{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T19:58:43Z","timestamp":1776196723952,"version":"3.50.1"},"reference-count":56,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,11,27]],"date-time":"2022-11-27T00:00:00Z","timestamp":1669507200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Traffic state estimation (TSE) is a critical component of the efficient intelligent transportation systems (ITS) operations. In the literature, TSE methods are divided into model-driven methods and data-driven methods. Each approach has its limitations. The physics information-based neural network (PINN) framework emerges to mitigate the limitations of the traditional TSE methods, while the state-of-art of such a framework has focused on single road segments but can hardly deal with traffic networks. This paper introduces a PINN framework that can effectively make use of a small amount of observational speed data to obtain high-quality TSEs for a traffic network. Both model-driven and data-driven components are incorporated into PINNs to combine the advantages of both approaches and to overcome their disadvantages. Simulation data of simple traffic networks are used for studying the highway network TSE. This paper demonstrates how to solve the popular LWR physical traffic flow model with a PINN for a traffic network. Experimental results confirm that the proposed approach is promising for estimating network traffic accurately.<\/jats:p>","DOI":"10.3390\/a15120447","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T04:56:25Z","timestamp":1669611385000},"page":"447","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Physics-Informed Neural Networks (PINNs)-Based Traffic State Estimation: An Application to Traffic Network"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4136-2169","authenticated-orcid":false,"given":"Muhammad","family":"Usama","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, The University of Alabama in Huntsville, Huntsville, AL 35899, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8568-6707","authenticated-orcid":false,"given":"Rui","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The University of Alabama in Huntsville, Huntsville, AL 35899, USA"}]},{"given":"Jason","family":"Hart","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The University of Alabama in Huntsville, Huntsville, AL 35899, USA"}]},{"given":"Mikaela","family":"Wojcik","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The University of Alabama in Huntsville, Huntsville, AL 35899, USA"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1111\/j.1467-8667.2010.00698.x","article-title":"Reconstructing the traffic state by fusion of heterogeneous data","volume":"26","author":"Treiber","year":"2010","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3484","DOI":"10.1109\/TITS.2016.2552639","article-title":"Highway traffic state estimation with mixed connected and conventional vehicles","volume":"17","author":"Roncoli","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1109\/TITS.2015.2499538","article-title":"A Dynamic Network Modeling-based approach for traffic observability problem","volume":"17","author":"Agarwal","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.arcontrol.2017.03.005","article-title":"Traffic State Estimation on Highway: A Comprehensive Survey","volume":"43","author":"Seo","year":"2017","journal-title":"Annu. Rev. Control"},{"key":"ref_5","first-page":"317","article-title":"On Kinematic Waves II. A theory of traffic flow on long crowded roads","volume":"229","author":"Lighthill","year":"1955","journal-title":"Proc. R. Soc. Lond. Ser. A. Math. Phys. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1287\/opre.4.1.42","article-title":"Shock waves on the highway","volume":"4","author":"Richards","year":"1956","journal-title":"Oper. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.trb.2021.02.007","article-title":"Macroscopic traffic flow modeling with physics regularized gaussian process: A new insight into machine learning applications in transportation","volume":"146","author":"Yuan","year":"2021","journal-title":"Transp. Res. Part B Methodol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jcp.2017.11.039","article-title":"Hidden physics models: Machine learning of nonlinear partial differential equations","volume":"357","author":"Raissi","year":"2018","journal-title":"J. Comput. Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.4208\/cicp.OA-2020-0164","article-title":"Extended physics-informed Neural Networks (xpinns): A generalized space-time domain decomposition based deep learning framework for nonlinear partial differential equations","volume":"28","author":"Jagtap","year":"2020","journal-title":"Commun. Comput. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"056113","DOI":"10.1103\/PhysRevE.79.056113","article-title":"Self-sustained nonlinear waves in traffic flow","volume":"79","author":"Flynn","year":"2009","journal-title":"Phys. Rev. E"},{"key":"ref_11","first-page":"51","article-title":"Models of Freeway Traffic and Control","volume":"Volume 1","author":"Payne","year":"1971","journal-title":"Mathematical Models of Public Systems"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1137\/S0036139997332099","article-title":"Resurrection of \u201csecond order\u201d models of Traffic Flow","volume":"60","author":"Aw","year":"2000","journal-title":"SIAM J. Appl. Math."