{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:48:32Z","timestamp":1782755312952,"version":"3.54.5"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100008675","name":"Zayed University","doi-asserted-by":"publisher","award":["R21045"],"award-info":[{"award-number":["R21045"]}],"id":[{"id":"10.13039\/501100008675","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1371\/journal.pone.0350264","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:36:46Z","timestamp":1782754606000},"page":"e0350264","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Forecasting COVID-19 new cases using NBEATS deep learning and mobility data"],"prefix":"10.1371","volume":"21","author":[{"given":"Amril","family":"Nazir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Shorfuzzaman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Lujaini","family":"Lotfi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3946-0920","authenticated-orcid":true,"given":"Firuz","family":"Kamalov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0859-3299","authenticated-orcid":true,"given":"Sufian","family":"Badawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maen","family":"Takruri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1874-7722","authenticated-orcid":true,"given":"Abdul-Halim","family":"Jallad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"pone.0350264.ref001","author":"WHO","year":"2020"},{"key":"pone.0350264.ref002","unstructured":"Wordometer COVID-19 coronavirus pandemic. https:\/\/www.worldometers.info\/coronavirus\/"},{"issue":"21","key":"pone.0350264.ref003","doi-asserted-by":"crossref","first-page":"2010","DOI":"10.1056\/NEJMc2115596","article-title":"Differential Kinetics of Immune Responses Elicited by Covid-19 Vaccines","volume":"385","author":"A-RY Collier","year":"2021","journal-title":"N Engl J Med"},{"issue":"1","key":"pone.0350264.ref004","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1038\/s41597-020-00609-9","article-title":"A structured open dataset of government interventions in response to COVID-19","volume":"7","author":"A Desvars-Larrive","year":"2020","journal-title":"Sci Data"},{"issue":"12","key":"pone.0350264.ref005","article-title":"Effectiveness of travel restrictions in the rapid containment of human influenza: a systematic review","volume":"92","author":"ALP Mateus","year":"2014","journal-title":"Bull World Health Organ"},{"issue":"6490","key":"pone.0350264.ref006","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1126\/science.abb4218","article-title":"The effect of human mobility and control measures on the COVID-19 epidemic in China","volume":"368","author":"MUG Kraemer","year":"2020","journal-title":"Science"},{"issue":"7","key":"pone.0350264.ref007","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1038\/s41562-021-01122-8","article-title":"A global database of COVID-19 vaccinations","volume":"5","author":"E Mathieu","year":"2021","journal-title":"Nat Hum Behav"},{"key":"pone.0350264.ref008","unstructured":"Inc G. COVID-19 Community Mobility Report. 2020. https:\/\/www.google.com\/covid19\/mobility\/"},{"key":"pone.0350264.ref009","unstructured":"Inc A. COVID-19 Mobility Trends Reports. 2020. https:\/\/covid19.apple.com\/mobility"},{"issue":"11","key":"pone.0350264.ref010","doi-asserted-by":"crossref","first-page":"3481","DOI":"10.3390\/jcm9113481","article-title":"Increased Psychological Distress during COVID-19 and Quarantine in Ireland: A National Survey","volume":"9","author":"T Burke","year":"2020","journal-title":"J Clin Med"},{"key":"pone.0350264.ref011","doi-asserted-by":"crossref","unstructured":"de Palma A, Vosough S, Liao F. An overview of effects of covid-19 on mobility and lifestyle: 18 months since the outbreak. Transportation Research Part A: Policy and Practice. 2022.","DOI":"10.1016\/j.tra.2022.03.024"},{"issue":"9","key":"pone.0350264.ref012","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1016\/j.numecd.2020.05.020","article-title":"Quarantine during COVID-19 outbreak: Changes in diet and physical activity increase the risk of cardiovascular disease","volume":"30","author":"AV Mattioli","year":"2020","journal-title":"Nutr Metab Cardiovasc Dis"},{"key":"pone.0350264.ref013","first-page":"100218","article-title":"COVID-19 lockdown and reduction of traffic accidents in Tarragona province, Spain","volume":"8","author":"\u00d2 Saladi\u00e9","year":"2020","journal-title":"Transp Res Interdiscip Perspect"},{"key":"pone.0350264.ref014","doi-asserted-by":"crossref","first-page":"102022","DOI":"10.1016\/j.jairtraman.2021.102022","article-title":"COVID-19 pandemic and prospects for recovery of the global aviation industry","volume":"92","author":"K