{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T01:36:53Z","timestamp":1788745013028,"version":"build-2803163510"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e.V. (DLR)"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>During the COVID-19 crisis, mechanistic models have guided evidence-based decision making. However, time-critical decisions in a dynamical environment limit the time available to gather supporting evidence. We address this bottleneck by developing a graph neural network (GNN) surrogate of an age-structured and spatially resolved mechanistic metapopulation simulation model. This combined approach complements classical modeling approaches which are mostly mechanistic and purely data-driven machine learning approaches which are often black box. Our design of experiments spans outbreak and persistent-threat regimes, up to three contact change points, and age-structured contact matrices on a spatial graph with 400 nodes representing German counties. We benchmark multiple GNN layers and identify an ARMAConv-based architecture that offers a strong accuracy\u2013runtime trade-off. Across horizons of 30\u201390 day simulation and prediction, allowing up to three contact change points, the surrogate model attains 10\u201327% mean absolute percentage error (MAPE) while delivering (near) constant runtime with respect to the forecast horizon. Our approach accelerates evaluation by up to 28\u00a0670 times compared with the mechanistic model, allowing responsive decision support in time-critical scenarios and straightforward web integration. These results show how GNN surrogates can translate complex metapopulation models into immediate, reliable tools for pandemic response.<\/jats:p>","DOI":"10.1038\/s41598-026-39431-5","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T07:54:23Z","timestamp":1770969263000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Graph neural network surrogates to leverage mechanistic expert knowledge towards reliable and immediate pandemic response"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5766-8804","authenticated-orcid":false,"given":"Agatha","family":"Schmidt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9825-365X","authenticated-orcid":false,"given":"Henrik","family":"Zunker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-8104","authenticated-orcid":false,"given":"Alexander","family":"Heinlein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0906-6984","authenticated-orcid":false,"given":"Martin J.","family":"K\u00fchn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"39431_CR1","unstructured":"European Centre for Disease Prevention and Control. Public Health and Social Measures For Health Emergencies and Pandemics in the EU\/EEA: Recommendations for Strengthening Preparedness Planning TechRep (2024)."},{"key":"39431_CR2","doi-asserted-by":"publisher","unstructured":"Daszak, P. et al. Workshop Report on Biodiversity and Pandemics of the Intergovernmental Platform on Biodiversity and Ecosystem Services (IPBES). Tech. Rep. https:\/\/doi.org\/10.5281\/zenodo.7432079 (2020).","DOI":"10.5281\/zenodo.7432079"},{"key":"39431_CR3","doi-asserted-by":"publisher","first-page":"e1009288","DOI":"10.1371\/journal.pcbi.1009288","volume":"17","author":"S Bauer","year":"2021","unstructured":"Bauer, S. et al. Relaxing restrictions at the pace of vaccination increases freedom and guards against further COVID-19 waves. PLoS Comput. Biol. 17, e1009288 (2021) (Publisher: Public Library of Science San Francisco, CA USA.).","journal-title":"PLoS Comput. Biol."