Skip to main content
Springer Nature Link
Log in

GMR-Net: GCN-based mesh refinement framework for elliptic PDE problems

  • Original Article
  • Published:
Engineering with Computers Aims and scope Submit manuscript

Abstract

In this study, we propose a new approach for automatically generating high-quality non-uniform meshes based on supervised learning. The proposed framework, GMR-Net, is based on training a graph convolutional neural network (GCN) that learns local error density around each interior vertex in the mesh. The target edge length is then estimated using the predicted local error density. GMR-Net performs vertex-based error estimation as a preprocessing step to avoid expensive error estimation. The proposed GCN-based neural net has new input features for learning the local error density with various polygonal geometries, a range of partial differential equation parameters, and boundary conditions. During the test process, it predicts the target edge length around each interior vertex for the coarse input mesh, and the final non-uniform meshes are generated over the domain using Gmsh. To demonstrate the effectiveness of the GMR-Net, we tested the GMR-Net on Poisson’s equations and linear elasticity problems to previously unseen and new polygonal geometries and a range of PDE coefficients and boundary conditions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Data availability statement

The datasets used for this study are partially available on request to the corresponding author.

References

  1. Shewchuck JR (2002) What is a good linear element? Interpolation, conditioning, and quality measures. In: Proceedings of the 11th international meshing roundtable, pp 115–126

  2. Kim J, Panitanarak T, Shontz SM (2013) A multiobjective mesh optimization framework for mesh quality improvement and mesh untangling. Int J Numer Methods Eng 94:20–42

    Article  MathSciNet  MATH  Google Scholar 

  3. Ainsworth M, Oden JT (1997) A posteriori error estimation in finite element analysis. Comput Methods Appl Mech Eng 142:1–88

    Article  MathSciNet  MATH  Google Scholar 

  4. Bank RE, Weiser A (1985) Some a posteriori error estimators for elliptic partial differential equations. Math Comput 44:283–301

    Article  MathSciNet  MATH  Google Scholar 

  5. Zhang Z, Wang Y, Jimack PK, Wang H (2020) MeshingNet: a new mesh generation method based on deep learning. In: International conference on computational science. Springer, Berlin, pp 186–198

  6. Zhang Z, Jimack PK, Wang H (2021) MeshingNet3D: efficient generation of adapted tetrahedral meshes for computational mechanics. Adv Eng Softw 157:103021

    Article  Google Scholar 

  7. Shewchuk JR (2002) Delaunay refinement algorithms for triangular mesh generation. Comput Geom 22:21–74

    Article  MathSciNet  MATH  Google Scholar 

  8. Zienkiewicz O, Zhu J (1991) Adaptivity and mesh generation. Int J Numer Methods Eng 32:783–810

    Article  MATH  Google Scholar 

  9. Floater MS (2003) Mean value coordinates. Comput Aided Geom Des 20:19–27

    Article  MathSciNet  MATH  Google Scholar 

  10. Chan CL, Scholz F, Takacs T (2022) Locally refined quad meshing for linear elasticity problems based on convolutional neural networks. Eng Comput. arXiv:2203.07843

  11. Geuzaine C, Remacle J-F (2009) Gmsh: a three-dimensional finite element mesh generator with built-in pre- and post-processing facilities. Int J Numer Methods Eng 79:1309–1331

    Article  MATH  Google Scholar 

  12. Yang J, Dzanic T, Petersen B et al (2021) Reinforcement learning for adaptive mesh refinement. arXiv preprint. arXiv:2103.01342

  13. Gillette A, Keith B, Petrides S (2022) Learning robust marking policies for adaptive mesh refinement. arXiv preprint. arXiv:2207.06339

  14. Yang J et al (2022) Multi-agent reinforcement learning for adaptive mesh refinement. arXiv preprint. arXiv:2211.00801

  15. Foucart C, Charous A, Lermusiaux PFJ (2022) Deep reinforcement learning for adaptive mesh refinement. arXiv preprint. arXiv:2209.12351

  16. Pan J, Huang J, Cheng G, Zeng Y (2022) Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach. arXiv preprint. arXiv:2203.11203

  17. Song W et al (2022) M2N: mesh movement networks for PDE solvers. arXiv preprint. arXiv:2204.11188

  18. Pfaff T, Fortunatoet M, Sanchez-Gonzalez A, Battaglia P (2020) Learning mesh-based simulation with graph networks. In: International conference on learning representations

