Using NeuralPDE.jl to solve differential equations

This paper describes the application of physics-informed neural network (PINN) for solving partial derivative equations. Physics Informed Neural Network is a type of deep learning that takes into account physical laws to solve physical equations more efficiently compared to classical methods. The so...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Discrete and continuous models and applied computational science Ročník 33; číslo 3; s. 284 - 298
Hlavní autori: Belicheva, Daria M., Demidova, Ekaterina A., Shtepa, Kristina A., Gevorkyan, Migran N., Korolkova, Anna V., Kulyabov, Dmitry S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Peoples’ Friendship University of Russia (RUDN University) 15.10.2025
Predmet:
differential equations
julia programming language
neuralpde
numerical methods
physics-informed neural networks
ISSN:2658-4670, 2658-7149
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This paper describes the application of physics-informed neural network (PINN) for solving partial derivative equations. Physics Informed Neural Network is a type of deep learning that takes into account physical laws to solve physical equations more efficiently compared to classical methods. The solution of partial derivative equations (PDEs) is of most interest, since numerical methods and classical deep learning methods are inefficient and too difficult to tune in cases when the complex physics of the process needs to be taken into account. The advantage of PINN is that it minimizes a loss function during training, which takes into account the constraints of the system and th e laws of the domain. In this paper, we consider the solution of ordinary differential equations (ODEs) and PDEs using PINN, and then compare the efficiency and accuracy of this solution method compared to classical methods. The solution is implemented in the Julia programming language. We use NeuralPDE.jl, a package containing methods for solving equations in partial derivatives using physics-based neural networks. The classical method for solving PDEs is implemented through the DifferentialEquations.jl library. As a result, a comparative analysis of the considered solution methods for ODEs and PDEs has been performed, and an evaluation of their performance and accuracy has been obtained. In this paper we have demonstrated the basic capabilities of the NeuralPDE.jl package and its efficiency in comparison with numerical methods.
AbstractList This paper describes the application of physics-informed neural network (PINN) for solving partial derivative equations. Physics Informed Neural Network is a type of deep learning that takes into account physical laws to solve physical equations more efficiently compared to classical methods. The solution of partial derivative equations (PDEs) is of most interest, since numerical methods and classical deep learning methods are inefficient and too difficult to tune in cases when the complex physics of the process needs to be taken into account. The advantage of PINN is that it minimizes a loss function during training, which takes into account the constraints of the system and th e laws of the domain. In this paper, we consider the solution of ordinary differential equations (ODEs) and PDEs using PINN, and then compare the efficiency and accuracy of this solution method compared to classical methods. The solution is implemented in the Julia programming language. We use NeuralPDE.jl, a package containing methods for solving equations in partial derivatives using physics-based neural networks. The classical method for solving PDEs is implemented through the DifferentialEquations.jl library. As a result, a comparative analysis of the considered solution methods for ODEs and PDEs has been performed, and an evaluation of their performance and accuracy has been obtained. In this paper we have demonstrated the basic capabilities of the NeuralPDE.jl package and its efficiency in comparison with numerical methods.
Author Demidova, Ekaterina A.
Gevorkyan, Migran N.
Shtepa, Kristina A.
Korolkova, Anna V.
Kulyabov, Dmitry S.
Belicheva, Daria M.
Author_xml – sequence: 1
  givenname: Daria M.
  orcidid: 0009-0007-0072-0453
  surname: Belicheva
  fullname: Belicheva, Daria M.
  organization: RUDN University
– sequence: 2
  givenname: Ekaterina A.
  orcidid: 0009-0005-2255-4025
  surname: Demidova
  fullname: Demidova, Ekaterina A.
  organization: RUDN University
– sequence: 3
  givenname: Kristina A.
  orcidid: 0000-0002-4092-4326
  surname: Shtepa
  fullname: Shtepa, Kristina A.
  organization: RUDN University
– sequence: 4
  givenname: Migran N.
