Pith. sign in

REVIEW 48 references

Constitutive Manifold Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.13648 v3 pith:GVSGU2FF submitted 2025-06-16 cs.CE

Wouter J. Schuttert , Mohammed Iqbal Abdul Rasheed , Bojana Rosić This is my paper · ORCID
classification cs.CE
keywords tensorsmanifoldneuralmaterialnetworkstochasticuncertaintiesanisotropic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Anisotropic material properties, such as the thermal conductivities of engineering composites, exhibit variability due to inherent material heterogeneity and manufacturing-related uncertainties. Mathematically, these properties are modeled as symmetric positive definite (SPD) tensors, which reside on a curved Riemannian manifold. Extending this description to a stochastic framework requires preserving both the SPD structure and the underlying spatial symmetries of the tensors. This is achieved through the spectral decomposition of tensors, which enables the parameterization of uncertainties into scale (strength) and rotation (orientation) components. To quantify the impact of strength and orientation uncertainties on the thermal behaviour of the composite, the stochastic material tensor must be propagated through a physics-based forward model. This process necessitates computationally efficient surrogate models, for which a feedforward neural network (FNN) is employed. However, conventional FNN architectures are not well-suited for SPD tensors, as directly using tensor components as input features fails to preserve their underlying geometric structure, often leading to suboptimal performance. To address this issue, we introduce the Constitutive Manifold Neural Network (CMNN), which incorporates input layers that map SPD tensors from the curved manifold to the local tangent space-a flat vector space-thus preserving the statistical and geometric information in the dataset. A case study involving steady-state heat conduction with stochastic anisotropic conductivity demonstrates that geometry-preserving neural network significantly enhances learning performance compared to conventional multilayer perceptrons (MLPs). These findings underscore the importance of manifold-aware methods when working with tensor-valued data in engineering applications.

Discussion (0). Continue with ORCID to comment.

Reference graph

Works this paper leans on

48 extracted references · 42 canonical work pages

  1. [1]

    Field-scale apparent soil electrical conductivity,

    D. L. Corwin and E. Scudiero, “Field-scale apparent soil electrical conductivity,” Soil Science Society of America Journal , vol. 84, no. 5, pp. 1405–1441, 2020. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/saj2.20153. 24

    work page doi:10.1002/saj2.20153 2020

  2. [2]

    Stochastic Finite Element Analysis Framework for Mod- elling Mechanical Properties of Particulate Modified Polymer Composites,

    H. Ahmadi Moghaddam and P. Mertiny, “Stochastic Finite Element Analysis Framework for Mod- elling Mechanical Properties of Particulate Modified Polymer Composites,” Materials, vol. 12, p. 2777, Jan. 2019. Number: 17 Publisher: Multidisciplinary Digital Publishing Institute

    work page 2019

  3. [3]

    A principled approach to conductivity uncertainty analysis in electric field calculations,

    G. B. Saturnino, A. Thielscher, K. H. Madsen, T. R. Kn¨ osche, and K. Weise, “A principled approach to conductivity uncertainty analysis in electric field calculations,” NeuroImage, vol. 188, pp. 821– 834, Mar. 2019

    work page 2019

  4. [4]

    An Introduction to Tensors for Students of Physics and Engineering,

    J. C. Kolecki, “An Introduction to Tensors for Students of Physics and Engineering,”Glenn Research Center, 2002

    work page 2002

  5. [5]

    A review on lightweight materials for defence applications: Present and future de- velopments,

    S. Siengchin, “A review on lightweight materials for defence applications: Present and future de- velopments,” Defence Technology, vol. 24, pp. 1–17, June 2023

    work page 2023

  6. [6]

    Electrical Properties Tomogra- phy: A Methodological Review,

    R. Leijsen, W. Brink, C. van den Berg, A. Webb, and R. Remis, “Electrical Properties Tomogra- phy: A Methodological Review,” Diagnostics, vol. 11, p. 176, Feb. 2021. Number: 2 Publisher: Multidisciplinary Digital Publishing Institute

    work page 2021

  7. [7]

    Digital mapping of GlobalSoilMap soil properties at a broad scale: A review,

    S. Chen, D. Arrouays, V. Leatitia Mulder, L. Poggio, B. Minasny, P. Roudier, Z. Libohova, P. La- gacherie, Z. Shi, J. Hannam, J. Meersmans, A. C. Richer-de Forges, and C. Walter, “Digital mapping of GlobalSoilMap soil properties at a broad scale: A review,” Geoderma, vol. 409, p. 115567, Mar. 2022

    work page 2022

  8. [8]

