EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Forecasting COVID-19 new cases using NBEATS deep learning and mobility data

Amril Nazir, Mohammad Shorfuzzaman, Muhammad Lujaini Lotfi, Firuz Kamalov iD, Sufian Badawi iD, Maen Takruri, Abdul-Halim Jallad iD

PLOS One · 29.06.2026 · 21 (6) · e0350264

DOI: 10.1371/journal.pone.0350264 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 29.06.2026. Verfasst von Amril Nazir und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Systems and Technology Management, Zayed University, Abu Dhabi, United Arab Emirates. Hauptthemen laut MEDLINE: COVID-19, Deep Learning. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zayed University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

COVID-19 is a highly contagious disease transmitted primarily through human contact. Therefore, understanding population mobility is essential for predicting COVID-19 case trends. In this paper, we propose a novel deep learning approach for forecasting new COVID-19 cases using a neural architecture called Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS). The N-BEATS model effectively handles long input sequences and large output horizons without information loss or increased computational complexity. We compare the performance of N-BEATS with a state-of-the-art benchmark model, LSTM-Markov, across four major countries: the United States, the United Kingdom, Russia, and Brazil. Three distinct COVID-19 datasets from Google, Apple, and Our World in Data (OWID) were used in this study. Incorporating Google and Apple mobility data as covariates enhances both the accuracy and interpretability of the N-BEATS model. Our results show that N-BEATS consistently outperforms LSTM-Markov across all datasets and countries, consistently yielding lower Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). Furthermore, the N-BEATS model with covariates outperforms its counterpart without covariates, indicating that mobility data provide substantial value for forecasting new COVID-19 cases. Overall, this study demonstrates the effectiveness of the N-BEATS architecture in capturing pandemic dynamics and offers valuable insights for policymakers and public health officials in managing future outbreaks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Deep LearningHumansForecastingPandemicsSARS-CoV-2United StatesLong Short Term MemoryUnited KingdomPrediction AlgorithmsPredictive Learning ModelsBrazil

Autor:innen und Institutionen

  • Department of Information Systems and Technology Management, Zayed University, Abu Dhabi, United Arab Emirates.
  • Department of Software Engineering, College of Engineering and Advanced Computing, Alfaisal University, Riyadh, Saudi Arabia.
  • AnalytiCray Ltd, Kuala Lumpur, Malaysia.
  • Canadian University Dubai, Dubai, United Arab Emirates.
  • Department of Autonomous Systems, Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, Jordan.
  • College of Engineering and Technology, American University of the Middle East, Egaila, Kuwait.

ORCID-Profile: Firuz Kamalov, Sufian Badawi, Abdul-Halim Jallad

Förderung

  • Zayed University

Zitieren

APA

Nazir, A., Shorfuzzaman, M., Lotfi, M. L., Kamalov, F., Badawi, S., Takruri, M., & Jallad, A. H. (2026). Forecasting COVID-19 new cases using NBEATS deep learning and mobility data. PLOS One, 21(6), e0350264. https://doi.org/10.1371/journal.pone.0350264

Vancouver

Nazir A, Shorfuzzaman M, Lotfi ML, Kamalov F, Badawi S, Takruri M, et al. Forecasting COVID-19 new cases using NBEATS deep learning and mobility data. PLOS One. 2026;21(6):e0350264. doi:10.1371/journal.pone.0350264

BibTeX
@article{Nazir2026,
  author = {Nazir, Amril and Shorfuzzaman, Mohammad and Lotfi, Muhammad Lujaini and Kamalov, Firuz and Badawi, Sufian and Takruri, Maen and Jallad, Abdul-Halim},
  title = {Forecasting COVID-19 new cases using NBEATS deep learning and mobility data},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0350264},
  doi = {10.1371/journal.pone.0350264}
}
Kostenlos starten →