  19. Obiols-Sales O, Vishnu A, Malaya N, Chandramowlishwaran A (2022) NUNet: deep learning for non-uniform super-resolution of turbulent flows. arXiv preprint. arXiv:2203.14154

  20. Chen X, Li T, Wan Q, He X, Gong C, Pang Y, Liu J (2022) MGNet: a novel differential mesh generation method based on unsupervised neural networks. Eng Comput 38:4409–4421

    Article  Google Scholar 

  21. Papagiannopoulos A, Clausen P, Avellan F (2021) How to teach neural networks to mesh: application on 2-D simplicial contours. Neural Netw. 136:152–179

    Article  Google Scholar 

  22. Long Z, Lu Y, Ma X, Dong B (2018) PDE-Net: learning PDEs from data. In: Proceedings of the 35th international conference on machine learning, pp 3208–3216

  23. Chen TQ, Rubanova Y, Bettencourt J, Duvenaud DK (2018) Neural ordinary differential equations. In: Advances in neural information processing systems, pp 6572–6583

  24. Sirignano J, Spiliopoulos K (2018) DGM: a deep learning algorithm for solving partial differential equations. J Comput Phys 375:1339–1364

    Article  MathSciNet  MATH  Google Scholar 

  25. Weinan E, Yu B (2018) The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems. Commun Math Stat 6:1–12

    Article  MathSciNet  MATH  Google Scholar 

  26. Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20:61–80

    Article  Google Scholar 

  27. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations

  28. Hecht F (2012) New development in FreeFem++. J Numer Math 20:251–266

    Article  MathSciNet  MATH  Google Scholar 

  29. Wenming T, Qiu G (2021) Dense graph convolutional neural networks on 3D meshes for 3D object segmentation and classification. Image Vis Comput 114:104265

    Article  Google Scholar 

  30. Huang G, Liu Z, Pleiss G, van der Maaten L, Weinberger KQ (2019) Convolutional networks with dense connectivity. IEEE Trans Pattern Anal Mach Intell 99:1

    Google Scholar 

  31. Wang N, Zhang Y, Li Z, Fu Y, Liu W, Jiang Y (2018) Pixel2mesh: generating 3D mesh models from single RGB images. In: Proceedings of the European conference on computer vision

  32. Wen C, Zhang Y, Li Z, Fu Y (2019) Pixel2mesh++: multi-view 3d mesh generation via deformation. In: Proceedings of the IEEE/CVF international conference on computer vision

  33. Filipe De Avila B, Economon T, Kolter JZ (2020) Combining differentiable PDE solvers and graph neural networks for fluid flow prediction. In: International conference on machine learning

  34. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Conference on computer vision and pattern recognition

  35. Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Conference on computer vision and pattern recognition

  36. Li G, Müller M, Thabet A, Ghanem B (2019) Deep GCNs: can GCNs go as deep as CNNs? In: International conference on computer vision

  37. Fu X et al (2021) An FEA surrogate model with Boundary Oriented Graph Embedding approach. arXiv preprint. arXiv:2108.13509

  38. Paszke A et al (2019) PyTorch: an imperative style, high performance deep learning library. In: Advances in neural information processing systems

  39. Fey M, Lenssen Jan E (2019) Fast graph representation learning with PyTorch. In: ICLR workshop on representation learning on graphs and manifolds

  40. Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations

  41. Lahav A, Tal A (2020) MeshWalker: deep mesh understanding by random walks. ACM Trans Graph 39:1–13

    Article  Google Scholar 

  42. Izhak RB, Lahav A, Tal A (2022) AttWalk: attentive cross-walks for deep mesh analysis. arXiv preprint. arXiv:2104.11571

Download references

Acknowledgements

This work was supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korean Government (MSIT) under Grant NRF-2020R1A2C1007917. This work was also supported in part by the National Research Foundation of Korea (NRF) Grant funded by the Korean Government (MSIT) under Grant NRF-2022R1A4A5034121.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Incheon National University, Incheon, 22012, South Korea

    Minseong Kim, Jaeseung Lee & Jibum Kim

Authors
  1. Minseong Kim
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jaeseung Lee
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Jibum Kim
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Jibum Kim.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kim, M., Lee, J. & Kim, J. GMR-Net: GCN-based mesh refinement framework for elliptic PDE problems. Engineering with Computers 39, 3721–3737 (2023). https://doi.org/10.1007/s00366-023-01811-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00366-023-01811-0

Keywords