  orcidid: 0000-0002-4834-4895
  surname: Gevorkyan
  fullname: Gevorkyan, Migran N.
  organization: RUDN University
– sequence: 5
  givenname: Anna V.
  orcidid: 0000-0001-7141-7610
  surname: Korolkova
  fullname: Korolkova, Anna V.
  organization: RUDN University
– sequence: 6
  givenname: Dmitry S.
  orcidid: 0000-0002-0877-7063
  surname: Kulyabov
  fullname: Kulyabov, Dmitry S.
  organization: RUDN University, Joint Institute for Nuclear Research
BookMark eNo9kE1LAzEQhoNUsNb-hz14Tc3XJlnwIrVqoagHew6z-Shb1o0mW8F_725bPM3wvsMD81yjSRc7j9AtJQvGuOR3TJYaC6kIZoSVmHPMMdMCs0pfoOmxVVRUk_M-Xl6hec57QgjTipdEThHb5qbbFa_-kKB9f1wt9m3RxyLH9scXrgnBJ9_1DbSF_z5A38Qu36DLAG328_Ocoe3T6mP5gjdvz-vlwwZbqrjGlCuQThERwIeSuNpzQZiCYGupbVC1Zy5oXVEquJMiVDL4evjMEyssCZ7P0PrEdRH25is1n5B-TYTGHIOYdgZS39jWG7CsGiQoJmotlOIVlFpRkBCYcIHSgXV_YtkUc04-_PMoMUedZpRkRklm1Gk4N0OmhRl08j9jCml9
Cites_doi 10.1145/3511528.3511535
10.5334/jors.151
10.1016/j.icheatmasstransfer.2022.105890
10.22363/2658-4670-2023-31-4-399-418
10.1016/0893-6080(91)90009-T
10.1016/j.jcp.2018.10.045
10.48550/ARXIV.2107.09443
10.22363/2658-4670-2024-32-1-48-60
10.1117/12.2315066
10.22363/2658-4670-2024-32-3-306-318
ContentType Journal Article
DBID AAYXX
CITATION
DOA
DOI 10.22363/2658-4670-2025-33-3-284-298
DatabaseName CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList
CrossRef
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2658-7149
EndPage 298
ExternalDocumentID oai_doaj_org_article_ac29202724b847739a5871a6af24df11
10_22363_2658_4670_2025_33_3_284_298
GroupedDBID AAFWJ
AAYXX
AFPKN
ALMA_UNASSIGNED_HOLDINGS
CITATION
GROUPED_DOAJ
VCL
VIT
ID FETCH-LOGICAL-c1738-137a6d704faef50dbe34027afcb68cf7be2df8891143d64f96feb223e0c4c0fe3
IEDL.DBID DOA
ISSN 2658-4670
IngestDate Mon Nov 03 22:03:12 EST 2025
Wed Nov 05 20:56:11 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License https://creativecommons.org/licenses/by-nc/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c1738-137a6d704faef50dbe34027afcb68cf7be2df8891143d64f96feb223e0c4c0fe3
ORCID 0000-0002-4834-4895
0000-0001-7141-7610
0009-0007-0072-0453
0000-0002-0877-7063
0000-0002-4092-4326
0009-0005-2255-4025
OpenAccessLink https://doaj.org/article/ac29202724b847739a5871a6af24df11
PageCount 15
ParticipantIDs doaj_primary_oai_doaj_org_article_ac29202724b847739a5871a6af24df11
crossref_primary_10_22363_2658_4670_2025_33_3_284_298
PublicationCentury 2000
PublicationDate 2025-10-15
PublicationDateYYYYMMDD 2025-10-15
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-15
  day: 15
PublicationDecade 2020
PublicationTitle Discrete and continuous models and applied computational science
PublicationYear 2025
Publisher Peoples’ Friendship University of Russia (RUDN University)
Publisher_xml – name: Peoples’ Friendship University of Russia (RUDN University)
References ref13
ref12
ref15
ref14
ref20
ref11
ref10
ref21
ref2
ref1
ref17
ref16
ref19
ref18
ref8