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/S0191-2615(00)00050-3","article-title":"A non-equilibrium traffic model devoid of gas-like behavior","volume":"36","author":"Zhang","year":"2002","journal-title":"Transp. Res. Part B Methodol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"132","DOI":"10.3141\/1836-17","article-title":"Exploring imputation techniques for missing data in Transportation Management Systems","volume":"1836","author":"Smith","year":"2003","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"160","DOI":"10.3141\/1855-20","article-title":"Detecting errors and imputing missing data for single-loop surveillance systems","volume":"1855","author":"Chen","year":"2003","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.trc.2004.07.006","article-title":"Estimation of missing traffic counts using factor, genetic, neural, and regression techniques","volume":"12","author":"Zhong","year":"2004","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1177\/0361198105193500107","article-title":"Markov chain Monte Carlo multiple imputation using Bayesian networks for Incomplete Intelligent Transportation Systems Data","volume":"1935","author":"Ni","year":"2005","journal-title":"Transp. Res. Rec. J. Transp. Res. Board"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"763469","DOI":"10.1155\/2014\/763469","article-title":"Robust missing traffic flow imputation considering nonnegativity and road capacity","volume":"2014","author":"Tan","year":"2014","journal-title":"Math. Probl. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.trc.2012.12.007","article-title":"A tensor-based method for missing traffic data completion","volume":"28","author":"Tan","year":"2013","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.trc.2017.02.024","article-title":"Deep learning for short-term traffic flow prediction","volume":"79","author":"Polson","year":"2017","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"103820","DOI":"10.1016\/j.trc.2022.103820","article-title":"A novel reinforced dynamic graph convolutional network model with data imputation for network-wide traffic flow prediction","volume":"143","author":"Chen","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"13084","DOI":"10.1109\/TITS.2021.3119638","article-title":"Traffic State data imputation: An efficient generating method based on the graph aggregator","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/MITS.2020.2990165","article-title":"Graph attention LSTM: A spatiotemporal approach for traffic flow forecasting","volume":"14","author":"Zhang","year":"2022","journal-title":"IEEE Intell. Transp. Syst. Mag."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103448","DOI":"10.1016\/j.trc.2021.103448","article-title":"On the estimation of traffic speeds with deep convolutional neural networks given probe data","volume":"134","author":"Rempe","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103372","DOI":"10.1016\/j.trc.2021.103372","article-title":"A customized deep learning approach to integrate network-scale online traffic data imputation and prediction","volume":"132","author":"Zhang","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ye, Y., Zhang, S., and Yu, J.J.Q. (2021, January 19\u201322). Traffic data imputation with ensemble convolutional Autoencoder. Proceedings of the 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Indianapolis, IN, USA.","DOI":"10.1109\/ITSC48978.2021.9564839"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.trc.2016.09.015","article-title":"An efficient realization of deep learning for traffic data imputation","volume":"72","author":"Duan","year":"2016","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103826","DOI":"10.1016\/j.trc.2022.103826","article-title":"Memory-augmented dynamic graph convolution networks for traffic data imputation with diverse missing patterns","volume":"143","author":"Liang","year":"2022","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Huang, A.J., and Agarwal, S. (2020, January 20\u201323). Physics informed Deep Learning for traffic state estimation. Proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece.","DOI":"10.1109\/ITSC45102.2020.9294236"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Barreau, M., Aguiar, M., Liu, J., and Johansson, K.H. (2021, January 13\u201317). Physics-informed learning for identification and state reconstruction of traffic density. Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), Austin, TX, USA.","DOI":"10.1109\/CDC45484.2021.9683295"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Shi, R., Mo, Z., and Di, X. (2021, January 2\u20139). Physics-Informed Deep Learning for Traffic State Estimation: A Hybrid Paradigm Informed by Second-Order Traffic Models. Proceedings of the AAAI Conference on Artificial Intelligence, Online.","DOI":"10.1609\/aaai.v35i1.16132"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"11688","DOI":"10.1109\/TITS.2021.3106259","article-title":"A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation","volume":"23","author":"Shi","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"17849","DOI":"10.1109\/TITS.2022.3157439","article-title":"Incorporating kinematic wave theory into a deep learning method for high-resolution traffic speed estimation","volume":"23","author":"Thodi","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1137\/140974596","article-title":"Bayesian numerical homogenization","volume":"13","author":"Owhadi","year":"2015","journal-title":"Multiscale Modeling Simul."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1016\/j.jcp.2017.01.060","article-title":"Inferring solutions of differential equations using noisy multi-fidelity data","volume":"335","author":"Raissi","year":"2017","journal-title":"J. Comput. Phys."