Parsimonious physics-informed random projection neural networks for initial value problems of ODEs and index-1 DAEs

We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial value problems (IVPs) of nonlinear stiff ordinary differential equations (ODEs) and index-1 differential algebraic equations (DAEs), which may al...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Chaos (Woodbury, N.Y.) Jg. 33; H. 4
Hauptverfasser: Fabiani, Gianluca, Galaris, Evangelos, Russo, Lucia, Siettos, Constantinos
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.04.2023
ISSN:1089-7682, 1089-7682
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial value problems (IVPs) of nonlinear stiff ordinary differential equations (ODEs) and index-1 differential algebraic equations (DAEs), which may also arise from spatial discretization of partial differential equations (PDEs). The internal weights are fixed to ones while the unknown weights between the hidden and output layer are computed with Newton's iterations using the Moore-Penrose pseudo-inverse for low to medium scale and sparse QR decomposition with L 2 regularization for medium- to large-scale systems. Building on previous works on random projections, we also prove its approximation accuracy. To deal with stiffness and sharp gradients, we propose an adaptive step-size scheme and address a continuation method for providing good initial guesses for Newton iterations. The "optimal" bounds of the uniform distribution from which the values of the shape parameters of the Gaussian kernels are sampled and the number of basis functions are "parsimoniously" chosen based on bias-variance trade-off decomposition. To assess the performance of the scheme in terms of both numerical approximation accuracy and computational cost, we used eight benchmark problems (three index-1 DAEs problems, and five stiff ODEs problems including the Hindmarsh-Rose neuronal model of chaotic dynamics and the Allen-Cahn phase-field PDE). The efficiency of the scheme was compared against two stiff ODEs/DAEs solvers, namely, ode15s and ode23t solvers of the MATLAB ODE suite as well as against deep learning as implemented in the DeepXDE library for scientific machine learning and physics-informed learning for the solution of the Lotka-Volterra ODEs included in the demos of the library. A software/toolbox in Matlab (that we call RanDiffNet) with demos is also provided.
AbstractList We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial value problems (IVPs) of nonlinear stiff ordinary differential equations (ODEs) and index-1 differential algebraic equations (DAEs), which may also arise from spatial discretization of partial differential equations (PDEs). The internal weights are fixed to ones while the unknown weights between the hidden and output layer are computed with Newton's iterations using the Moore-Penrose pseudo-inverse for low to medium scale and sparse QR decomposition with L 2 regularization for medium- to large-scale systems. Building on previous works on random projections, we also prove its approximation accuracy. To deal with stiffness and sharp gradients, we propose an adaptive step-size scheme and address a continuation method for providing good initial guesses for Newton iterations. The "optimal" bounds of the uniform distribution from which the values of the shape parameters of the Gaussian kernels are sampled and the number of basis functions are "parsimoniously" chosen based on bias-variance trade-off decomposition. To assess the performance of the scheme in terms of both numerical approximation accuracy and computational cost, we used eight benchmark problems (three index-1 DAEs problems, and five stiff ODEs problems including the Hindmarsh-Rose neuronal model of chaotic dynamics and the Allen-Cahn phase-field PDE). The efficiency of the scheme was compared against two stiff ODEs/DAEs solvers, namely, ode15s and ode23t solvers of the MATLAB ODE suite as well as against deep learning as implemented in the DeepXDE library for scientific machine learning and physics-informed learning for the solution of the Lotka-Volterra ODEs included in the demos of the library. A software/toolbox in Matlab (that we call RanDiffNet) with demos is also provided.We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial value problems (IVPs) of nonlinear stiff ordinary differential equations (ODEs) and index-1 differential algebraic equations (DAEs), which may also arise from spatial discretization of partial differential equations (PDEs). The internal weights are fixed to ones while the unknown weights between the hidden and output layer are computed with Newton's iterations using the Moore-Penrose pseudo-inverse for low to medium scale and sparse QR decomposition with L 2 regularization for medium- to large-scale systems. Building on previous works on random projections, we also prove its approximation accuracy. To deal with stiffness and sharp gradients, we propose an adaptive step-size scheme and address a continuation method for providing good initial guesses for Newton iterations. The "optimal" bounds of the uniform distribution from which the values of the shape parameters of the Gaussian kernels are sampled and the number of basis functions are "parsimoniously" chosen based on bias-variance trade-off decomposition. To assess the performance of the scheme in terms of both numerical approximation accuracy and computational cost, we used eight benchmark problems (three index-1 DAEs problems, and five stiff ODEs problems including the Hindmarsh-Rose neuronal model of chaotic dynamics and the Allen-Cahn phase-field PDE). The efficiency of the scheme was compared against two stiff ODEs/DAEs solvers, namely, ode15s and ode23t solvers of the MATLAB ODE suite as well as against deep learning as implemented in the DeepXDE library for scientific machine learning and physics-informed learning for the solution of the Lotka-Volterra ODEs included in the demos of the library. A software/toolbox in Matlab (that we call RanDiffNet) with demos is also provided.
