{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:07:15Z","timestamp":1790878035586,"version":"4.1.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Research, Technology and Space","award":["13N15742"],"award-info":[{"award-number":["13N15742"]}],"id":[{"id":"https:\/\/ror.org\/04pz7b180","id-type":"ROR","asserted-by":"crossref"}]},{"name":"German Federal Ministry of Research, Technology and Space","award":["13N15742"],"award-info":[{"award-number":["13N15742"]}],"id":[{"id":"https:\/\/ror.org\/04pz7b180","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>The COVID-19 pandemic presented severe challenges in understanding and predicting the spread of infectious diseases, necessitating innovative approaches beyond traditional epidemiological models. This study introduces an advanced method for automated model discovery using the Sparse Identification of Nonlinear Dynamics (SINDy) algorithm, leveraging a dataset from the COVID-19 outbreak in Thuringia, Germany, encompassing more than 400,000 patient records and vaccination data. We develop a flexible, data-driven model capturing pandemic dynamics, incorporating external factors and interventions into the mathematical framework. The fixed coefficient values globally determined by SINDy were not accurate for local modelling of the data, a limitation of prior SINDy-based epidemiological applications that our framework directly addresses. We therefore refined our technique based on the differential equations as found by SINDy, by investigating three modifications that account for recent local data, each offering different strengths for short-term prediction, scenario analysis, and capturing nonlinear effects, achieving an R\u00b2 of 0.87 at a one-week horizon. In a first approach, we re-optimized the coefficient values using seven days of past data, without changing the globally determined differential equation. In a second approach, we allowed a temporal dependence of the coefficient values, fitted using all previous data, in combination with regularization. As a last method, we kept the coefficients fixed to the original values but augmented the differential equation with a small neural network, locally optimized to the data of the past week. Our results link vaccination and public health measures to the pandemic's trajectory. The proposed model allows simulation of intervention scenarios, such as vaccination strategies and public health interventions. While the current study is based on retrospective data from a single region, the framework could serve as a basis for exploring responses to future outbreaks, subject to further validation.<\/jats:p>","DOI":"10.1371\/journal.pone.0344409","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:36:56Z","timestamp":1790876216000},"page":"e0344409","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated model discovery based on COVID-19 epidemiological data from Thuringia, Germany"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7217-3689","authenticated-orcid":true,"given":"Morteza","family":"Babazadeh Shareh","sequence":"first","affiliation":[{"name":"School of Computing and Communications, Lancaster University Leipzig","place":["Leipzig, Saxony, Germany"]},{"name":"Leibniz Institute of Photonic Technology","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-0829","authenticated-orcid":true,"given":"Florian","family":"Kleiner","sequence":"additional","affiliation":[{"name":"Leibniz Institute of Photonic Technology","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"B\u00f6hme","sequence":"additional","affiliation":[{"name":"Leibniz Institute of Photonic Technology","place":["Jena, Thuringia, Germany"]},{"name":"Institute of Inorganic and Analytical Chemistry, Friedrich Schiller University Jena","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corinna","family":"H\u00e4gele","sequence":"additional","affiliation":[{"name":"Leibniz Institute of Photonic Technology","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petra","family":"Dickmann","sequence":"additional","affiliation":[{"name":"Jena University Hospital","place":["Jena, Thuringia, Germany"],"department":["Department of Anaesthesiology and Intensive Care"]},{"name":"Leibniz Centre for Photonics in Infection Research (LPI)","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4950-1936","authenticated-orcid":true,"given":"Rainer","family":"Heintzmann","sequence":"additional","affiliation":[{"name":"Leibniz Institute of Photonic Technology","place":["Jena, Thuringia, Germany"]},{"name":"Institute of Physical Chemistry and Abbe Center of Photonics, Friedrich Schiller