View in EDS HTML Full Text PDF Full Text

Integrating spatiotemporal features in LSTM for spatially informed COVID-19 hospitalization forecasting.

Saved in:
Bibliographic Details
Title: Integrating spatiotemporal features in LSTM for spatially informed COVID-19 hospitalization forecasting.
Authors: Wang, Zhongying1 (AUTHOR), Ngo, Thoai D.2 (AUTHOR), Zoraghein, Hamidreza3 (AUTHOR), Lucas, Benjamin1 (AUTHOR), Karimzadeh, Morteza1 (AUTHOR) karimzadeh@colorado.edu
Source: International Journal of Geographical Information Science. Aug2026, Vol. 40 Issue 8, p2622-2659. 38p.
Subjects: Long short-term memory, Spatiotemporal processes, COVID-19, Deep learning, Medical forecasting, Social distancing, Epidemiological models
Geographic Terms: United States
Abstract: The COVID-19 pandemic's severe impact highlighted the need for accurate and timely hospitalization forecasting to support effective healthcare planning. However, most forecasting models struggled, particularly during variant surges, when they were most needed. This study introduces a novel parallel-stream Long Short-Term Memory (LSTM) framework to forecast daily state-level incident hospitalizations in the United States. Our framework incorporates a spatiotemporal feature, Social Proximity to Hospitalizations (SPH), derived from Meta's Social Connectedness Index, to improve forecasts. SPH serves as a proxy for interstate population interaction, capturing transmission dynamics across space and time. Our architecture captures both short- and long-term temporal dependencies, and a multi-horizon ensembling strategy balances forecasting consistency and error. An evaluation against the COVID-19 Forecast Hub ensemble models during the Delta and Omicron surges reveals the superiority of our model. On average, our model surpasses the ensemble by 27, 42, 54, and 69 hospitalizations per state at the 7-, 14-, 21-, and 28-day horizons, respectively, during the Omicron surge. Data-ablation experiments confirm SPH's predictive power, highlighting its effectiveness in enhancing forecasting models. This research not only advances hospitalization forecasting but also underscores the significance of spatiotemporal features, such as SPH, in modeling the complex dynamics of infectious disease spread. KEY POLICY HIGHLIGHTS: 1. Deep learning can be used to more reliably forecast the spread of infectious diseases. 2. Social media friendship data can help quantify interstate disease transmission. 3. Spatial models that leverage multi-state data are more reliable for forecasting and policymaking. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 195679701
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Integrating spatiotemporal features in LSTM for spatially informed COVID-19 hospitalization forecasting.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Wang%2C+Zhongying%22">Wang, Zhongying</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ngo%2C+Thoai+D%2E%22">Ngo, Thoai D.</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zoraghein%2C+Hamidreza%22">Zoraghein, Hamidreza</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lucas%2C+Benjamin%22">Lucas, Benjamin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Karimzadeh%2C+Morteza%22">Karimzadeh, Morteza</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> karimzadeh@colorado.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Geographical+Information+Science%22">International Journal of Geographical Information Science</searchLink>. Aug2026, Vol. 40 Issue 8, p2622-2659. 38p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br /><searchLink fieldCode="DE" term="%22Spatiotemporal+processes%22">Spatiotemporal processes</searchLink><br /><searchLink fieldCode="DE" term="%22COVID-19%22">COVID-19</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+forecasting%22">Medical forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Social+distancing%22">Social distancing</searchLink><br /><searchLink fieldCode="DE" term="%22Epidemiological+models%22">Epidemiological models</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22United+States%22">United States</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The COVID-19 pandemic's severe impact highlighted the need for accurate and timely hospitalization forecasting to support effective healthcare planning. However, most forecasting models struggled, particularly during variant surges, when they were most needed. This study introduces a novel parallel-stream Long Short-Term Memory (LSTM) framework to forecast daily state-level incident hospitalizations in the United States. Our framework incorporates a spatiotemporal feature, Social Proximity to Hospitalizations (SPH), derived from Meta's Social Connectedness Index, to improve forecasts. SPH serves as a proxy for interstate population interaction, capturing transmission dynamics across space and time. Our architecture captures both short- and long-term temporal dependencies, and a multi-horizon ensembling strategy balances forecasting consistency and error. An evaluation against the COVID-19 Forecast Hub ensemble models during the Delta and Omicron surges reveals the superiority of our model. On average, our model surpasses the ensemble by 27, 42, 54, and 69 hospitalizations per state at the 7-, 14-, 21-, and 28-day horizons, respectively, during the Omicron surge. Data-ablation experiments confirm SPH's predictive power, highlighting its effectiveness in enhancing forecasting models. This research not only advances hospitalization forecasting but also underscores the significance of spatiotemporal features, such as SPH, in modeling the complex dynamics of infectious disease spread. KEY POLICY HIGHLIGHTS: 1. Deep learning can be used to more reliably forecast the spread of infectious diseases. 2. Social media friendship data can help quantify interstate disease transmission. 3. Spatial models that leverage multi-state data are more reliable for forecasting and policymaking. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Geographical Information Science is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=195679701
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/13658816.2025.2527266
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 38
        StartPage: 2622
    Subjects:
      – SubjectFull: Long short-term memory
        Type: general
      – SubjectFull: Spatiotemporal processes
        Type: general
      – SubjectFull: COVID-19
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Medical forecasting
        Type: general
      – SubjectFull: Social distancing
        Type: general
      – SubjectFull: Epidemiological models
        Type: general
      – SubjectFull: United States
        Type: general
    Titles:
      – TitleFull: Integrating spatiotemporal features in LSTM for spatially informed COVID-19 hospitalization forecasting.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Wang, Zhongying
      – PersonEntity:
          Name:
            NameFull: Ngo, Thoai D.
      – PersonEntity:
          Name:
            NameFull: Zoraghein, Hamidreza
      – PersonEntity:
          Name:
            NameFull: Lucas, Benjamin
      – PersonEntity:
          Name:
            NameFull: Karimzadeh, Morteza
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 13658816
          Numbering:
            – Type: volume
              Value: 40
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: International Journal of Geographical Information Science
              Type: main
ResultId 1