulative Betti numbers and then integrate the cumulative Betti numbers as topological descriptors into three predictive machine learning models: random forest, generalized boosted regression, and deep neural network. Furthermore, to better quantify for various sources of uncertainties, we combine the resulting individual model forecasts into an ensemble of the Zika spread predictions using Bayesian model averaging. The proposed methodology is illustrated in application to forecasting of the Zika space‐time spread in Brazil in the year 2018.