{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:21:40Z","timestamp":1787664100653,"version":"build-2736575974"},"reference-count":44,"publisher":"AIP Publishing","issue":"8","funder":[{"DOI":"10.13039\/501100021778","name":"Agencia Nacional de Promoci\u00f3n de la Investigaci\u00f3n, el Desarrollo Tecnol\u00f3gico y la Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PICT2021-I130"],"award-info":[{"award-number":["PICT2021-I130"]}],"id":[{"id":"10.13039\/501100021778","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002923","name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","doi-asserted-by":"publisher","award":["DEEPMET PIET-R 29820250100118CO"],"award-info":[{"award-number":["DEEPMET PIET-R 29820250100118CO"]}],"id":[{"id":"10.13039\/501100002923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012478","name":"Secretaria de Ciencia y Tecnolog\u00eda - Universidad Nacional de C\u00f3rdoba","doi-asserted-by":"publisher","award":["Proyecto Consolidar 33620230100671CB"],"award-info":[{"award-number":["Proyecto Consolidar 33620230100671CB"]}],"id":[{"id":"10.13039\/100012478","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012478","name":"Secretaria de Ciencia y Tecnolog\u00eda - Universidad Nacional de C\u00f3rdoba","doi-asserted-by":"publisher","award":["Proyecto Consolidar Proyecto Consolidar 2023-258-E-UNC-SECYT#ACTIP"],"award-info":[{"award-number":["Proyecto Consolidar Proyecto Consolidar 2023-258-E-UNC-SECYT#ACTIP"]}],"id":[{"id":"10.13039\/100012478","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002923","name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","doi-asserted-by":"publisher","award":["PIP 11220200101100CO"],"award-info":[{"award-number":["PIP 11220200101100CO"]}],"id":[{"id":"10.13039\/501100002923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021778","name":"Agencia Nacional de Promoci\u00f3n de la Investigaci\u00f3n, el Desarrollo Tecnol\u00f3gico y la Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PICT2019-3095"],"award-info":[{"award-number":["PICT2019-3095"]}],"id":[{"id":"10.13039\/501100021778","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021778","name":"ANPCYT","doi-asserted-by":"publisher","award":["PICT2019-3095"],"award-info":[{"award-number":["PICT2019-3095"]}],"id":[{"id":"10.13039\/501100021778","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:p>Understanding pedestrian dynamics is critical for mitigating crowd-related risks and improving public safety. In this work, we propose a novel data-driven mesoscopic modeling framework that combines the kinetic theory of active particles (KTAPs) with data assimilation techniques, thereby offering a data-driven learning approach applicable to collective systems with learning and decision-making behavior, in line with recent KTAP developments in this area. The framework uses an ensemble Kalman filter to sequentially estimate the time-dependent spatial distribution of pedestrians and model parameters by fusing observations with the mesoscopic forward model state. Through a series of twin experiments, we show that the panic factor\u2014a key behavioral parameter\u2014is identifiable within this framework. We also evaluate the robustness of the approach by assimilating synthetic observations generated by an agent-based model (ABM). This setup introduces structural model error because the ABM is governed by microscopic rules that differ fundamentally from the mesoscopic kinetic equations. Despite this discrepancy, the ensemble Kalman filter, through the observation-based innovation term, successfully drives the kinetic model to track the observed pedestrian density while simultaneously recovering the panic factor. In this framework, observations act as a physical constraint on the evolution of the kinetic model. Crowd-dynamics models, including ABMs and kinetic models, often rely on phenomenological terms to describe social interactions, with parameters that are highly uncertain. Our findings indicate that in such systems, free-running simulations inevitably may diverge from the true state, whereas an online data-driven approach effectively constrains the system\u2019s trajectory to its underlying dynamical manifold.