基于由历史气象数据修改的时空模型对COVID-19流行病的高分辨率短期预测
Bin Chen1,2, Ruming Chen1,2, Lin Zhao1
1College of Atmospheric Sciences, Lanzhou University, Lanzhou 730000, China.
Fundamental research
|June 27, 2024
概括
这项研究引入了一种新的Meteor-ConvLSTM模型,通过整合气象因素来预测每天的COVID-19病例. 该模型显著提高了预测准确度,有助于疫情控制和规划.
科学领域:
- 流行病学 流行病学
- 数据科学数据科学数据科学
- 环境科学 环境科学
背景情况:
- 准确预测2019年冠状病毒病 (COVID-19) 病例对于公共卫生和社会经济规划至关重要.
- 传统模型通常依赖于有限的,一维的时间序列数据.
- 气象因素对COVID-19传播动态的影响需要进一步调查.
研究的目的:
- 为短期COVID-19病例预测开发一个创新的时空预测模型.
- 将气象因素集成到深度学习模型中,以提高预测准确度.
- 分析COVID-19传播的空间和时间特征与天气模式相关.
主要方法:
- 制定了预测问题作为一个多维的,网格式的时间序列任务.
- 开发了一个Convolutional Long Short-Term Memory (ConvLSTM) 网络,通过整合历史气象数据进一步改进为Meteor-ConvLSTM.
- 利用空间分析技术评估10个气象因素与COVID-19进展之间的相关性.
主要成果:
- 与原来的ConvLSTM相比,Meteor-ConvLSTM模型表现出优越的性能.
- 实现了0.592的减少根平均平方误差 (RMSE) 和0.692.692的增加R平方 (R2) .
- 该模型以0.01° × 0.01°像素分辨率提供5天的预测,根据上海3.15疫情数据进行验证.
结论:
- 通过整合气象数据,Meteor-ConvLSTM有效地预测COVID-19新病例.
- 该模型为了解流行病学特征和传播动态提供了有价值的工具.
- 这种方法提高了流行病预测能力,以改善公共卫生干预措施.
相关概念视频
01:18Steps in Outbreak Investigation
122
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
122
01:07What is Weather?
18.2K
Overview
18.2K
01:50Global Climate Change
24.3K
Throughout its ~4.5 billion year history, the Earth has experienced periods of warming and cooling. However, the current drastic increase in global temperatures is well outside of the Earth’s cyclic norms, and evidence for human-caused global climate change is compelling. Paleoclimatology, the study of ancient climate conditions, provides ample evidence for human-caused global climate change by comparing recent conditions with those in the past.
24.3K