    Itskov, Tensor Algebra and Tensor Analysis for Engineers: With Applications to Continuum Mechanics

    M. Itskov, Tensor Algebra and Tensor Analysis for Engineers: With Applications to Continuum Mechanics. Mathematical Engineering, Cham: Springer International Publishing, 2015

    work page 2015

Show all 48 references
  1. [9]

    Modeling variability of the electrical conduc- tivity tensor for the induction welding of composites,

    W. J. Schuttert, M. I. Abdul Rasheed, and B. Rosi´ c, “Modeling variability of the electrical conduc- tivity tensor for the induction welding of composites,” PAMM, vol. 24, no. 3, p. e202400058, 2024. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/pamm.202400058

    2024 doi

  2. [10]

    Stochastic modelling of symmetric positive definite material tensors,

    S. K. Shivanand, B. Rosi´ c, and H. G. Matthies, “Stochastic modelling of symmetric positive definite material tensors,” Journal of Computational Physics , vol. 505, p. 112883, May 2024

    2024

  3. [11]

    Modern Monte Carlo methods for efficient uncertainty quantification and propaga- tion: A survey,

    J. Zhang, “Modern Monte Carlo methods for efficient uncertainty quantification and propaga- tion: A survey,” WIREs Computational Statistics , vol. 13, no. 5, p. e1539, 2021. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/wics.1539

    2021 doi

  4. [12]

    Lataniotis, Data-driven uncertainty quantification for high-dimensional engineering problems

    C. Lataniotis, Data-driven uncertainty quantification for high-dimensional engineering problems . phdthesis, ETH Zurich, Nov. 2019

    2019

  5. [13]

    A comparison between (quasi-)Monte Carlo and cubature rule based methods for solving high-dimensional integration problems,

    R. Sch¨ urer, “A comparison between (quasi-)Monte Carlo and cubature rule based methods for solving high-dimensional integration problems,” Mathematics and Computers in Simulation , vol. 62, pp. 509–517, Mar. 2003

    2003

  6. [14]

    Kriging, Polynomial Chaos Expansion, and Low-Rank Approximations in Material Science and Big Data Analytics,

    G. Mahdavi and M. A. Hariri-Ardebili, “Kriging, Polynomial Chaos Expansion, and Low-Rank Approximations in Material Science and Big Data Analytics,” Big Data , Apr. 2023. Publisher: Mary Ann Liebert, Inc., publishers

    2023

  7. [15]

    Surrogate models for uncertainty quantification: An overview,

    B. Sudret, S. Marelli, and J. Wiart, “Surrogate models for uncertainty quantification: An overview,” in 2017 11th European Conference on Antennas and Propagation (EUCAP), pp. 793–797, Mar. 2017. 25

    2017

  8. [16]

    Solving multiphysics-based inverse prob- lems with learned surrogates and constraints,

    Z. Yin, R. Orozco, M. Louboutin, and F. J. Herrmann, “Solving multiphysics-based inverse prob- lems with learned surrogates and constraints,” Advanced Modeling and Simulation in Engineering Sciences, vol. 10, p. 14, Oct. 2023

    2023

  9. [17]

    A review of uncertainty quan- tification in deep learning: Techniques, applications and challenges,

    M. Abdar, F. Pourpanah, S. Hussain, D. Rezazadegan, L. Liu, M. Ghavamzadeh, P. Fieguth, X. Cao, A. Khosravi, U. R. Acharya, V. Makarenkov, and S. Nahavandi, “A review of uncertainty quan- tification in deep learning: Techniques, applications and challenges,” Information Fusion...

    2021

  10. [18]

    Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification,

    R. K. Tripathy and I. Bilionis, “Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification,” Journal of Computational Physics , vol. 375, pp. 565–588, Dec. 2018

    2018

  11. [19]

    Constitu- tive artificial neural networks: A fast and general approach to predictive data-driven constitutive modeling by deep learning,

    K. Linka, M. Hillg¨ artner, K. P. Abdolazizi, R. C. Aydin, M. Itskov, and C. J. Cyron, “Constitu- tive artificial neural networks: A fast and general approach to predictive data-driven constitutive modeling by deep learning,” Journal of Computational Physics , vol. 429, p. 110...

