{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:07:39Z","timestamp":1783015659911,"version":"3.54.6"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"24","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001412","name":"Council of Scientific and Industrial Research, India","doi-asserted-by":"publisher","award":["File No: 09\/0028(21164)\/2025-EMR-I"],"award-info":[{"award-number":["File No: 09\/0028(21164)\/2025-EMR-I"]}],"id":[{"id":"10.13039\/501100001412","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001734","name":"Copenhagen University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001734","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This work explores an interpretable approach based on physics-informed neural networks (PINNs) combined with symbolic regression (SR) to determine mathematical expressions for the predicted solutions of nonlinear partial differential equations that describe arterial blood flow influenced by external magnetic fields. PINNs are excellent at capturing the underlying physics, but can be computationally intensive and hard to interpret. The predictive power of PINN has been combined with evolutionary symbolic regression using PySR, an open-source Python module that employs genetic programming and customizable mathematical operators, including trigonometric, exponential, and arithmetic functions. This hybrid approach enables the derivation of concise, transparent mathematical expressions that closely replicate the behavior of these complex systems. This blend of PINNs and symbolic regression helps us to better understand how pulsatile blood flow and magnetic fields interact in the viscoelastic arterial circulation. The comparison graphs of the SR model and the PINN-predicted data at different time scales signify a better fit for the discovered mathematical expressions with data. As illustrated by the low mean squared error and statistical validation on residual losses, the symbolic expressions are extremely accurate and quick enough for real-time execution. Additionally, the solutions provided by the PINN are validated numerically to demonstrate the effectiveness of the proposed method. Our results demonstrate that combining symbolic regression with PINNs provides practical and interpretable solutions in biofluid mechanics, offering a more transparent and reliable alternative to traditional methods.<\/jats:p>","DOI":"10.1007\/s00521-025-11450-9","type":"journal-article","created":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:11:11Z","timestamp":1751760671000},"page":"20205-20240","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Physics-informed neural network with symbolic regression for deriving analytical approximate solutions to nonlinear partial differential equations"],"prefix":"10.1007","volume":"37","author":[{"given":"Joy","family":"Das","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bivas","family":"Bhaumik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumen","family":"De","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satyasaran","family":"Changdar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,6]]},"reference":[{"key":"11450_CR1","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.protcy.2016.05.045","volume":"24","author":"B Thomas","year":"2016","unstructured":"Thomas B, Sumam K (2016) Blood flow in human arterial system-a review. Procedia Technol 24:339\u2013346","journal-title":"Procedia Technol"},{"issue":"1","key":"11450_CR2","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1146\/annurev.fluid.29.1.399","volume":"29","author":"DN Ku","year":"1997","unstructured":"Ku DN (1997) Blood flow in arteries. Annu Rev Fluid Mech 29(1):399\u2013434","journal-title":"Annu Rev Fluid Mech"},{"key":"11450_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jmmm.2016.02.013","volume":"409","author":"NA Shah","year":"2016","unstructured":"Shah NA, Vieru D, Fetecau C (2016) Effects of the fractional order and magnetic field on the blood flow in cylindrical domains. J Magn Magn Mater 409:10\u201319","journal-title":"J Magn Magn Mater"},{"issue":"15","key":"11450_CR4","doi-asserted-by":"publisher","first-page":"2450183","DOI":"10.1142\/S0217979224501832","volume":"38","author":"LA Lund","year":"2024","unstructured":"Lund LA, Ghoto AA, Al-Khaled K, Ghachem K, Fadhel MA, Khan SU, Kolsi L (2024) Thin film flow of blood-based hybrid nanoparticles subject to slip effects: a stability assessment. Int J Mod Phys B 38(15):2450183","journal-title":"Int J Mod Phys B"},{"issue":"12","key":"11450_CR5","doi-asserted-by":"publisher","first-page":"121902","DOI":"10.1063\/5.0235391","volume":"36","author":"B