<\/jats:p>","DOI":"10.1063\/5.0346463","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:49:25Z","timestamp":1787662165000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Data-driven crowd dynamics using kinetic theory and ensemble-based data assimilation"],"prefix":"10.1063","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5414-3672","authenticated-orcid":false,"given":"Santiago","family":"Rosa","sequence":"first","affiliation":[{"name":"Facultad de Matem\u00e1tica, Astronom\u00eda, F\u00edsica y Computaci\u00f3n, Universidad Nacional de C\u00f3rdoba 1 , C\u00f3rdoba,","place":["Argentina"]},{"name":"Instituto de F\u00edsica Enrique Gaviola, CONICET 2 , C\u00f3rdoba,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3992-8044","authenticated-orcid":false,"given":"Manuel","family":"Pulido","sequence":"additional","affiliation":[{"name":"Facultad de Ciencias Exactas, Naturales y Agrimensura, Universidad Nacional del Nordeste 3 , Corrientes,","place":["Argentina"]},{"name":"Instituto de Modelado e Innovaci\u00f3n Tecnol\u00f3gica, CONICET 4 , Corrientes,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9452-4400","authenticated-orcid":false,"given":"Orlando","family":"Billoni","sequence":"additional","affiliation":[{"name":"Facultad de Matem\u00e1tica, Astronom\u00eda, F\u00edsica y Computaci\u00f3n, Universidad Nacional de C\u00f3rdoba 1 , C\u00f3rdoba,","place":["Argentina"]},{"name":"Instituto de F\u00edsica Enrique Gaviola, CONICET 2 , C\u00f3rdoba,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1319-9730","authenticated-orcid":false,"given":"Juan","family":"Martin Guerrieri","sequence":"additional","affiliation":[{"name":"Facultad de Ciencias Exactas, Naturales y Agrimensura, Universidad Nacional del Nordeste 3 , Corrientes,","place":["Argentina"]},{"name":"Instituto de Modelado e Innovaci\u00f3n Tecnol\u00f3gica, CONICET 4 , Corrientes,","place":["Argentina"]},{"name":"Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires 5 , Buenos Aires,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7982-6793","authenticated-orcid":false,"given":"Juan","family":"Pablo Agnelli","sequence":"additional","affiliation":[{"name":"Facultad de Matem\u00e1tica, Astronom\u00eda, F\u00edsica y Computaci\u00f3n, Universidad Nacional de C\u00f3rdoba 1 , C\u00f3rdoba,","place":["Argentina"]},{"name":"Centro de Investigaci\u00f3n y Estudios de Matem\u00e1tica, CONICET 6 , C\u00f3rdoba,","place":["Argentina"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"2026082508491923300_c1","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1038\/s41598-023-29000-5","article-title":"An urban crowd flow model integrating geographic characteristics","volume":"13","year":"2023","journal-title":"Sci. Rep."},{"key":"2026082508491923300_c2","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1002\/for.3216","article-title":"Data-driven predictive modeling of citywide crowd flow for urban safety management: A case study of Beijing, China","volume":"44","year":"2025","journal-title":"J. Forecast."},{"key":"2026082508491923300_c3","doi-asserted-by":"publisher","first-page":"16549","DOI":"10.1038\/s41598-019-53300-4","article-title":"The social physics collective","volume":"9","year":"2019","journal-title":"Sci. Rep."},{"key":"2026082508491923300_c4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2021.10.005","article-title":"Social physics","volume":"948","year":"2022","journal-title":"Phys. Rep."},{"key":"2026082508491923300_c5","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/35035023","article-title":"Simulating dynamical features of escape panic","volume":"407","year":"2000","journal-title":"Nature"},{"key":"2026082508491923300_c6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1287\/trsc.1040.0108","article-title":"Self-organized pedestrian crowd dynamics: Experiments, simulations, and design solutions","volume":"39","year":"2005","journal-title":"Transport. Sci."},{"key":"2026082508491923300_c7","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/j.trc.2013.04.009","article-title":"Enhancing the panic escape of crowd through architectural design","volume":"37","year":"2013","journal-title":"Transport. Res. Part C Emerg. Technol."},{"key":"2026082508491923300_c8","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/S0191-2615(01)00015-7","article-title":"A continuum theory for the flow of pedestrians","volume":"36","year":"2002","journal-title":"Transport. Res. Part B Methodol."},{"key":"2026082508491923300_c9","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","article-title":"Social force model for pedestrian dynamics","volume":"51","year":"1995","journal-title":"Phys. Rev. E"},{"key":"2026082508491923300_c10","doi-asserted-by":"publisher","first-page":"073102","DOI":"10.1063\/5.0149995","article-title":"Anticipation dynamics of pedestrians based on the elliptical social force model","volume":"33","year":"2023","journal-title":"Chaos"},{"key":"2026082508491923300_c11","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1080\/13658816.2019.1622015","article-title":"Flood evacuation simulations using cellular automata and multiagent systems-a human-environment relationship perspective","volume":"33","year":"2019","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"2026082508491923300_c12","doi-asserted-by":"publisher","first-page":"093131","DOI":"10.1063\/5.0148977","article-title":"Emergence of intelligent collective motion in a group of agents with memory","volume":"33","year":"2023","journal-title":"Chaos"},{"key":"2026082508491923300_c13","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1142\/S0219525908001854","article-title":"From crowd dynamics to crowd safety: A video-based analysis","volume":"11","year":"2008","journal-title":"Adv. Complex Syst."