University Jena","place":["Jena, Thuringia, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"issue":"772","key":"pone.0344409.ref001","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1098\/rspa.1927.0118","article-title":"A contribution to the mathematical theory of epidemics","volume":"115","author":"WO Kermack","year":"1927","journal-title":"Proc R Soc Lond A"},{"key":"pone.0344409.ref002","first-page":"133","article-title":"Stochastic SEIR model with jumps","volume":"239","author":"X Zhang","year":"2014","journal-title":"Appl Math Comput"},{"key":"pone.0344409.ref003","doi-asserted-by":"crossref","first-page":"2010","DOI":"10.1016\/j.physa.2017.11.116","article-title":"Dynamics of a stochastic delayed SIR epidemic model with vaccination and double diseases driven by L\u00e9vy jumps","volume":"492","author":"Q Liu","year":"2018","journal-title":"Physica A: Statistical Mech Appl"},{"issue":"4","key":"pone.0344409.ref004","doi-asserted-by":"crossref","first-page":"676","DOI":"10.3390\/sym13040676","article-title":"SARS-COV-2: SIR model limitations and predictive constraints","volume":"13","author":"C Roberto Telles","year":"2021","journal-title":"Symmetry"},{"issue":"18","key":"pone.0344409.ref005","first-page":"710","article-title":"Sparse identification of nonlinear dynamics with control (SINDYc)","volume":"49","author":"SL Brunton","year":"2016","journal-title":"IFAC-PapersOnLine"},{"issue":"1","key":"pone.0344409.ref006","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s13662-020-03192-w","article-title":"Mathematical model of SIR epidemic system (COVID-19) with fractional derivative: stability and numerical analysis","volume":"2021","author":"RT Alqahtani","year":"2021","journal-title":"Adv Differ Equ"},{"issue":"1","key":"pone.0344409.ref007","doi-asserted-by":"crossref","first-page":"72","DOI":"10.3390\/forecast4010005","article-title":"SIMLR: machine learning inside the SIR model for COVID-19 forecasting","volume":"4","author":"R Vega","year":"2022","journal-title":"Forecasting"},{"issue":"2","key":"pone.0344409.ref008","doi-asserted-by":"crossref","first-page":"427","DOI":"10.3390\/appliedmath4020022","article-title":"Enhancing COVID-19 prevalence forecasting: a hybrid approach integrating epidemic differential equations and recurrent neural networks","volume":"4","author":"L Kong","year":"2024","journal-title":"AppliedMath"},{"issue":"1","key":"pone.0344409.ref009","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1038\/s41598-025-85440-1","article-title":"Leveraging dynamics informed neural networks for predictive modeling of COVID-19 spread: a hybrid SEIRV-DNNs approach","volume":"15","author":"C Cheng","year":"2025","journal-title":"Sci Rep"},{"issue":"3","key":"pone.0344409.ref010","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1011931","article-title":"Mathematical models of Plasmodium vivax transmission: a scoping review","volume":"20","author":"MN Anwar","year":"2024","journal-title":"PLoS Comput Biol"},{"issue":"6500","key":"pone.0344409.ref011","doi-asserted-by":"crossref","DOI":"10.1126\/science.abb9789","article-title":"Inferring change points in the spread of COVID-19 reveals the effectiveness of interventions","volume":"369","author":"J Dehning","year":"2020","journal-title":"Science"},{"issue":"9","key":"pone.0344409.ref012","doi-asserted-by":"crossref","first-page":"1058","DOI":"10.1007\/s00103-021-03390-1","article-title":"Der Beitrag von epidemiologischen Modellen zur Beschreibung des Ausbruchsgeschehens der COVID-19-Pandemie","volume":"64","author":"V Priesemann","year":"2021","journal-title":"Bundesgesundheitsbl"},{"issue":"11","key":"pone.0344409.ref013","doi-asserted-by":"crossref","first-page":"2416","DOI":"10.1038\/s41591-022-02064-y","article-title":"Retrospectively modeling the effects of increased global vaccine sharing on the COVID-19 pandemic","volume":"28","author":"S Moore","year":"2022","journal-title":"Nat Med"},{"issue":"1","key":"pone.0344409.ref014","doi-asserted-by":"crossref","first-page":"10870","DOI":"10.1038\/s41598-023-37118-9","article-title":"Forecasting virus outbreaks with social media data via neural ordinary differential equations","volume":"13","author":"M N\u00fa\u00f1ez","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0344409.ref015","doi-asserted-by":"crossref","first-page":"3093","DOI":"10.1038\/s41467-023-38756-3","article-title":"Evidence-driven spatiotemporal COVID-19 hospitalization prediction with Ising dynamics","volume":"14","author":"J Gao","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"pone.0344409.ref016","first-page":"228","article-title":"Observed