Bhaumik","year":"2024","unstructured":"Bhaumik B, Changdar S, Chakraverty S, De S (2024) Effects of viscosity and induced magnetic fields on weakly nonlinear wave transmission in a viscoelastic tube using physics-informed neural networks. Phys Fluids 36(12):121902","journal-title":"Phys Fluids"},{"issue":"4","key":"11450_CR6","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1016\/j.jbiomech.2016.01.010","volume":"49","author":"X-F Wang","year":"2016","unstructured":"Wang X-F, Nishi S, Matsukawa M, Ghigo A, Lagr\u00e9e P-Y, Fullana J-M (2016) Fluid friction and wall viscosity of the 1d blood flow model. J Biomech 49(4):565\u2013571","journal-title":"J Biomech"},{"key":"11450_CR7","doi-asserted-by":"publisher","first-page":"112623","DOI":"10.1016\/j.cma.2019.112623","volume":"358","author":"G Kissas","year":"2020","unstructured":"Kissas G, Yang Y, Hwuang E, Witschey WR, Detre JA, Perdikaris P (2020) Machine learning in cardiovascular flows modeling: predicting arterial blood pressure from non-invasive 4d flow mri data using physics-informed neural networks. Comput Methods Appl Mech Eng 358:112623","journal-title":"Comput Methods Appl Mech Eng"},{"key":"11450_CR8","doi-asserted-by":"publisher","first-page":"112790","DOI":"10.1016\/j.cma.2019.112790","volume":"362","author":"E Samaniego","year":"2020","unstructured":"Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh VM, Guo H, Hamdia K, Zhuang X, Rabczuk T (2020) An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications. Comput Methods Appl Mech Eng 362:112790","journal-title":"Comput Methods Appl Mech Eng"},{"key":"11450_CR9","doi-asserted-by":"publisher","first-page":"42","DOI":"10.58496\/BJML\/2023\/008","volume":"2023","author":"MM Mijwel","year":"2023","unstructured":"Mijwel MM, Esen A, Shamil A (2023) Overview of neural networks. Babylonian J Mach Learn 2023:42\u201345","journal-title":"Babylonian J Mach Learn"},{"issue":"1","key":"11450_CR10","first-page":"233","volume":"29","author":"A Pratama","year":"2022","unstructured":"Pratama A, Danang MA, Bakar IN (2022) Ann-based methods for solving partial differential equations: a survey. Arab J Basic Appl Sci 29(1):233\u2013248","journal-title":"Arab J Basic Appl Sci"},{"key":"11450_CR11","unstructured":"Raissi M, Perdikaris P, Karniadakis GE (2017) Physics informed deep learning (part i): data-driven solutions of nonlinear partial differential equations. arXiv:1711.10561"},{"issue":"6","key":"11450_CR12","doi-asserted-by":"publisher","first-page":"063608","DOI":"10.1063\/5.0151244","volume":"35","author":"X Li","year":"2023","unstructured":"Li X, Liu Y, Liu Z (2023) Physics-informed neural network based on a new adaptive gradient descent algorithm for solving partial differential equations of flow problems. Phys Fluids 35(6):063608","journal-title":"Phys Fluids"},{"key":"11450_CR13","doi-asserted-by":"publisher","first-page":"110839","DOI":"10.1016\/j.jcp.2021.110839","volume":"451","author":"JN Fuhg","year":"2022","unstructured":"Fuhg JN, Bouklas N (2022) The mixed deep energy method for resolving concentration features in finite strain hyperelasticity. J Comput Phys 451:110839","journal-title":"J Comput Phys"},{"issue":"2","key":"11450_CR14","first-page":"2131","volume":"13","author":"MA Shihab","year":"2023","unstructured":"Shihab MA, Taha WM, Hameed RA, Jameel A, Ibrahim S (2023) Implementation of variational iteration method for various types of linear and nonlinear partial differential equations. Int J Electr Comput Eng 13(2):2131\u20132141","journal-title":"Int J Electr Comput Eng"},{"issue":"8","key":"11450_CR15","doi-asserted-by":"publisher","first-page":"419","DOI":"10.3390\/fractalfract6080419","volume":"6","author":"SA Altaie","year":"2022","unstructured":"Altaie SA, Anakira N, Jameel A, Ababneh O, Qazza A, Alomari AK (2022) Homotopy analysis method analytical scheme for developing a solution to partial differential equations in fuzzy environment. Fractal Fraction 6(8):419","journal-title":"Fractal Fraction"},{"key":"11450_CR16","doi-asserted-by":"publisher","first-page":"107911","DOI":"10.1016\/j.cnsns.2024.107911","volume":"132","author":"P Shi","year":"2024","unstructured":"Shi P, Zeng Z, Liang T (2024) Physics-informed convnet: learning physical field from a shallow neural network. Commun Nonlinear Sci Numer Simul 132:107911","journal-title":"Commun Nonlinear Sci Numer Simul"},{"key":"11450_CR17","unstructured":"Xiang Z, Peng W, Zhou W, Yao W (2022) Hybrid finite difference with the physics-informed neural network for solving pde in complex geometries. arXiv:2202.07926"},{"key":"11450_CR18","unstructured":"Majumdar