},{"key":"2026082508491923300_c14","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1142\/S0218202526400026","article-title":"New trends in kinetic theory toward the complexity of living systems","volume":"36","year":"2026","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0218202526500387","article-title":"Scientific machine learning for collective systems: Physics-brain-guided social-learning to decision-making","volume":"36","year":"2026","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c16","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1142\/S0218202515500049","article-title":"A kinetic theory approach to the dynamics of crowd evacuation from bounded domains","volume":"25","year":"2015","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c17","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1142\/S0218202521400030","article-title":"A kinetic theory approach for 2D crowd dynamics with emotional contagion","volume":"31","year":"2021","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c18","doi-asserted-by":"publisher","first-page":"123","DOI":"10.3390\/sym17010123","article-title":"Spatial kinetic modeling of crowd evacuation: Coupling social behavior and infectious disease contagion","volume":"17","year":"2025","journal-title":"Symmetry"},{"key":"2026082508491923300_c19","doi-asserted-by":"publisher","first-page":"1611","DOI":"10.1142\/S0218202523500379","article-title":"Human behavioral crowds review, critical analysis and research perspectives","volume":"33","year":"2023","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c20","doi-asserted-by":"publisher","first-page":"064102","DOI":"10.1103\/PhysRevE.110.064102","article-title":"Data-driven physics-based modeling of pedestrian dynamics","volume":"110","year":"2024","journal-title":"Phys. Rev. E"},{"key":"2026082508491923300_c21","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1142\/S021820252540007X","article-title":"Data-driven learning to enhance a kinetic model of distressed crowd dynamics","volume":"35","year":"2025","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c22","doi-asserted-by":"publisher","first-page":"e535","DOI":"10.1002\/wcc.535","article-title":"Data assimilation in the geosciences: An overview of methods, issues, and perspectives","volume":"9","year":"2018","journal-title":"WIREs Clim. Change"},{"key":"2026082508491923300_c23","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1175\/1520-0493(1998)126&lt;1719:ASITEK&gt;2.0.CO;2","article-title":"Analysis scheme in the ensemble Kalman filter","volume":"126","year":"1998","journal-title":"Mon. Weather Rev."},{"key":"2026082508491923300_c24","doi-asserted-by":"publisher","first-page":"79","DOI":"10.2151\/jmsj.2013-201","article-title":"Estimating model parameters with ensemble-based data assimilation: A review","volume":"91","year":"2013","journal-title":"J. Meteorol. Soc. Jpn. Ser. II"},{"key":"2026082508491923300_c25","doi-asserted-by":"publisher","first-page":"150703","DOI":"10.1098\/rsos.150703","article-title":"Dynamic calibration of agent-based models using data assimilation","volume":"3","year":"2016","journal-title":"R. Soc. Open Sci."},{"key":"2026082508491923300_c26","doi-asserted-by":"publisher","first-page":"102386","DOI":"10.1016\/j.simpat.2021.102386","article-title":"Real-time agent-based crowd simulation with the reversible jump unscented Kalman filter","volume":"113","year":"2021","journal-title":"Simul. Model. Pract. Theory"},{"key":"2026082508491923300_c27","doi-asserted-by":"publisher","first-page":"e0264892","DOI":"10.1371\/journal.pone.0264892","article-title":"Inference in epidemiological agent-based models using ensemble-based data assimilation","volume":"17","year":"2022","journal-title":"PLoS One"},{"key":"2026082508491923300_c28","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.physd.2006.11.008","article-title":"Efficient data assimilation for spaciotemporal chaos: A local ensemble transform Kalman filter","volume":"230","year":"2007","journal-title":"Physica D"},{"key":"2026082508491923300_c29","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1175\/MWR-D-14-00017.1","article-title":"Parameter estimation using ensemble-based data assimilation in the presence of model error","volume":"143","year":"2015","journal-title":"Mon. Weather Rev."