},{"key":"39431_CR4","doi-asserted-by":"publisher","first-page":"e0254660","DOI":"10.1371\/journal.pone.0254660","volume":"16","author":"L Sch\u00fcler","year":"2021","unstructured":"Sch\u00fcler, L., Calabrese, J. M. & Attinger, S. Data driven high resolution modeling and spatial analyses of the COVID-19 pandemic in Germany. PLoS ONE 16, e0254660 (2021).","journal-title":"PLoS ONE"},{"key":"39431_CR5","doi-asserted-by":"crossref","unstructured":"MacDonald, N. Periodic Solutions 39\u201349 (Springer, 1978).","DOI":"10.1007\/978-3-642-93107-9_3"},{"key":"39431_CR6","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1016\/j.matcom.2025.07.045","volume":"239","author":"L Pl\u00f6tzke","year":"2026","unstructured":"Pl\u00f6tzke, L., Wendler, A., Schmieding, R. & K\u00fchn, M. J. Revisiting the linear chain trick in epidemiological models: Implications of underlying assumptions for numerical solutions. Math. Comput. Simul. 239, 823\u2013844 (2026).","journal-title":"Math. Comput. Simul."},{"key":"39431_CR7","doi-asserted-by":"publisher","first-page":"1831","DOI":"10.1007\/s00285-019-01412-w","volume":"79","author":"PJ Hurtado","year":"2019","unstructured":"Hurtado, P. J. & Kirosingh, A. S. Generalizations of the \u2018Linear Chain Trick\u2019: Incorporating more flexible dwell time distributions into mean field ODE models. J. Math. Biol. 79, 1831\u20131883 (2019).","journal-title":"J. Math. Biol."},{"key":"39431_CR8","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/S0025-5564(03)00041-5","volume":"184","author":"J Medlock","year":"2003","unstructured":"Medlock, J. & Kot, M. Spreading disease: Integro-differential equations old and new. Math. Biosci. 184, 201\u2013222 (2003).","journal-title":"Math. Biosci."},{"key":"39431_CR9","first-page":"129636","volume":"509","author":"A Wendler","year":"2026","unstructured":"Wendler, A., Pl\u00f6tzke, L., Tritzschak, H. & K\u00fchn, M. J. A nonstandard numerical scheme for a novel secir integro-differential equation-based model allowing nonexponentially distributed stay times. Appl. Math. Comput. 509, 129636 (2026).","journal-title":"Appl. Math. Comput."},{"key":"39431_CR10","doi-asserted-by":"publisher","first-page":"eabd6370","DOI":"10.1126\/sciadv.abd6370","volume":"6","author":"S Pei","year":"2020","unstructured":"Pei, S., Kandula, S. & Shaman, J. Differential effects of intervention timing on COVID-19 spread in the United States. Sci. Adv. 6, eabd6370 (2020).","journal-title":"Sci. Adv."},{"key":"39431_CR11","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1080\/13658816.2021.1873999","volume":"35","author":"X Chen","year":"2021","unstructured":"Chen, X., Zhang, A., Wang, H., Gallaher, A. & Zhu, X. Compliance and containment in social distancing: Mathematical modeling of COVID-19 across townships. Int. J. Geogr. Inf. Sci. 35, 446\u2013465 (2021).","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"39431_CR12","doi-asserted-by":"publisher","first-page":"e0245919","DOI":"10.1371\/journal.pone.0245919","volume":"16","author":"MW Levin","year":"2021","unstructured":"Levin, M. W., Shang, M. & Stern, R. Effects of short-term travel on COVID-19 spread: A novel SEIR model and case study in Minnesota. PLoS ONE 16, e0245919 (2021).","journal-title":"PLoS ONE"},{"key":"39431_CR13","first-page":"25","volume":"161","author":"J Liu","year":"2022","unstructured":"Liu, J., Ong, G. P. & Pang, V. J. Modelling effectiveness of COVID-19 pandemic control policies using an area-based SEIR model with consideration of infection during interzonal travel. Transport. Res. Part A. 161, 25\u201347 (2022).","journal-title":"Transport. Res. Part A."},{"key":"39431_CR14","doi-asserted-by":"publisher","first-page":"1012650","DOI":"10.1371\/journal.pcbi.1012630","volume":"20","author":"H Zunker","year":"2024","unstructured":"Zunker, H. et al. Novel travel time aware metapopulation models and multi-layer waning immunity for late-phase epidemic and endemic scenarios. PLOS Computat. Biol. 20, 1012650 (2024).","journal-title":"PLOS Computat. Biol."