R, Jadhav V, Deodhar A, Karande S, Vig L, Runkana V (2023) Symbolic regression for pdes using pruned differentiable programs. arXiv:2303.07009"},{"issue":"28","key":"11450_CR19","doi-asserted-by":"publisher","first-page":"21093","DOI":"10.1007\/s00521-023-08876-4","volume":"35","author":"Z Zhu","year":"2023","unstructured":"Zhu Z, Hao J, Huang J, Huang B (2023) Bc-pinn: an adaptive physics informed neural network based on biased multiobjective coevolutionary algorithm. Neural Comput Appl 35(28):21093\u201321113","journal-title":"Neural Comput Appl"},{"key":"11450_CR20","unstructured":"Oh H, Amici R, Bomarito G, Zhe S, Kirby R, Hochhalter J (2023) Genetic programming based symbolic regression for analytical solutions to differential equations. arXiv:2302.03175"},{"issue":"12","key":"11450_CR21","doi-asserted-by":"publisher","first-page":"121924","DOI":"10.1063\/5.0247888","volume":"36","author":"S Changdar","year":"2024","unstructured":"Changdar S, Bhaumik B, Sadhukhan N, Pandey S, Mukhopadhyay S, De S, Bakalis S (2024) Integrating symbolic regression with physics-informed neural networks for simulating nonlinear wave dynamics in arterial blood flow. Phys Fluids 36(12):121924","journal-title":"Phys Fluids"},{"issue":"5","key":"11450_CR22","doi-asserted-by":"publisher","first-page":"e202100351","DOI":"10.1002\/zamm.202100351","volume":"103","author":"A Abbasi","year":"2023","unstructured":"Abbasi A, Al-Khaled K, Zouidi F, Khan SU, Khan MI, Bafakeeh OT, Farooq W, Choudhari R (2023) Blood-based electro-osmotic flow of non-newtonian nanofluid (carreau-yasuda) in a tapered channel with entropy generation. ZAMM J Appl Math Mech Zeitschrift f\u00fcr Angewandte Mathematik und Mechanik 103(5):e202100351","journal-title":"ZAMM J Appl Math Mech Zeitschrift f\u00fcr Angewandte Mathematik und Mechanik"},{"key":"11450_CR23","unstructured":"Wang X (2014) 1D modeling of blood flow in networks: numerical computing and applications. Ph.d thesis, Universit\u00e9 Pierre et Marie Curie-Paris VI"},{"issue":"1","key":"11450_CR24","first-page":"32","volume":"16","author":"S Ahmad","year":"2021","unstructured":"Ahmad S, Al-Johani A, Sahu S (2021) Effect of magnetic and perturbation parameters on blood flow distribution through an artery. Appl Appl Math Int J (AAM) 16(1):32","journal-title":"Appl Appl Math Int J (AAM)"},{"issue":"1","key":"11450_CR25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1134\/S0015462808010055","volume":"43","author":"N Kudryashov","year":"2008","unstructured":"Kudryashov N, Chernyavskii I (2008) Numerical simulation of the process of autoregulation of the arterial blood flow. Fluid Dyn 43(1):32\u201348","journal-title":"Fluid Dyn"},{"key":"11450_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.31031\/RDMS.2020.13.000803","volume":"13","author":"R Nasrin","year":"2020","unstructured":"Nasrin R, Hossain A, Zahan I (2020) Blood flow analysis inside a stenotic artery using power-law fluid model. RDMS 13:1\u201310","journal-title":"RDMS"},{"issue":"4","key":"11450_CR27","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1137\/100810186","volume":"71","author":"BN Steele","year":"2011","unstructured":"Steele BN, Valdez-Jasso D, Haider MA, Olufsen MS (2011) Predicting arterial flow and pressure dynamics using a 1d fluid dynamics model with a viscoelastic wall. SIAM J Appl Math 71(4):1123\u20131143","journal-title":"SIAM J Appl Math"},{"key":"11450_CR28","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1007\/s11012-016-0376-4","volume":"51","author":"A Giusti","year":"2016","unstructured":"Giusti A, Mainardi F (2016) A dynamic viscoelastic analogy for fluid-filled elastic tubes. Meccanica 51:2321\u20132330","journal-title":"Meccanica"},{"key":"11450_CR29","first-page":"2017","volume":"1","author":"E Nikolova","year":"1895","unstructured":"Nikolova E, Jordanov I, Dimitrova Z, Vitanov N (1895) Evolution of nonlinear waves in a blood-filled artery with an aneurysm. AIP Conf Proc 1:2017","journal-title":"AIP Conf Proc"},{"issue":"6","key":"11450_CR30","doi-asserted-by":"publisher","first-page":"2390","DOI":"10.1016\/j.cnsns.2010.09.020","volume":"16","author":"NA Kudryashov","year":"2011","unstructured":"Kudryashov NA, Sinelshchikov DI (2011) Nonlinear evolution equation for describing waves in a viscoelastic tube. Commun Nonlinear Sci Numer Simul 16(6):2390\u20132396","journal-title":"Commun Nonlinear Sci Numer Simul"},{"issue":"3","key":"11450_CR31","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/s10915-022-01939-z","volume":"92","author":"S Cuomo","year":"2022","unstructured":"Cuomo S, Di Cola VS, Giampaolo F, Rozza G, Raissi M, Piccialli F (2022) Scientific