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – ident: ref2
– ident: ref3
– ident: ref7
– ident: ref13
  doi: 10.1145/3511528.3511535
– ident: ref16
  doi: 10.5334/jors.151
– ident: ref8
  doi: 10.1016/j.icheatmasstransfer.2022.105890
– ident: ref19
  doi: 10.22363/2658-4670-2023-31-4-399-418
– ident: ref5
  doi: 10.1016/0893-6080(91)90009-T
– ident: ref4
  doi: 10.1016/j.jcp.2018.10.045
– ident: ref6
  doi: 10.48550/ARXIV.2107.09443
– ident: ref20
  doi: 10.22363/2658-4670-2024-32-1-48-60
– ident: ref9
– ident: ref18
– ident: ref21
  doi: 10.1117/12.2315066
– ident: ref10
– ident: ref11
– ident: ref17
– ident: ref1
  doi: 10.48550/ARXIV.2107.09443
– ident: ref12
– ident: ref14
– ident: ref15
  doi: 10.22363/2658-4670-2024-32-3-306-318
SSID ssj0002873506
ssib050730783
Score 2.3064177
Snippet This paper describes the application of physics-informed neural network (PINN) for solving partial derivative equations. Physics Informed Neural Network is a...
SourceID doaj
crossref
SourceType Open Website
Index Database
StartPage 284
SubjectTerms differential equations
julia programming language
neuralpde
numerical methods
physics-informed neural networks
Title Using NeuralPDE.jl to solve differential equations
URI https://doaj.org/article/ac29202724b847739a5871a6af24df11
Volume 33
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2658-7149
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002873506
  issn: 2658-4670
  databaseCode: DOA
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2658-7149
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib050730783
  issn: 2658-4670
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA4iInoQn1hf7MFr2mzeOfpo8SClB4XeQnaTgKW02tb-fifZttSTF68DG7LfzM5kNsn3IXSfxF8jlClMTGUwVzFgbTjFTLuq8iYI5rNqyavq9_VwaAZbUl_pTFhDD9wA13F10lOiivIKEqlixglY4zvpIuU-Nrd6iTJbzRREkkiBu96fGuVfSIqJLLRJoeRiyA5kHyZK2lAdJetsjBA0VGDGMMOQtzE1-le92qL1z_Wnd4yOVgvH4qGZ8AnaCZNTdLhFJ3iGaN7_LxLfhhsPnrvt0bhYTAuIrmUo1koo8EWPi_DVMHzPz9F7r_v29IJXmgi4LhXkppIpJ70iPLoQBfFVYNABKhfrSuo6qipQH7WGFMaZlzwaGaF3piyQmtckBnaBdifTSbhERempkdQ744PhJQwYRXQySXGoWBsvW0is39x-NtQXFlqGjJhNiNmEmE2IWcYs2DS3gFgLPSaYNs8kAutsALfalVvtX269-o9BrtFB9mc6gCJu0O5i9h1u0V69XHzMZ3c5Yn4AoPi7pw
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Using+NeuralPDE.jl+to+solve+differential+equations&rft.jtitle=Discrete+and+continuous+models+and+applied+computational+science&rft.au=Belicheva%2C+Daria+M.&rft.au=Demidova%2C+Ekaterina+A.&rft.au=Shtepa%2C+Kristina+A.&rft.au=Gevorkyan%2C+Migran+N.&rft.date=2025-10-15&rft.issn=2658-4670&rft.eissn=2658-7149&rft.volume=33&rft.issue=3&rft.spage=284&rft.epage=298&rft_id=info:doi/10.22363%2F2658-4670-2025-33-3-284-298&rft.externalDBID=n%2Fa&rft.externalDocID=10_22363_2658_4670_2025_33_3_284_298
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2658-4670&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2658-4670&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2658-4670&client=summon