We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial value problems (IVPs) of nonlinear stiff ordinary differential equations (ODEs) and index-1 differential algebraic equations (DAEs), which may also arise from spatial discretization of partial differential equations (PDEs). The internal weights are fixed to ones while the unknown weights between the hidden and output layer are computed with Newton's iterations using the Moore-Penrose pseudo-inverse for low to medium scale and sparse QR decomposition with L 2 regularization for medium- to large-scale systems. Building on previous works on random projections, we also prove its approximation accuracy. To deal with stiffness and sharp gradients, we propose an adaptive step-size scheme and address a continuation method for providing good initial guesses for Newton iterations. The "optimal" bounds of the uniform distribution from which the values of the shape parameters of the Gaussian kernels are sampled and the number of basis functions are "parsimoniously" chosen based on bias-variance trade-off decomposition. To assess the performance of the scheme in terms of both numerical approximation accuracy and computational cost, we used eight benchmark problems (three index-1 DAEs problems, and five stiff ODEs problems including the Hindmarsh-Rose neuronal model of chaotic dynamics and the Allen-Cahn phase-field PDE). The efficiency of the scheme was compared against two stiff ODEs/DAEs solvers, namely, ode15s and ode23t solvers of the MATLAB ODE suite as well as against deep learning as implemented in the DeepXDE library for scientific machine learning and physics-informed learning for the solution of the Lotka-Volterra ODEs included in the demos of the library. A software/toolbox in Matlab (that we call RanDiffNet) with demos is also provided.
Author Fabiani, Gianluca
Siettos, Constantinos
Galaris, Evangelos
Russo, Lucia
Author_xml – sequence: 1
  givenname: Gianluca
  orcidid: 0000-0002-9799-451X
  surname: Fabiani
  fullname: Fabiani, Gianluca
  organization: Scuola Superiore Meridionale, Largo San Marcellino 10, 80138 Napoli (NA), Italy
– sequence: 2
  givenname: Evangelos
  orcidid: 0009-0004-7481-1356
  surname: Galaris
  fullname: Galaris, Evangelos
  organization: Dipartimento di Matematica e Applicazioni "Renato Caccioppoli," Università degli Studi di Napoli Federico II, Corso Umberto I 40, 80138 Napoli (NA), Italy
– sequence: 3
  givenname: Lucia
  orcidid: 0000-0003-4888-467X
  surname: Russo
  fullname: Russo, Lucia
  organization: Istituto di Scienze e Tecnologie per l'Energia e la Mobilità Sostenibili, Consiglio Nazionale delle Ricerche, Via Guglielmo Marconi 4, 80125 Napoli (NA), Italy
– sequence: 4
  givenname: Constantinos
  orcidid: 0000-0002-9568-3355
  surname: Siettos
  fullname: Siettos, Constantinos
  organization: Dipartimento di Matematica e Applicazioni "Renato Caccioppoli," Università degli Studi di Napoli Federico II, Corso Umberto I 40, 80138 Napoli (NA), Italy
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37097940$$D View this record in MEDLINE/PubMed
BookMark eNpNkEtPwzAQhC0Eog848AeQj1xS1nYSJ8eqLQ-pUjnAuXKcjXBJ7GInQP89RhSJ06x2Po12dkJOrbNIyBWDGYNc3GYzYCIrQZyQMYOiTGRe8NN_84hMQtgBAOMiOycjIaGUZQpjEp6UD6Zz1rgh0P3rIRgdEmMb5zusqVe2dh3de7dD3RtnqcXBqzZK_-n8W6ARpMaa3sTlh2oH_IGrFrtAXUM3y1WgMSMiNX4ljC7nq3BBzhrVBrw86pS83K2eFw_JenP_uJivEy0K0SeiBs4UZ1CxBkqEQlcadJZqVTSKYTRklipRZbKpJWZKQJUi5zoXQkqWMz4lN7-58aL3AUO_7UzQ2LbKYmy75QXkICGFNKLXR3SoYu_t3ptO-cP271H8G4bda3A
CitedBy_id crossref_primary_10_1016_j_apm_2025_116127
crossref_primary_10_1016_j_jcp_2024_113433
crossref_primary_10_1016_j_cma_2023_116578
crossref_primary_10_1016_j_matcom_2024_12_004
crossref_primary_10_1137_24M1639890
crossref_primary_10_1016_j_cma_2024_117584
crossref_primary_10_1016_j_compbiolchem_2024_108291
crossref_primary_10_1088_1402_4896_ad6219
crossref_primary_10_3390_sym16111490
crossref_primary_10_1103_l8dq_mphg
crossref_primary_10_1016_j_jcp_2025_113906
crossref_primary_10_1016_j_chaos_2024_115215
crossref_primary_10_1137_24M1686991
crossref_primary_10_1098_rsta_2024_0221
crossref_primary_10_3389_fams_2024_1221051
crossref_primary_10_1016_j_eswa_2024_124678
crossref_primary_10_1137_23M1602991
crossref_primary_10_1109_ACCESS_2024_3457670
crossref_primary_10_1016_j_compbiolchem_2025_108380
crossref_primary_10_1016_j_cam_2025_116635
crossref_primary_10_1103_PhysRevE_111_055302
crossref_primary_10_1016_j_cma_2024_116819
crossref_primary_10_1016_j_nexres_2025_100623
crossref_primary_10_1371_journal_pcbi_1011916
crossref_primary_10_1038_s41467_024_48024_7
ContentType Journal Article
Copyright 2023 Author(s). Published under an exclusive license by AIP Publishing.