},{"key":"39431_CR15","doi-asserted-by":"publisher","first-page":"116782","DOI":"10.1016\/j.chaos.2025.116782","volume":"199","author":"H Zunker","year":"2025","unstructured":"Zunker, H., D\u00f6nges, P., Lenz, P., Contreras, S. & K\u00fchn, M. J. Risk-mediated dynamic regulation of effective contacts de-synchronizes outbreaks in metapopulation epidemic models. Chaos Solitons Fractals 199, 116782 (2025).","journal-title":"Chaos Solitons Fractals"},{"key":"39431_CR16","first-page":"059","volume":"76","author":"A Bershteyn","year":"2018","unstructured":"Bershteyn, A. et al. Implementation and applications of EMOD, an individual-based multi-disease modeling platform. Pathogens Dis. 76, 059 (2018).","journal-title":"Pathogens Dis."},{"key":"39431_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1009149","volume":"17","author":"CC Kerr","year":"2021","unstructured":"Kerr, C. C. et al. Covasim: An agent-based model of COVID-19 dynamics and interventions. PLoS Comput. Biol. 17, 1\u201332 (2021).","journal-title":"PLoS Comput. Biol."},{"key":"39431_CR18","doi-asserted-by":"crossref","unstructured":"M\u00fcller, S.\u00a0A. et al. Predicting the effects of COVID-19 related interventions in urban settings by combining activity-based modelling, agent-based simulation, and mobile phone data. medRxiv (2021).","DOI":"10.1101\/2021.02.27.21252583"},{"key":"39431_CR19","doi-asserted-by":"publisher","first-page":"110269","DOI":"10.1016\/j.compbiomed.2025.110269","volume":"193","author":"D Kerkmann","year":"2025","unstructured":"Kerkmann, D. et al. Agent-based modeling for realistic reproduction of human mobility and contact behavior to evaluate test and isolation strategies in epidemic infectious disease spread. Comput. Biol. Med. 193, 110269 (2025).","journal-title":"Comput. Biol. Med."},{"key":"39431_CR20","first-page":"571","volume":"10","author":"J Bicker","year":"2025","unstructured":"Bicker, J., Schmieding, R., Meyer-Hermann, M. & K\u00fchn, M. J. Hybrid metapopulation agent-based epidemiological models for efficient insight on the individual scale: A contribution to green computing. Infect. Dis. Model. 10, 571\u2013590 (2025).","journal-title":"Infect. Dis. Model."},{"key":"39431_CR21","doi-asserted-by":"publisher","first-page":"20240421","DOI":"10.1098\/rspa.2024.0421","volume":"481","author":"K Kehrer","year":"2025","unstructured":"Kehrer, K., Weiser, M. & Conrad, T. Hybrid PDE\u2013ODE models for efficient simulation of infection spread in epidemiology. Proc. R. Soc. A 481, 20240421. https:\/\/doi.org\/10.1098\/rspa.2024.0421 (2025).","journal-title":"Proc. R. Soc. A"},{"key":"39431_CR22","doi-asserted-by":"crossref","unstructured":"Bostanci, I. & Conrad, T. Integrating agent-based and compartmental models for infectious disease modeling: A novel hybrid approach (2024). arXiv:2407.20993.","DOI":"10.18564\/jasss.5567"},{"key":"39431_CR23","doi-asserted-by":"publisher","first-page":"110338","DOI":"10.1016\/j.chaos.2020.110338","volume":"142","author":"NM-H Tayarani","year":"2021","unstructured":"Tayarani, N.M.-H. Applications of artificial intelligence in battling against COVID-19: A literature review. Chaos Solitons Fractals 142, 110338 (2021).","journal-title":"Chaos Solitons Fractals"},{"key":"39431_CR24","doi-asserted-by":"crossref","unstructured":"Memon, S. Automated. et al. Automated Processing of Pipelines Managing Now- and Forecasting of In563 fectious Diseases. In 2024 47th MIPRO ICT and Electronics Convention (MIPRO) 1157\u2013564 1162 (IEEE, 2024)","DOI":"10.1109\/MIPRO60963.2024.10569336"},{"key":"39431_CR25","doi-asserted-by":"crossref","unstructured":"K\u00fchn, M.