},{"key":"2026082508491923300_c30","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/j.ijnonlinmec.2006.02.008","article-title":"On the mathematical theory of vehicular traffic flow II: Discrete velocity kinetic models","volume":"42","year":"2007","journal-title":"Int. J. Non-Linear Mech."},{"key":"2026082508491923300_c31","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1142\/S0218202507002157","article-title":"Mathematical modeling of vehicular traffic: A discrete kinetic theory approach","volume":"17","year":"2007","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c32","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","year":"1960","journal-title":"J. Basic Eng."},{"key":"2026082508491923300_c33","doi-asserted-by":"publisher","first-page":"1913","DOI":"10.1175\/1520-0493(2002)130&lt;1913:EDAWPO&gt;2.0.CO;2","article-title":"Ensemble data assimilation without perturbed observations","volume":"130","year":"2002","journal-title":"Mon. Weather Rev."},{"key":"2026082508491923300_c34","doi-asserted-by":"publisher","first-page":"79","DOI":"10.2151\/jmsj.2013-201","article-title":"Estimating model parameters with ensemble-based data assimilation: A review","volume":"91","year":"2013","journal-title":"J. Meteorol. Soc. Jpn."},{"key":"2026082508491923300_c35","volume-title":"Splitting Methods for Partial Differential Equations with Rough Solutions: Analysis and MATLAB Programs","year":"2010"},{"key":"2026082508491923300_c36"},{"key":"2026082508491923300_c37","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1006\/jcph.1998.5901","article-title":"Mpdata: A finite-difference solver for geophysical flows","volume":"140","year":"1998","journal-title":"J. Comput. Phys."},{"key":"2026082508491923300_c38","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1142\/S0218202525400081","article-title":"Individual-based crowd dynamics with social interaction","volume":"35","year":"2025","journal-title":"Math. Models Methods Appl. Sci."},{"key":"2026082508491923300_c39","doi-asserted-by":"publisher","first-page":"3973","DOI":"10.1175\/MWR-D-19-0240.1","article-title":"A review of innovation-based methods to jointly estimate model and observation error covariance matrices in ensemble data assimilation","volume":"148","year":"2020","journal-title":"Mon. Weather Rev."},{"key":"2026082508491923300_c40","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1002\/qj.3931","article-title":"Model error covariance estimation in particle and ensemble Kalman filters using an online expectation\u2013maximization algorithm","volume":"147","year":"2021","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"2026082508491923300_c41","volume-title":"Atmospheric Modeling, Data Assimilation and Predictability","year":"2003"},{"key":"2026082508491923300_c42","doi-asserted-by":"publisher","first-page":"e0318426","DOI":"10.1371\/journal.pone.0318426","article-title":"Transmission matrix parameter estimation of COVID-19 evolution with age compartments using ensemble-based data assimilation","volume":"20","year":"2025","journal-title":"PLoS One"},{"key":"2026082508491923300_c43","doi-asserted-by":"publisher","first-page":"2974","DOI":"10.1002\/qj.2879","article-title":"Estimation of the functional form of subgrid-scale parametrizations using ensemble-based data assimilation: A simple model experiment","volume":"142","year":"2016","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"2026082508491923300_c44","unstructured":"S.\n            Rosa\n          , M.Pulido, J.Guerrieri, O.Billoni, and J. P.Agnelli (2026). \u201ccrowds,\u201d GitLab repository. https:\/\/gitlab.com\/santiagorosa1804\/crowds."}],"container-title":["Chaos: An Interdisciplinary Journal of Nonlinear Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/cha\/article-pdf\/doi\/10.1063\/5.0346463\/21117665\/083151_1_5.0346463.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/cha\/article-pdf\/doi\/10.1063\/5.0346463\/21117665\/083151_1_5.0346463.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:49:27Z","timestamp":1787662167000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/cha\/article\/36\/8\/083151\/3403018\/Data-driven-crowd-dynamics-using-kinetic-theory"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":44,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0346463","relation":{},"ISSN":["1054-1500","1089-7682"],"issn-type":[{"value":"1054-1500","type":"print"},{"value":"1089-7682","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,8,1]]},"article-number":"083151"}}