    2021

  12. [20]

    Learning constitutive relations using symmetric positive definite neural networks,

    K. Xu, D. Z. Huang, and E. Darve, “Learning constitutive relations using symmetric positive definite neural networks,” Journal of Computational Physics , vol. 428, p. 110072, Mar. 2021

    2021

  13. [21]

    A new family of Constitutive Artificial Neural Networks towards automated model discovery,

    K. Linka and E. Kuhl, “A new family of Constitutive Artificial Neural Networks towards automated model discovery,” Computer Methods in Applied Mechanics and Engineering , vol. 403, p. 115731, Jan. 2023

    2023

  14. [22]

    Symmetry-enforcing neural networks with applications to constitutive modeling,

    K. Garanger, J. Kraus, and J. J. Rimoli, “Symmetry-enforcing neural networks with applications to constitutive modeling,” Dec. 2023. arXiv:2312.13511 [cond-mat]

    2023 arXiv

  15. [23]

    Pennec, P

    X. Pennec, P. Fillard, and N. Ayache, A Riemannian Framework for Tensor Computing . report, INRIA, 2004. Pages: 34

    2004

  16. [24]

    A Riemannian Framework for Tensor Computing,

    X. Pennec, P. Fillard, and N. Ayache, “A Riemannian Framework for Tensor Computing,” Inter- national Journal of Computer Vision , vol. 66, pp. 41–66, Jan. 2006

    2006

  17. [25]

    Symplectic Model Reduction of Hamiltonian Systems on Nonlinear Manifolds and Approximation with Weakly Symplectic Autoencoder,

    P. Buchfink, S. Glas, and B. Haasdonk, “Symplectic Model Reduction of Hamiltonian Systems on Nonlinear Manifolds and Approximation with Weakly Symplectic Autoencoder,” SIAM journal on scientific computing, vol. 45, pp. A289–A311, Mar. 2023. Publisher: SIAM

    2023

  18. [26]

    A Riemannian Network for SPD Matrix Learning,

    Z. Huang and L. Van Gool, “A Riemannian Network for SPD Matrix Learning,” Dec. 2016. arXiv:1608.04233 [cs]

    2016 arXiv

  19. [27]

    Riemannian batch nor- malization for SPD neural networks,

    D. Brooks, O. Schwander, F. Barbaresco, J.-Y. Schneider, and M. Cord, “Riemannian batch nor- malization for SPD neural networks,” Sept. 2019. arXiv:1909.02414 [cs, stat]

    2019 arXiv

  20. [28]

    Riemannian Residual Neural Networks,

    I. Katsman, E. M. Chen, S. Holalkere, A. Asch, A. Lou, S.-N. Lim, and C. De Sa, “Riemannian Residual Neural Networks,” Oct. 2023. arXiv:2310.10013 [cs, stat]

    2023 arXiv

  21. [29]

    A CNN for homogneous Riemannian manifolds with applications to Neuroimaging,

    R. Chakraborty, M. Banerjee, and B. C. Vemuri, “A CNN for homogneous Riemannian manifolds with applications to Neuroimaging,” Aug. 2018. arXiv:1805.05487 [cs]. 26

    2018 arXiv

  22. [30]

    Anisotropy respecting constitutive neural net- works,

    W. J. Schuttert, M. I. A. Rasheed, and B. Rosi´ c, “Anisotropy respecting constitutive neural net- works,” 9th European Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2024, Oct. 2024

    2024

  23. [31]

    Reciprocal Relations in Irreversible Processes. I.,

    L. Onsager, “Reciprocal Relations in Irreversible Processes. I.,” Physical Review, vol. 37, pp. 405– 426, Feb. 1931. Publisher: American Physical Society

    1931

  24. [32]

    Smooth Manifolds,

    J. M. Lee, “Smooth Manifolds,” in Introduction to Smooth Manifolds (J. M. Lee, ed.), pp. 1–29, New York, NY: Springer, 2003

    2003

  25. [33]

    Gallier and J

    J. Gallier and J. Quaintance, Differential Geometry and Lie Groups: A Computational Perspective , vol. 12 of Geometry and Computing . Cham: Springer International Publishing, 2020

    2020

  26. [34]

