Modeling the Geospatial Evolution of COVID-19 using Spatio-temporal Convolutional Sequence-to-sequence Neural Networks

@article{Cardoso2021ModelingTG,
  title={Modeling the Geospatial Evolution of COVID-19 using Spatio-temporal Convolutional Sequence-to-sequence Neural Networks},
  author={M{\'a}rio Cardoso and Andr{\'e}a de F{\'a}tima Cavalheiro and Alexandre Borges and Ana F. Duarte and Am{\'i}lcar Soares and Maria Jo{\~a}o Pereira and Nuno Jardim Nunes and Leonardo Azevedo and Arlindo L. Oliveira},
  journal={ACM Transactions on Spatial Algorithms and Systems},
  year={2021},
  volume={8},
  pages={1 - 19}
}
Europe was hit hard by the COVID-19 pandemic and Portugal was severely affected, having suffered three waves in the first twelve months. Approximately between January 19th and February 5th 2021 Portugal was the country in the world with the largest incidence rate, with 14-day incidence rates per 100,000 inhabitants in excess of 1,000. Despite its importance, accurate prediction of the geospatial evolution of COVID-19 remains a challenge, since existing analytical methods fail to capture the… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 36 REFERENCES

A package for geostatistical integration of coarse and fine scale data

Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

This paper proposes the convolutional LSTM (ConvLSTM) and uses it to build an end-to-end trainable model for the precipitation nowcasting problem and shows that it captures spatiotemporal correlations better and consistently outperforms FC-L STM and the state-of-the-art operational ROVER algorithm.

Geostatistical COVID-19 infection risk maps for Portugal

This work proposes to apply direct block sequential simulation to model the spatial distribution of the COVID-19 infection risk in mainland Portugal and shows the regions with greater risks of infection and the critical dynamics related to its development over time.

Social disparities in the first wave of COVID-19 incidence rates in Germany: a county-scale explainable machine learning approach

Objectives Knowledge about the socioeconomic spread of the first wave of COVID-19 infections in Germany is scattered across different studies. We explored whether COVID-19 incidence rates differed

Prevalence of Asymptomatic SARS-CoV-2 Infection

An extended Weight Kernel Density Estimation model forecasts COVID-19 onset risk and identifies spatiotemporal variations of lockdown effects in China

The authors find that the Wuhan lockdown delayed COVID-19 peak onset by 1–2 days and decreased onset risk by up to 21%.

Social disparities in the first wave of COVID-19 infections in Germany: A county-scale explainable machine learning approach

An ecological study design exploring regional correlates of COVID-19 diagnoses in Germany found features related to economic and educational characteristics of the young population in a county played an important role at the beginning of the pandemic up to the 2nd lockdown phase, while mitigation measures and beliefs about the seriousness of thePandemic as well as the compliance with mitigation measures put lower SES groups at higher risks later on.

A multimethod approach for county-scale geospatial analysis of emerging infectious diseases: a cross-sectional case study of COVID-19 incidence in Germany

The multimethod ESDA approach provided unique insights into spatial and aspatial non-stationarities of COVID-19 incidence in Germany and suggested that measures to implement social distancing and reduce unnecessary travel may be important methods for reducing contagion.

Geospatial digital monitoring of COVID-19 cases at high spatiotemporal resolution