Mário Cardoso, A. Cavalheiro, Alexandre Borges, A. F. Duarte, A. Soares, M. Pereira, N. Nunes, L. Azevedo, Arlindo L. Oliveira
{"title":"基于时空卷积序列到序列神经网络的新冠肺炎地理空间演化模型","authors":"Mário Cardoso, A. Cavalheiro, Alexandre Borges, A. F. Duarte, A. Soares, M. Pereira, N. Nunes, L. Azevedo, Arlindo L. Oliveira","doi":"10.1145/3550272","DOIUrl":null,"url":null,"abstract":"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 complex dynamics that result from the contagion within a region and the spreading of the infection from infected neighboring regions. We use a previously developed methodology and official municipality level data from the Portuguese Directorate-General for Health (DGS), relative to the first twelve months of the pandemic, to compute an estimate of the incidence rate in each location of mainland Portugal. The resulting sequence of incidence rate maps was then used as a gold standard to test the effectiveness of different approaches in the prediction of the spatial-temporal evolution of the incidence rate. Four different methods were tested: a simple cell level autoregressive moving average (ARMA) model, a cell level vector autoregressive (VAR) model, a municipality-by-municipality compartmental SIRD model followed by direct block sequential simulation, and a new convolutional sequence-to-sequence neural network model based on the STConvS2S architecture. We conclude that the modified convolutional sequence-to-sequence neural network is the best performing method in this task, when compared with the ARMA, VAR, and SIRD models, as well as with the baseline ConvLSTM model.","PeriodicalId":43641,"journal":{"name":"ACM Transactions on Spatial Algorithms and Systems","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2021-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Modeling the Geospatial Evolution of COVID-19 using Spatio-temporal Convolutional Sequence-to-sequence Neural Networks\",\"authors\":\"Mário Cardoso, A. Cavalheiro, Alexandre Borges, A. F. Duarte, A. Soares, M. Pereira, N. Nunes, L. Azevedo, Arlindo L. Oliveira\",\"doi\":\"10.1145/3550272\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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 complex dynamics that result from the contagion within a region and the spreading of the infection from infected neighboring regions. We use a previously developed methodology and official municipality level data from the Portuguese Directorate-General for Health (DGS), relative to the first twelve months of the pandemic, to compute an estimate of the incidence rate in each location of mainland Portugal. The resulting sequence of incidence rate maps was then used as a gold standard to test the effectiveness of different approaches in the prediction of the spatial-temporal evolution of the incidence rate. Four different methods were tested: a simple cell level autoregressive moving average (ARMA) model, a cell level vector autoregressive (VAR) model, a municipality-by-municipality compartmental SIRD model followed by direct block sequential simulation, and a new convolutional sequence-to-sequence neural network model based on the STConvS2S architecture. We conclude that the modified convolutional sequence-to-sequence neural network is the best performing method in this task, when compared with the ARMA, VAR, and SIRD models, as well as with the baseline ConvLSTM model.\",\"PeriodicalId\":43641,\"journal\":{\"name\":\"ACM Transactions on Spatial Algorithms and Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2021-05-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Transactions on Spatial Algorithms and Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3550272\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"REMOTE SENSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Spatial Algorithms and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3550272","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"REMOTE SENSING","Score":null,"Total":0}
Modeling the Geospatial Evolution of COVID-19 using Spatio-temporal Convolutional Sequence-to-sequence Neural Networks
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 complex dynamics that result from the contagion within a region and the spreading of the infection from infected neighboring regions. We use a previously developed methodology and official municipality level data from the Portuguese Directorate-General for Health (DGS), relative to the first twelve months of the pandemic, to compute an estimate of the incidence rate in each location of mainland Portugal. The resulting sequence of incidence rate maps was then used as a gold standard to test the effectiveness of different approaches in the prediction of the spatial-temporal evolution of the incidence rate. Four different methods were tested: a simple cell level autoregressive moving average (ARMA) model, a cell level vector autoregressive (VAR) model, a municipality-by-municipality compartmental SIRD model followed by direct block sequential simulation, and a new convolutional sequence-to-sequence neural network model based on the STConvS2S architecture. We conclude that the modified convolutional sequence-to-sequence neural network is the best performing method in this task, when compared with the ARMA, VAR, and SIRD models, as well as with the baseline ConvLSTM model.
期刊介绍:
ACM Transactions on Spatial Algorithms and Systems (TSAS) is a scholarly journal that publishes the highest quality papers on all aspects of spatial algorithms and systems and closely related disciplines. It has a multi-disciplinary perspective in that it spans a large number of areas where spatial data is manipulated or visualized (regardless of how it is specified - i.e., geometrically or textually) such as geography, geographic information systems (GIS), geospatial and spatiotemporal databases, spatial and metric indexing, location-based services, web-based spatial applications, geographic information retrieval (GIR), spatial reasoning and mining, security and privacy, as well as the related visual computing areas of computer graphics, computer vision, geometric modeling, and visualization where the spatial, geospatial, and spatiotemporal data is central.