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"A2603","DOI":"10.1137\/18M1229845","article-title":"FPINNs: Fractional physics-informed Neural Networks","volume":"41","author":"Pang","year":"2019","journal-title":"SIAM J. Sci. Comput."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"A639","DOI":"10.1137\/19M1260141","article-title":"Learning in modal space: Solving time-dependent stochastic pdes using physics-informed Neural Networks","volume":"42","author":"Zhang","year":"2020","journal-title":"SIAM J. Sci. Comput."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"113547","DOI":"10.1016\/j.cma.2020.113547","article-title":"HP-VPINNs: Variational physics-informed neural networks with domain decomposition","volume":"374","author":"Kharazmi","year":"2021","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1109\/MSP.2021.3118904","article-title":"A physics-informed neural network for quantifying the microstructural properties of polycrystalline nickel using ultrasound data: A promising approach for solving inverse problems","volume":"39","author":"Shukla","year":"2022","journal-title":"IEEE Signal Processing Mag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"110775","DOI":"10.1016\/j.oceaneng.2022.110775","article-title":"Deep learning of inverse water waves problems using multi-fidelity data: Application to serre\u2013green\u2013naghdi equations","volume":"248","author":"Jagtap","year":"2022","journal-title":"Ocean Eng."},{"key":"ref_41","unstructured":"McClenny, L., and Braga-Neto, U. (2020). Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"112789","DOI":"10.1016\/j.cma.2019.112789","article-title":"Physics-informed neural networks for high-speed flows","volume":"360","author":"Mao","year":"2020","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"113028","DOI":"10.1016\/j.cma.2020.113028","article-title":"Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems","volume":"365","author":"Jagtap","year":"2020","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"110683","DOI":"10.1016\/j.jcp.2021.110683","article-title":"Parallel physics-informed neural networks via domain decomposition","volume":"447","author":"Shukla","year":"2021","journal-title":"J. Comput. Phys."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"111402","DOI":"10.1016\/j.jcp.2022.111402","article-title":"Physics-informed neural networks for inverse problems in supersonic flows","volume":"466","author":"Jagtap","year":"2022","journal-title":"J. Comput. Phys."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1093\/imanum\/drab032","article-title":"Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for pdes","volume":"42","author":"Mishra","year":"2021","journal-title":"IMA J. Numer. Anal."},{"key":"ref_47","unstructured":"Ryck, T.D., Jagtap, A.D., and Mishra, S. (2022). Error estimates for physics informed neural networks approximating the Navier-Stokes equations. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"A3158","DOI":"10.1137\/21M1447039","article-title":"When do extended physics-informed Neural Networks (xpinns) improve generalization?","volume":"44","author":"Hu","year":"2022","journal-title":"SIAM J. Sci. Comput."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"05017003","DOI":"10.1061\/JTEPBS.0000058","article-title":"Artificial Neural Network\u2013based traffic state estimation using Erroneous Automated Sensor Data","volume":"143","author":"Fulari","year":"2017","journal-title":"J. Transp. Eng. Part A Syst."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"7269382","DOI":"10.1155\/2016\/7269382","article-title":"Freeway multisensor data fusion approach integrating data from cellphone probes and fixed sensors","volume":"2016","author":"He","year":"2016","journal-title":"J. Sens."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neunet.2021.01.026","article-title":"A survey on modern trainable activation functions","volume":"138","author":"Apicella","year":"2021","journal-title":"Neural Netw."},{"key":"ref_52","unstructured":"Jagtap, A.D., and Karniadakis, G.E. (2022). How important are activation functions in regression and classification? A survey, performance comparison, and future directions. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"109136","DOI":"10.1016\/j.jcp.2019.109136","article-title":"Adaptive activation functions accelerate convergence in deep and physics-informed Neural Networks","volume":"404","author":"Jagtap","year":"2020","journal-title":"J. Comput. Phys."},{"key":"ref_54","first-page":"20200334","article-title":"Locally adaptive activation functions with slope recovery for deep and physics-informed Neural Networks","volume":"476","author":"Jagtap","year":"2020","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"ref_55","unstructured":"Abbasi, J., and Andersen, P.\u00d8. (2022). Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs). arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.neucom.2021.10.036","article-title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","volume":"468","author":"Jagtap","year":"2022","journal-title":"Neurocomputing"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/12\/447\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:27:59Z","timestamp":1760146079000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/12\/447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,27]]},"references-count":56,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["a15120447"],"URL":"https:\/\/doi.org\/10.3390\/a15120447","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,27]]}}}