\u00a0J. et al. Assessment of effective mitigation and prediction of the spread of SARS-CoV-2 in Germany using demographic information and spatial resolution. Math. Biosci. 108648 (2021).","DOI":"10.1016\/j.mbs.2021.108648"},{"key":"39431_CR26","doi-asserted-by":"publisher","first-page":"e1010054","DOI":"10.1371\/journal.pcbi.1010054","volume":"18","author":"W Koslow","year":"2022","unstructured":"Koslow, W. et al. Appropriate relaxation of non-pharmaceutical interventions minimizes the risk of a resurgence in SARS-CoV-2 infections in spite of the Delta variant. PLoS Comput. Biol. 18, e1010054 (2022).","journal-title":"PLoS Comput. Biol."},{"key":"39431_CR27","doi-asserted-by":"publisher","first-page":"e0263150","DOI":"10.1371\/journal.pone.0263150","volume":"17","author":"C Angione","year":"2022","unstructured":"Angione, C., Silverman, E. & Yaneske, E. Using machine learning as a surrogate model for agent-based simulations. PLoS ONE 17, e0263150 (2022).","journal-title":"PLoS ONE"},{"key":"39431_CR28","doi-asserted-by":"crossref","unstructured":"Robertson, C., Safta, C., Collier, N., Ozik, J. & Ray, J. Bayesian calibration of stochastic agent based model via random forest (2024). ArXiv:2406.19524 [cs, stat].","DOI":"10.2172\/2540457"},{"key":"39431_CR29","unstructured":"Eurostat. Nuts 2024. https:\/\/ec.europa.eu\/eurostat\/de\/web\/gisco\/geodata\/statistical-units\/territorial-units-statistic. Accessed: 2024-10-10."},{"key":"39431_CR30","doi-asserted-by":"crossref","unstructured":"Gori, M., Monfardini, G. & Scarselli, F. A new model for learning in graph domains. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005 vol.\u00a02, 729\u2013734 vol. 2 (2005). ISSN: 2161-4407.","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"39431_CR31","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2009","unstructured":"Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61\u201380 (2009) (Conference Name: IEEE Transactions on Neural Networks).","journal-title":"IEEE Trans. Neural Netw."},{"key":"39431_CR32","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1126\/science.adi2336","volume":"382","author":"R Lam","year":"2023","unstructured":"Lam, R. et al. Learning skillful medium-range global weather forecasting. Science 382, 1416\u20131421 (2023).","journal-title":"Science"},{"key":"39431_CR33","doi-asserted-by":"crossref","unstructured":"Deng, S., Wang, S., Rangwala, H., Wang, L. & Ning, Y. Cola-gnn: Cross-location attention based graph neural networks for long-term ili prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM \u201920, 245\u2013254 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3340531.3411975"},{"key":"39431_CR34","unstructured":"Kapoor, A. et al. Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks (2020)."},{"key":"39431_CR35","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1093\/jamia\/ocaa322","volume":"28","author":"J Gao","year":"2021","unstructured":"Gao, J. et al. STAN: Spatio-temporal attention network for pandemic prediction using real-world evidence. J. Am. Med. Inform. Assoc. 28, 733\u2013743 (2021).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"39431_CR36","first-page":"4838","volume":"35","author":"G Panagopoulos","year":"2021","unstructured":"Panagopoulos, G., Nikolentzos, G. & Vazirgiannis, M. Transfer graph neural networks for pandemic forecasting. Proc. AAAI Conf. Arti. Intell. 35, 4838\u20134845 (2021) (Number: 6).","journal-title":"Proc. AAAI Conf. Arti. Intell."