Dube","year":"2021","journal-title":"J Air Transp Manag"},{"issue":"7","key":"pone.0350264.ref015","doi-asserted-by":"crossref","first-page":"5437","DOI":"10.1007\/s00521-022-07967-y","article-title":"Interpretable tourism volume forecasting with multivariate time series under the impact of COVID-19","volume":"35","author":"B Wu","year":"2023","journal-title":"Neural Comput Appl"},{"key":"pone.0350264.ref016","doi-asserted-by":"crossref","first-page":"123990","DOI":"10.1016\/j.energy.2022.123990","article-title":"Interpretable wind speed prediction with multivariate time series and temporal fusion transformers","volume":"252","author":"B Wu","year":"2022","journal-title":"Energy"},{"issue":"1","key":"pone.0350264.ref017","doi-asserted-by":"crossref","first-page":"12238","DOI":"10.1038\/s41598-024-61730-y","article-title":"A comprehensive analysis of COVID-19 nonlinear mathematical model by incorporating the environment and social distancing","volume":"14","author":"M Riaz","year":"2024","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0350264.ref018","doi-asserted-by":"crossref","first-page":"17421","DOI":"10.1038\/s41598-021-97037-5","article-title":"The prediction and analysis of COVID-19 epidemic trend by combining LSTM and Markov method","volume":"11","author":"R Ma","year":"2021","journal-title":"Sci Rep"},{"issue":"3","key":"pone.0350264.ref019","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.3390\/su14031767","article-title":"COVID-19 Lockdown and the Impact on Mobility, Air Quality, and Utility Consumption: A Case Study from Sharjah, United Arab Emirates","volume":"14","author":"A Shanableh","year":"2022","journal-title":"Sustainability"},{"issue":"2","key":"pone.0350264.ref020","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.dsm.2023.03.003","article-title":"Time series clustering of COVID-19 pandemic-related data","volume":"6","author":"Z Luo","year":"2023","journal-title":"Data Science and Management"},{"issue":"2","key":"pone.0350264.ref021","doi-asserted-by":"crossref","first-page":"022041","DOI":"10.1088\/1757-899X\/981\/2\/022041","article-title":"Deep learning time series to forecast COVID-19 active cases in INDIA: a comparative study","volume":"981","author":"MA Shaik","year":"2020","journal-title":"IOP Conf Ser: Mater Sci Eng"},{"key":"pone.0350264.ref022","doi-asserted-by":"crossref","first-page":"109046","DOI":"10.1016\/j.oceaneng.2021.109046","article-title":"Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks","volume":"232","author":"C J\u00f6rges","year":"2021","journal-title":"Ocean Engineering"},{"issue":"1","key":"pone.0350264.ref023","first-page":"21","article-title":"Prediction of COVID-19 cases using machine learning algorithms","volume":"14","author":"G Markov","year":"2021","journal-title":"International Journal of Control and Automation"},{"key":"pone.0350264.ref024","first-page":"1109","article-title":"An enhanced on bidirectional lifi attocell access point slicing and virtualization using das2 conspire","volume":"8","author":"Y Chanti","year":"2019","journal-title":"Int J Recent Technol Eng"},{"key":"pone.0350264.ref025","doi-asserted-by":"crossref","first-page":"163655","DOI":"10.1016\/j.scitotenv.2023.163655","article-title":"Application of wastewater-based surveillance and copula time-series model for COVID-19 forecasts","volume":"885","author":"HA Jeng","year":"2023","journal-title":"Sci Total Environ"},{"key":"pone.0350264.ref026","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.neucom.2022.09.005","article-title":"Deep learning for Covid-19 forecasting: State-of-the-art review","volume":"511","author":"F Kamalov","year":"2022","journal-title":"Neurocomputing (Amst)"},{"key":"pone.0350264.ref027","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.dsm.2021.07.001","article-title":"Improving Google Flu Trends for COVID-19 estimates using Weibo posts","volume":"3","author":"S Guo","year":"2021","journal-title":"Data Science and Management"},{"key":"pone.0350264.ref028","author":"M Roser","year":"2020"},{"issue":"6","key":"pone.0350264.ref029","first-page":"390","article-title":"A survey on text classification methods through machine learning methods","volume":"12","author":"C J\u00f6rges","year":"2019","journal-title":"International Journal of Control and Automation"},{"issue":"4","key":"pone.0350264.ref030","first-page":"169","article-title":"Time series forecasting using vector quantization","volume":"29","author":"M Ali Shaik","year":"2020","journal-title":"International Journal of Advanced Science and Technology"},{"key":"pone.0350264.ref031","volume-title":"Laboratory testing for coronavirus disease 2019 (COVID-19) in suspected human cases: Interim