    Geometries and Interpolations for Symmetric Positive Definite Matri- ces,

    A. Feragen and A. Fuster, “Geometries and Interpolations for Symmetric Positive Definite Matri- ces,” in Modeling, Analysis, and Visualization of Anisotropy (T. Schultz, E. ¨Ozarslan, and I. Hotz, eds.), (Cham), pp. 85–113, Springer International Publishing, 2017

    2017

  27. [35]

    K. V. Mardia and P. E. Jupp, Directional Statistics. Chichester: John Wiley & Sons, Ltd, 2000

    2000

  28. [36]

    A mathematical theory of communication,

    C. E. Shannon, “A mathematical theory of communication,” The Bell System Technical Journal , vol. 27, pp. 379–423, July 1948. Conference Name: The Bell System Technical Journal

    1948

  29. [37]

    Information Theory and Statistical Mechanics,

    E. T. Jaynes, “Information Theory and Statistical Mechanics,” Physical Review, vol. 106, pp. 620– 630, May 1957. Publisher: American Physical Society

    1957

  30. [38]

    Geometric Means in a Novel Vector Space Struc- ture on Symmetric Positive-Definite Matrices,

    V. Arsigny, P. Fillard, X. Pennec, and N. Ayache, “Geometric Means in a Novel Vector Space Struc- ture on Symmetric Positive-Definite Matrices,” SIAM Journal on Matrix Analysis and Applications , vol. 29, pp. 328–347, Jan. 2007

    2007

  31. [39]

    Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods,

    M. Harandi, M. Salzmann, and R. Hartley, “Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods,” May 2016. arXiv:1605.06182 [cs]

    2016 arXiv

  32. [40]

    Riemannian metrics for neural networks I: feedforward networks,

    Y. Ollivier, “Riemannian metrics for neural networks I: feedforward networks,” Feb. 2015. arXiv:1303.0818 [cs, math]

    2015 arXiv

  33. [41]

    Schwartzman, Random ellipsoids and false discovery rates: statistics for diffusion tensor imaging data

    A. Schwartzman, Random ellipsoids and false discovery rates: statistics for diffusion tensor imaging data. PhD thesis, Stanford University, Jan. 2006

    2006

  34. [42]

    Lognormal Distributions and Geometric Averages of Symmetric Positive Def- inite Matrices,

    A. Schwartzman, “Lognormal Distributions and Geometric Averages of Symmetric Positive Def- inite Matrices,” International Statistical Review , vol. 84, no. 3, pp. 456–486, 2016. eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/insr.12113

    2016 doi

  35. [43]

    Modeling and experimental in- vestigation of induction welding of thermoplastic composites and comparison with other welding processes,

    P. Gouin O’Shaughnessey, M. Dub´ e, and I. Fernandez Villegas, “Modeling and experimental in- vestigation of induction welding of thermoplastic composites and comparison with other welding processes,” Journal of Composite Materials , vol. 50, pp. 2895–2910, Sept. 2016

    2016

  36. [44]

    COMSOL Multiphsyics ® v. 6.2

    “COMSOL Multiphsyics ® v. 6.2..” https://www.comsol.com/. [Accesed 6/8/2025]

    2025

  37. [45]

    Optuna: A Next-generation Hyperpa- rameter Optimization Framework,

    T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A Next-generation Hyperpa- rameter Optimization Framework,” July 2019. arXiv:1907.10902 [cs]. 27

    2019 arXiv

  38. [46]

    Characterisation of Or- thotropic Electrical Conductivity of Unidirectional C/PAEK Thermoplastic Composites,

    Y. Buser, G. Bieleman, W. Grouve, S. Wijskamp, and R. Akkerman, “Characterisation of Or- thotropic Electrical Conductivity of Unidirectional C/PAEK Thermoplastic Composites,” in Pro- ceedings of the 20th European Conference on Composite Materials - Composites Meet Sustainabili...

    2022

  39. [47]

    Simulating the induction heat- ing of cross-ply C/PEKK laminates – sensitivity and effect of material variability,

    W. J. B. Grouve, F. Sacchetti, E. J. Vruggink, and R. Akkerman, “Simulating the induction heat- ing of cross-ply C/PEKK laminates – sensitivity and effect of material variability,” Advanced Composite Materials , vol. 30, pp. 409–430, Sept. 2021. Publisher: Taylor & Francis epr...

    2021

  40. [48]

    Enlighten Project

    “Enlighten Project.” https://www.tpc-enlighten.nl. [Accesed 6/8/2025]. 28

    2025

Pith tools