},{"key":"39431_CR37","doi-asserted-by":"crossref","unstructured":"Fritz, C., Dorigatti, E. & R\u00fcgamer, D. Combining graph neural networks and spatio-temporal disease models to improve the prediction of weekly covid-19 cases in germany. Sci. Rep.12 (2022).","DOI":"10.1038\/s41598-022-07757-5"},{"key":"39431_CR38","unstructured":"Robert Koch Institute (RKI). ControlCOVID: Strategie und Handreichung zur Entwicklung von Stufenkonzepten bis Fr\u00fchjahr 2021. Tech. Rep., Robert Koch Institute (2021). https:\/\/www.rki.de\/DE\/Content\/InfAZ\/N\/Neuartiges_Coronavirus\/Downloads\/Stufenplan-Fruehjahr21.pdf?_blob=publicationFile. Stand 19.03.2021, \u00c4nderung: Grenzwerte des Indikators Hospitalisierungsinzidenz."},{"key":"39431_CR39","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/j.jinf.2020.10.009","volume":"81","author":"KA Walsh","year":"2020","unstructured":"Walsh, K. A. et al. The duration of infectiousness of individuals infected with SARS-CoV-2. J. Infect. 81, 847\u2013856 (2020).","journal-title":"J. Infect."},{"key":"39431_CR40","first-page":"147","volume":"21","author":"O Puhach","year":"2023","unstructured":"Puhach, O., Meyer, B. & Eckerle, I. SARS-CoV-2 viral load and shedding kinetics. Nat. Rev. Microbiol. 21, 147\u2013161 (2023) (Publisher: Nature Publishing Group).","journal-title":"Nat. Rev. Microbiol."},{"key":"39431_CR41","unstructured":"Bicker, J. et al. MEmilio - A high performance Modular EpideMIcs simuLatIOn software for multi-scale and comparative simulations of infectious disease dynamics (2026). To be submitted."},{"key":"39431_CR42","unstructured":"Regionaldatenbank Deutschland. Fortschreibung des Bev\u00f6lkerungsstandes: 12411-04-02-4-b Bev\u00f6lkerung nach Geschlecht und Altersjahren (79) - Stichtag 31.12. - (ab 2011) regionale Ebenen (2024). Key date used: 31.12.2020."},{"key":"39431_CR43","unstructured":"Bundesagentur f\u00fcr Arbeit. Pendlerverflechtungen der sozialversicherungspflichtig Besch\u00e4ftigten nach Kreisen - Deutschland (Jahreszahlen) (2020). https:\/\/statistik.arbeitsagentur.de\/SiteGlobals\/Forms\/Suche\/Einzelheftsuche_Formular.html?nn=24390&topic_f=beschaeftigung-pendler-krpend."},{"key":"39431_CR44","unstructured":"Chollet, F. et al. Keras (2015). https:\/\/keras.io."},{"key":"39431_CR45","unstructured":"Abadi, M. et al. TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/. Software available from tensorflow.org."},{"key":"39431_CR46","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/MCI.2020.3039072","volume":"16","author":"D Grattarola","year":"2021","unstructured":"Grattarola, D. & Alippi, C. Graph Neural Networks in TensorFlow and Keras with Spektral [Application Notes]. IEEE Comput. Intell. Mag. 16, 99\u2013106 (2021).","journal-title":"IEEE Comput. Intell. Mag."},{"key":"39431_CR47","unstructured":"Fey, M. & Lenssen, J.\u00a0E. Fast Graph Representation Learning with PyTorch Geometric (2019). https:\/\/github.com\/pyg-team\/pytorch_geometric. Original-date: 2017-10-06T16:03:03Z."},{"key":"39431_CR48","unstructured":"Wang, M. et al. Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks (2020). ArXiv:1909.01315 [cs, stat]."},{"key":"39431_CR49","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 4\u201324 (2021).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"39431_CR50","unstructured":"Kipf, T.\u00a0N. & Welling, M. Semi-Supervised Classification with Graph Convolutional Networks (2017). ArXiv:1609.02907 [cs, stat]."},{"key":"39431_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3054830","volume":"PP","author":"FM Bianchi","year":"2021","unstructured":"Bianchi, F. M., Grattarola, D., Livi, L. & Alippi, C. Graph neural networks with convolutional ARMA filters. IEEE Trans. Pattern Anal. Mach. Intell. PP, 1\u20131 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39431_CR52","unstructured":"Gasteiger, J., Bojchevski, A. & G\u00fcnnemann, S. Predict then Propagate: Graph Neural Networks meet Personalized PageRank (2022). ArXiv:1810.05997 [cs, stat]."