{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T14:09:02Z","timestamp":1764079742268,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:00:00Z","timestamp":1635292800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:00:00Z","timestamp":1635292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007105","name":"Universit\u00e4t Mannheim","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007105","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Math. Control Signals Syst."],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We propose a neural network approach to model general interaction dynamics and an adjoint-based stochastic gradient descent algorithm to calibrate its parameters. The parameter calibration problem is considered as optimal control problem that is investigated from a theoretical and numerical point of view. We prove the existence of optimal controls, derive the corresponding first-order optimality system and formulate a stochastic gradient descent algorithm to identify parameters for given data sets. To validate the approach, we use real data sets from traffic and crowd dynamics to fit the parameters. The results are compared to forces corresponding to well-known interaction models such as the Lighthill\u2013Whitham\u2013Richards model for traffic and the social force model for crowd motion.<\/jats:p>","DOI":"10.1007\/s00498-021-00309-8","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T00:02:42Z","timestamp":1635292962000},"page":"185-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Parameter calibration with stochastic gradient descent for interacting particle systems driven by neural networks"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8512-4525","authenticated-orcid":false,"given":"Simone","family":"G\u00f6ttlich","sequence":"first","affiliation":[]},{"given":"Claudia","family":"Totzeck","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,27]]},"reference":[{"issue":"4","key":"309_CR1","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.aml.2012.10.011","volume":"26","author":"G Albi","year":"2013","unstructured":"Albi G, Pareschi L (2013) Modeling self-organized systems interacting with few individuals: from microscopic to macroscopic dynamics. Appl Math Lett 26(4):397\u2013401","journal-title":"Appl Math Lett"},{"issue":"5","key":"309_CR2","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1142\/S0218202517500208","volume":"27","author":"M Bongini","year":"2017","unstructured":"Bongini M, Fornasier M, Hansen M, Maggioni M (2017) Inferring interaction rules from ovservations of evolutive systems i: the variational appraoch. Math Mod Method Appl Sci 27(5):909\u2013951","journal-title":"Math Mod Method Appl Sci"},{"key":"309_CR3","doi-asserted-by":"crossref","unstructured":"Burger M, Pinnau R, Totzeck C, Tse O (2020) Mean-field optimal control and optimality conditions in the space of probability measures. accepted for publication in SCICON","DOI":"10.1137\/19M1249461"},{"key":"309_CR4","doi-asserted-by":"crossref","unstructured":"Haber E, Ruthotto L (Dec 2017) Stable architectures for deep neural networks. Inverse Problems 34(1):014004","DOI":"10.1088\/1361-6420\/aa9a90"},{"key":"309_CR5","doi-asserted-by":"crossref","unstructured":"Carrillo JA, Fornasier M, Toscani G, Vecil F (2010) Particle, kinetic, and hydrodynamic models of swarming. In: G Naldi, L Pareschi, G Toscani (eds) Mathematical modeling of collective behavior in socio-economic and life sciences, pp 297\u2013336. Birkh\u00e4user Boston","DOI":"10.1007\/978-0-8176-4946-3_12"},{"key":"309_CR6","unstructured":"Chen R, Rubanova Y, Bettencourt J, Duvenaud D (2018) Neural ordinary differential equations. In: S Bengio, H Wallach, H Larochelle, K Grauman, N Cesa-Bianchi, R Garnett (eds) Advances in neural information processing systems, vol 31, pp 6571\u20136583. Curran Associates, Inc"},{"issue":"2","key":"309_CR7","doi-asserted-by":"publisher","first-page":"337","DOI":"10.3934\/mbe.2015.12.337","volume":"12","author":"A Corbetta","year":"2015","unstructured":"Corbetta A, Muntean A, Vafayi K (2015) Parameter estimation of social forces in pedestrian dynamics models via a probabilistic method. Math Biosci Eng MBE 12(2):337\u2013356","journal-title":"Math Biosci Eng MBE"},{"key":"309_CR8","series-title":"MS&A. Modeling, Simulation and Applications","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-06620-2","volume-title":"Multiscale modeling of pedestrian dynamics","author":"E Cristiani","year":"2014","unstructured":"Cristiani E, Piccoli B, Tosin A (2014) Multiscale modeling of pedestrian dynamics, vol 12. MS&amp;A. Modeling, Simulation and Applications. Springer, Cham"},{"key":"309_CR9","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TAC.2007.895842","volume":"52","author":"F Cucker","year":"2007","unstructured":"Cucker F, Smale S (2007) Emergent behaviour in flocks. IEEE Trans Autom Control 52:852\u2013862","journal-title":"IEEE Trans Autom Control"},{"issue":"4","key":"309_CR10","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1137\/18M1215980","volume":"79","author":"SN Gomes","year":"2019","unstructured":"Gomes SN, Stuart AM, Wolfram M-T (2019) Parameter estimation for macroscopic pedestrian dynamics models from microscopic data. SIAM J Appl Math 79(4):1475\u20131500","journal-title":"SIAM J Appl Math"},{"key":"309_CR11","first-page":"11","volume-title":"Artificial neural networks for the estimation of pedestrian interaction forces","author":"S G\u00f6ttlich","year":"2020","unstructured":"G\u00f6ttlich S, Knapp S (2020) Artificial neural networks for the estimation of pedestrian interaction forces. Springer International Publishing, Berlin, pp 11\u201332"},{"key":"309_CR12","doi-asserted-by":"crossref","unstructured":"Gr\u00fcne