guidance","author":"WHO","year":"2020"},{"issue":"9","key":"pone.0350264.ref032","doi-asserted-by":"crossref","first-page":"619","DOI":"10.7326\/M20-0751","article-title":"Coronavirus Disease 2019 (COVID-19): Protecting Hospitals From the Invisible","volume":"172","author":"M Klompas","year":"2020","journal-title":"Ann Intern Med"},{"key":"pone.0350264.ref033","first-page":"1126","article-title":"Research on multi-agent experiment in clustering","volume":"8","author":"MA Shaik","year":"2019","journal-title":"International Journal of Recent Technology and Engineering"},{"issue":"6","key":"pone.0350264.ref034","first-page":"390","article-title":"A survey on text classification methods through machine learning methods","volume":"12","author":"I Qureshi","year":"2019","journal-title":"Mathematical model for implementing Non Linear Time Series Forecasting using Deep Learning"},{"issue":"3","key":"pone.0350264.ref035","doi-asserted-by":"crossref","first-page":"294","DOI":"10.3390\/epidemiologia2030022","article-title":"The Role of Mobility and Sanitary Measures on the Delay of Community Transmission of COVID-19 in Costa Rica","volume":"2","author":"LA Barboza","year":"2021","journal-title":"Epidemiologia (Basel)"},{"issue":"6","key":"pone.0350264.ref036","doi-asserted-by":"crossref","first-page":"786","DOI":"10.3390\/e23060786","article-title":"Are Mobility and COVID-19 Related? A Dynamic Analysis for Portuguese Districts","volume":"23","author":"A Casa Nova","year":"2021","journal-title":"Entropy (Basel)"},{"key":"pone.0350264.ref037","doi-asserted-by":"crossref","unstructured":"Fantazzini D. Short-term forecasting of the COVID-19 pandemic using Google Trends data: evidence from 158 countries. Applied Econometrics. 2020;:Forthcoming.","DOI":"10.2139\/ssrn.3671005"},{"key":"pone.0350264.ref038","doi-asserted-by":"crossref","DOI":"10.1017\/S0950268820002757","article-title":"Community movement and COVID-19: a global study using Google\u2019s Community Mobility Reports","volume":"148","author":"M Sulyok","year":"2020","journal-title":"Epidemiol Infect"},{"key":"pone.0350264.ref039","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1080\/10911359.2020.1845903","article-title":"Stay-at-home works to fight against COVID-19: International evidence from Google mobility data","volume":"31","author":"H Yilmazkuday","year":"2021","journal-title":"Journal of Human Behavior in the Social Environment"},{"key":"pone.0350264.ref040","unstructured":"Oreshkin BN, Carpov D, Chapados N, Bengio Y. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. In: 2019. https:\/\/doi.org\/10.48550\/arXiv.1905.10437"},{"issue":"2","key":"pone.0350264.ref041","article-title":"Reporting delays improve epidemic forecasts: An analysis of COVID-19 cases across eight regions","volume":"20","author":"W Ma","year":"2024","journal-title":"PLOS Computational Biology"},{"key":"pone.0350264.ref042","author":"E Mathieu","year":"2020"},{"key":"pone.0350264.ref043"},{"key":"pone.0350264.ref044","first-page":"100167","article-title":"The impact of government measures and human mobility trend on COVID-19 related deaths in the UK","volume":"6","author":"GM Hadjidemetriou","year":"2020","journal-title":"Transp Res Interdiscip Perspect"},{"issue":"10263","key":"pone.0350264.ref045","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1016\/S0140-6736(20)32164-4","article-title":"The Brazilian Government\u2019s mistakes in responding to the COVID-19 pandemic","volume":"396","author":"S Ferigato","year":"2020","journal-title":"Lancet"},{"key":"pone.0350264.ref046","unstructured":"Insider S. The New Coronavirus Is Finally Slamming Russia. Is the Country Ready?. https:\/\/www.science.org\/content\/article\/new-coronavirus-finally-slamming-russia-country-ready"},{"key":"pone.0350264.ref047","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.compenvurbsys.2018.04.001","article-title":"Human mobility and socioeconomic status: Analysis of Singapore and Boston","volume":"72","author":"Y Xu","year":"2018","journal-title":"Computers, Environment and Urban Systems"},{"issue":"1","key":"pone.0350264.ref048","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1038\/s41467-021-21358-2","article-title":"Reduction in mobility and COVID-19 transmission","volume":"12","author":"P Nouvellet","year":"2021","journal-title":"Nat Commun"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:36:58Z","timestamp":1782754618000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350264"}},"subtitle":[],"editor":[{"given":"Jie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":48,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350264","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]}}}