},{"key":"39431_CR53","unstructured":"Velickovic, P. et al. Graph Attention Networks (2018). ArXiv:1710.10903 [cs, stat]."},{"key":"39431_CR54","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1186\/s12879-022-07302-9","volume":"22","author":"MJ K\u00fchn","year":"2022","unstructured":"K\u00fchn, M. J. et al. Regional opening strategies with commuter testing and containment of new SARS-CoV-2 variants in Germany. BMC Infect. Dis. 22, 333 (2022).","journal-title":"BMC Infect. Dis."},{"key":"39431_CR55","doi-asserted-by":"publisher","first-page":"108315","DOI":"10.1016\/j.buildenv.2021.108315","volume":"206","author":"G Calzolari","year":"2021","unstructured":"Calzolari, G. & Liu, W. Deep learning to replace, improve, or aid CFD analysis in built environment applications: A review. Build. Environ. 206, 108315 (2021).","journal-title":"Build. Environ."},{"key":"39431_CR56","doi-asserted-by":"publisher","first-page":"112732","DOI":"10.1016\/j.cma.2019.112732","volume":"361","author":"L Sun","year":"2020","unstructured":"Sun, L., Gao, H., Pan, S. & Wang, J.-X. Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data. Comput. Methods Appl. Mech. Eng. 361, 112732 (2020).","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"39431_CR57","doi-asserted-by":"publisher","first-page":"11688","DOI":"10.1109\/TITS.2021.3106259","volume":"23","author":"R Shi","year":"2022","unstructured":"Shi, R., Mo, Z., Huang, K., Di, X. & Du, Q. A physics-informed deep learning paradigm for traffic state and fundamental diagram estimation. IEEE Trans. Intell. Transp. Syst. 23, 11688\u201311698 (2022).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"39431_CR58","doi-asserted-by":"publisher","first-page":"145301","DOI":"10.1103\/PhysRevLett.120.145301","volume":"120","author":"T Xie","year":"2018","unstructured":"Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018) (Publisher: American Physical Society).","journal-title":"Phys. Rev. Lett."},{"key":"39431_CR59","doi-asserted-by":"publisher","first-page":"e1009037","DOI":"10.1371\/journal.pcbi.1009037","volume":"17","author":"JB Maguire","year":"2021","unstructured":"Maguire, J. B., Grattarola, D., Mulligan, V. K., Klyshko, E. & Melo, H. XENet: Using a new graph convolution to accelerate the timeline for protein design on quantum computers. PLoS Comput. Biol. 17, e1009037 (2021).","journal-title":"PLoS Comput. Biol."},{"key":"39431_CR60","doi-asserted-by":"publisher","unstructured":"Bicker, J. et al. MEmilio v2.1.0 - A high performance Modular EpideMIcs simuLatIOn software. zenodo (2025). https:\/\/elib.dlr.de\/209739\/; Release version 2.1.0 code: https:\/\/doi.org\/10.5281\/zenodo.16684608.","DOI":"10.5281\/zenodo.16684608"},{"key":"39431_CR61","doi-asserted-by":"publisher","unstructured":"Schmidt, A, Zunker, H., Heinlein, A. & K\u00fchn, M. J. Supplementary code to graph neural network surrogates to leverage mechanistic expert knowledge towards reliable and immediate pandemic response (2025). https:\/\/doi.org\/10.5281\/zenodo.15055792.","DOI":"10.5281\/zenodo.15055792"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39431-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39431-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39431-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:13:18Z","timestamp":1781633598000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-39431-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["39431"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-39431-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"assertion":[{"value":"6 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6361"}}