L (2020) Computing lyapunov functions using deep neural networks. arXiv:2001.08423v3","DOI":"10.3934\/jcd.2021006"},{"key":"309_CR13","doi-asserted-by":"crossref","unstructured":"Gr\u00fcne L (2020) Overcoming the curse of dimensionality for approximating lyapunov functions with deep neural networks under a small-gain condition. arXiv:2001.08423v3","DOI":"10.1016\/j.ifacol.2021.06.152"},{"key":"309_CR14","doi-asserted-by":"crossref","unstructured":"Haber E, Ruthotto L (Dec 2017) Stable architectures for deep neural networks. Inverse Problems 34(1):014004","DOI":"10.1088\/1361-6420\/aa9a90"},{"issue":"5","key":"309_CR15","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing D, Moln\u00e1r P (1995) Social force model for pedestrian dynamics. Phys Rev E 51(5):4282\u20134286","journal-title":"Phys Rev E"},{"key":"309_CR16","volume-title":"Optimization with PDE Constraints","author":"M Hinze","year":"2009","unstructured":"Hinze M, Pinnau R, Ulbrich M, Ulbrich S (2009) Optimization with PDE Constraints. Springer, Berlin"},{"key":"309_CR17","doi-asserted-by":"publisher","first-page":"409","DOI":"10.3934\/nhm.2018018","volume":"13","author":"H Holden","year":"2018","unstructured":"Holden H, Risebro NH (2018) Follow-the-leader models can be viewed as a numerical approximation to the lighthill-whitham-richards model for traffic flow. Netw Heterog Media 13:409\u2013421","journal-title":"Netw Heterog Media"},{"key":"309_CR18","unstructured":"Kallo E, Fazekas A, Lamberty S, Oeser M (2019) Microscopic traffic data obtained from videos recorded on a german motorway. Mendeley Data, V1"},{"issue":"31","key":"309_CR19","first-page":"120","volume":"22","author":"F Lu","year":"2021","unstructured":"Lu F, Maggioni M, Tang S (2021) Learning interaction kernels in heterogeneous systems of agents from multiple trajectories. J Mach Learn Res 22(31):120","journal-title":"J Mach Learn Res"},{"key":"309_CR20","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1016\/j.apenergy.2018.07.084","volume":"228","author":"AP Marug\u00e1n","year":"2018","unstructured":"Marug\u00e1n AP, Garc\u00eda M\u00e1rquez FP, Pinar Perez J M, Ruiz-Hern\u00e1ndez D (2018) A survey of artificial neural network in wind energysystems. Appl Energy 228:1822\u20131836","journal-title":"Appl Energy"},{"key":"309_CR21","volume-title":"Interacting Multiagent Systems: kinetic equations and Monte Carlo methods","author":"L Pareschi","year":"2013","unstructured":"Pareschi L, Toscani G (2013) Interacting Multiagent Systems: kinetic equations and Monte Carlo methods. Oxford University Press, Oxford"},{"issue":"1","key":"309_CR22","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1142\/S0218202517400061","volume":"27","author":"R Pinnau","year":"2017","unstructured":"Pinnau R, Totzeck C, Tse O, Martin S (2017) A consensus-based model for global optimization and its mean-field limit. Math Models Methods Appl Sci 27(1):130","journal-title":"Math Models Methods Appl Sci"},{"issue":"9","key":"309_CR23","doi-asserted-by":"publisher","first-page":"873","DOI":"10.3390\/app7090873","volume":"7","author":"V Ricciardi","year":"2017","unstructured":"Ricciardi V, Augsburg K, Gramstat S, Schreiber V, Ivanov V (2017) Survey on modelling and techniques for frictionestimation in automotive brakes. Appl Sci 7(9):873","journal-title":"Appl Sci"},{"key":"309_CR24","doi-asserted-by":"publisher","unstructured":"Seyfried A, Boltes M (2021) Data archive of experimental data from studies about pedestrian dynamics. https:\/\/doi.org\/10.34735\/ped.2013.5","DOI":"10.34735\/ped.2013.5"},{"key":"309_CR25","doi-asserted-by":"crossref","unstructured":"Tordeux A, Chraibi M, Seyfried A, Schadschneider A (2019) Prediction of pedestrian speed with artificial neural networks. In Hamdar SH (ed) Traffic and Granular Flow \u201917. Springer International Publishing, Cham, pp 327\u2013335","DOI":"10.1007\/978-3-030-11440-4_36"},{"issue":"3","key":"309_CR26","doi-asserted-by":"publisher","first-page":"481","DOI":"10.4310\/CMS.2006.v4.n3.a1","volume":"4","author":"G Toscani","year":"2006","unstructured":"Toscani G (2006) Kinetic models of opinion formation. Commun Math Sci 4(3):481\u2013496","journal-title":"Commun Math Sci"},{"issue":"6","key":"309_CR27","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.3934\/krm.2020044","volume":"13","author":"C Totzeck","year":"2020","unstructured":"Totzeck C (2020) An anisotropic interaction model with collision avoidance. Kinetic Related Models 13(6):1219\u20131242","journal-title":"Kinetic Related Models"},{"key":"309_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2020.132542","volume":"411","author":"M Zhong","year":"2020","unstructured":"Zhong M, Miller J, Maggioni M (2020) Data-driven discovery of emergent behaviors in collective dynamics. Physica D Nonlinear Phenomena 411:132542","journal-title":"Physica D Nonlinear Phenomena"}],"container-title":["Mathematics of Control, Signals, and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00498-021-00309-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00498-021-00309-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00498-021-00309-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T19:54:50Z","timestamp":1699732490000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00498-021-00309-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,27]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["309"],"URL":"https:\/\/doi.org\/10.1007\/s00498-021-00309-8","relation":{},"ISSN":["0932-4194","1435-568X"],"issn-type":[{"type":"print","value":"0932-4194"},{"type":"electronic","value":"1435-568X"}],"subject":[],"published":{"date-parts":[[2021,10,27]]},"assertion":[{"value":"29 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}