versus estimated actual trend of COVID-19 case numbers in Cameroon: a data-driven modelling","volume":"8","author":"AB Sandie","year":"2023","journal-title":"Infect Dis Model"},{"key":"pone.0344409.ref017","author":"P Chen","year":"2022"},{"key":"pone.0344409.ref018","author":"C Rackauckas","year":"2020"},{"issue":"4","key":"pone.0344409.ref019","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v107.i04","article-title":"DataFrames.jl: flexible and fast tabular data in Julia","volume":"107","author":"M Bouchet-Valat","year":"2023","journal-title":"J Stat Softw"},{"issue":"6","key":"pone.0344409.ref020","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0249499","article-title":"Human IgG and IgA responses to COVID-19 mRNA vaccines","volume":"16","author":"AV Wisnewski","year":"2021","journal-title":"PLoS One"},{"issue":"1","key":"pone.0344409.ref021","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1186\/s12916-022-02547-2","article-title":"SARS-CoV-2 infection, vaccination, and antibody response trajectories in adults: a cohort study in Catalonia","volume":"20","author":"M Karachaliou","year":"2022","journal-title":"BMC Med"},{"issue":"8","key":"pone.0344409.ref022","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2020-039856","article-title":"Inferred duration of infectious period of SARS-CoV-2: rapid scoping review and analysis of available evidence for asymptomatic and symptomatic COVID-19 cases","volume":"10","author":"AW Byrne","year":"2020","journal-title":"BMJ Open"},{"issue":"11","key":"pone.0344409.ref023","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1016\/S2213-2600(22)00226-0","article-title":"Onset and window of SARS-CoV-2 infectiousness and temporal correlation with symptom onset: a prospective, longitudinal, community cohort study","volume":"10","author":"S Hakki","year":"2022","journal-title":"Lancet Respir Med"},{"issue":"16","key":"pone.0344409.ref024","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v098.i16","article-title":"Distributions.jl: definition and modelling of probability distributions in the JuliaStats ecosystem","volume":"98","author":"M Besan\u00e7on","year":"2021","journal-title":"J Stat Softw"},{"key":"pone.0344409.ref025","volume-title":"SciML\/DataDrivenDiffEq.jl: v1.4.0","author":"J Martensen","year":"2024"},{"issue":"1","key":"pone.0344409.ref026","doi-asserted-by":"crossref","first-page":"15","DOI":"10.5334\/jors.151","article-title":"DifferentialEquations.jl \u2013 a performant and feature-rich ecosystem for solving differential equations in Julia","volume":"5","author":"C Rackauckas","year":"2017","journal-title":"J Open Res Softw"},{"key":"pone.0344409.ref027","unstructured":"Ge H, Xu K, Ghahramani Z. Turing: a language for flexible probabilistic inference. Playa Blanca, Lanzarote, Canary Islands, 2018. 1682\u201390."},{"key":"pone.0344409.ref028","unstructured":"Rackauckas C, Ma Y, Martensen J, Warner C, Zubov K, Supekar R. DiffEqParamEstim.jl: parameter estimation tools for differential equations. 2024."},{"issue":"24","key":"pone.0344409.ref029","doi-asserted-by":"crossref","first-page":"615","DOI":"10.21105\/joss.00615","article-title":"Optim: a mathematical optimization package for Julia","volume":"3","author":"P K Mogensen","year":"2018","journal-title":"JOSS"},{"key":"pone.0344409.ref030","volume-title":"Lux: explicit parameterization of deep neural networks in Julia","author":"A Pal","year":"2023"},{"key":"pone.0344409.ref031","volume-title":"Optimization.jl: a unified optimization package","author":"VK Dixit","year":"2023"},{"issue":"4","key":"pone.0344409.ref032","first-page":"631","article-title":"Modelling financial time series with S-PLUS","volume":"90","author":"M Fischer","year":"2006","journal-title":"Allg Stat Arch"},{"key":"pone.0344409.ref033","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1016\/j.aej.2025.06.057","article-title":"Modeling and analysis of dynamical behavior in a fractional-order COVID-19 epidemic model with media coverage: a case study of Malaysia","volume":"127","author":"R Hu","year":"2025","journal-title":"Alexandria Engineering Journal"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:37:03Z","timestamp":1790876223000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0344409"}},"subtitle":[],"editor":[{"given":"Majid","family":"Bani-Yaghoub","sequence":"first","affiliation":[{"name":"University of Missouri Kansas City","place":["UNITED STATES OF AMERICA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":33,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0344409","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}