Copyright_xml – notice: 2023 Author(s). Published under an exclusive license by AIP Publishing.
DBID NPM
7X8
DOI 10.1063/5.0135903
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Sciences (General)
Physics
EISSN 1089-7682
ExternalDocumentID 37097940
Genre Journal Article
GroupedDBID ---
-~X
.DC
1UP
2-P
29B
4.4
53G
5VS
AAAAW
AABDS
AAEUA
AAPUP
AAYIH
ABJGX
ABJNI
ACBRY
ACGFS
ACLYJ
ACNCT
ACZLF
ADCTM
AEJMO
AENEX
AFATG
AFHCQ
AGKCL
AGLKD
AGMXG
AGTJO
AHSDT
AJJCW
AJQPL
ALEPV
ALMA_UNASSIGNED_HOLDINGS
AQWKA
ATXIE
AWQPM
BDMKI
BPZLN
DU5
EBS
ESX
F5P
FDOHQ
FFFMQ
HAM
M6X
M71
M73
N9A
NPM
NPSNA
O-B
P2P
RIP
RNS
RQS
TAE
WH7
7X8
AAGWI
AMVHM
ID FETCH-LOGICAL-c383t-3d021a210b1f09e08cbc0c54ca8fa1e210754a3b57fd7e5a30b4e22c633771612
IEDL.DBID 7X8
ISICitedReferencesCount 24
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000972044100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1089-7682
IngestDate Fri Jul 11 08:06:59 EDT 2025
Wed Feb 19 02:23:36 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License 2023 Author(s). Published under an exclusive license by AIP Publishing.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c383t-3d021a210b1f09e08cbc0c54ca8fa1e210754a3b57fd7e5a30b4e22c633771612
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-9568-3355
0000-0002-9799-451X
0000-0003-4888-467X
0009-0004-7481-1356
PMID 37097940
PQID 2806070404
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2806070404
pubmed_primary_37097940
PublicationCentury 2000
PublicationDate 2023-Apr-01
20230401
PublicationDateYYYYMMDD 2023-04-01
PublicationDate_xml – month: 04
  year: 2023
  text: 2023-Apr-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Chaos (Woodbury, N.Y.)
PublicationTitleAlternate Chaos
PublicationYear 2023
SSID ssj0001235
Score 2.5253184
Snippet We present a numerical method based on random projections with Gaussian kernels and physics-informed neural networks for the numerical solution of initial...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
Title Parsimonious physics-informed random projection neural networks for initial value problems of ODEs and index-1 DAEs
URI https://www.ncbi.nlm.nih.gov/pubmed/37097940
https://www.proquest.com/docview/2806070404
Volume 33
WOSCitedRecordID wos000972044100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV05T8MwFLaAgsQCtFzlkpEYYLDq2M41oYq2YoDSAVC3yvEhdSApuOL385y46oSExJIhp_Xes_2OL99D6MZoZowVCYlpoXyAoonMGCc2SqgWlilRE5i-P6XjcTad5pOQcHMBVrlaE-uFWlfK58h7vgII5imouF98Et81yldXQwuNTdTi4Mp4SFc6XbOF-_9AG4B9TsCtZitmoYT3PFknj_O6V9YvnmW9w4z2_zu2A7QXfEvcb4yhjTZM2UE7NcZTuQ5qh3ns8G0gm747RG4CkS3oq_RYWNzkORxp6FSNxrCT6eoDh3wN6BB7Akz4SNnAxx2GG_HcI5DgpGcONzj0qHG4svhlMHQY3oFrVkYS4UF_6I7Q22j4-vBIQiMGoiCAXRKuwROQEBwWkaW5oZkqFFWxUDKzMjJwIY2F5EWcWp2aWHJaCMOYSjhPIR6L2DHaKqvSnCLMYptbzmkuo0IoISXXUcFNRLXmmcxNF12vRDwDQ_fVC1kakMBsLeQuOmn0NFs0jBwzntIcFhZ69oenz9GubxnfoG8uUMvCNDeXaFt9L-fu66q2IDiOJ88_LiLRDg
linkProvider ProQuest
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=Parsimonious+physics-informed+random+projection+neural+networks+for+initial+value+problems+of+ODEs+and+index-1+DAEs&rft.jtitle=Chaos+%28Woodbury%2C+N.Y.%29&rft.au=Fabiani%2C+Gianluca&rft.au=Galaris%2C+Evangelos&rft.au=Russo%2C+Lucia&rft.au=Siettos%2C+Constantinos&rft.date=2023-04-01&rft.issn=1089-7682&rft.eissn=1089-7682&rft.volume=33&rft.issue=4&rft_id=info:doi/10.1063%2F5.0135903&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-7682&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-7682&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-7682&client=summon