machine learning through physics-informed neural networks: Where we are and what\u2019s next. J Sci Comput 92(3):88","journal-title":"J Sci Comput"},{"key":"11450_CR32","unstructured":"Faroughi SA, Pawar N, Fernandes C, Raissi M, Das S, Kalantari NK, Mahjour SK (2022) Physics-guided, physics-informed, and physics-encoded neural networks in scientific computing. arXiv:2211.07377"},{"issue":"1\u20133","key":"11450_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0010-4655(97)00054-4","volume":"104","author":"IE Lagaris","year":"1997","unstructured":"Lagaris IE, Likas A, Fotiadis DI (1997) Artificial neural network methods in quantum mechanics. Comput Phys Commun 104(1\u20133):1\u201314","journal-title":"Comput Phys Commun"},{"key":"11450_CR34","doi-asserted-by":"publisher","first-page":"114823","DOI":"10.1016\/j.cma.2022.114823","volume":"393","author":"J Yu","year":"2022","unstructured":"Yu J, Lu L, Meng X, Karniadakis GE (2022) Gradient-enhanced physics-informed neural networks for forward and inverse pde problems. Comput Methods Appl Mech Eng 393:114823","journal-title":"Comput Methods Appl Mech Eng"},{"issue":"1","key":"11450_CR35","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1137\/19M1274067","volume":"63","author":"L Lu","year":"2021","unstructured":"Lu L, Meng X, Mao Z, Karniadakis GE (2021) Deepxde: a deep learning library for solving differential equations. SIAM Rev 63(1):208\u2013228","journal-title":"SIAM Rev"},{"key":"11450_CR36","doi-asserted-by":"publisher","first-page":"101517","DOI":"10.1016\/j.swevo.2024.101517","volume":"86","author":"Y Song","year":"2024","unstructured":"Song Y, Wu Y, Guo Y, Yan R, Suganthan PN, Zhang Y, Pedrycz W, Das S, Mallipeddi R, Ajani OS et al (2024) Reinforcement learning-assisted evolutionary algorithm: a survey and research opportunities. Swarm Evol Comput 86:101517","journal-title":"Swarm Evol Comput"},{"key":"11450_CR37","doi-asserted-by":"crossref","unstructured":"Shukla A, Pandey HM, Mehrotra D (2015) Comparative review of selection techniques in genetic algorithm. IEEE, pp\u00a0515\u2013519","DOI":"10.1109\/ABLAZE.2015.7154916"},{"key":"11450_CR38","doi-asserted-by":"publisher","first-page":"12363","DOI":"10.1007\/s00521-020-04832-8","volume":"32","author":"A Slowik","year":"2020","unstructured":"Slowik A, Kwasnicka H (2020) Evolutionary algorithms and their applications to engineering problems. Neural Comput Appl 32:12363\u201312379","journal-title":"Neural Comput Appl"},{"key":"11450_CR39","volume-title":"Genetic algorithms","author":"O Kramer","year":"2017","unstructured":"Kramer O, Kramer O (2017) Genetic algorithms. Springer, Berlin"},{"key":"11450_CR40","doi-asserted-by":"publisher","first-page":"8091","DOI":"10.1007\/s11042-020-10139-6","volume":"80","author":"S Katoch","year":"2021","unstructured":"Katoch S, Chauhan SS, Kumar V (2021) A review on genetic algorithm: past, present, and future. Multimedia Tools Appl 80:8091\u20138126","journal-title":"Multimedia Tools Appl"},{"key":"11450_CR41","unstructured":"Cranmer M (2023) Interpretable machine learning for science with pysr and symbolicregression. arXiv:2305.01582"},{"key":"11450_CR42","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s10710-024-09503-4","volume":"26","author":"A Tonda","year":"2025","unstructured":"Tonda A (2025) Review of PySR: high-performance symbolic regression in python and julia. Genet Program Evolvable Mach 26:7","journal-title":"Genet Program Evolvable Mach"},{"issue":"3","key":"11450_CR43","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1253\/circj.CJ-08-0492","volume":"73","author":"N Inoue","year":"2009","unstructured":"Inoue N, Maeda R, Kawakami H, Shokawa T, Yamamoto H, Ito C, Sasaki H (2009) Aortic pulse wave velocity predicts cardiovascular mortality in middle-aged and elderly Japanese men. Circ J 73(3):549\u2013553","journal-title":"Circ J"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11450-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11450-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11450-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T01:12:01Z","timestamp":1757207521000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11450-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":43,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["11450"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11450-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,6]]},"assertion":[{"value":"10 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2025","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 have no conflicts to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}