mlsanityData to 7 Oct 2026

Predicting Mechanically Driven Full-Field Quantities of Interest with Deep Learning-Based Metamodels

arXiv 2108.03995 ↗First posted 24 Jul 2021cs.LG physics.data-ancited by 10

Not on the map. Why?

Abstract (arXiv)

Using simulation to predict the mechanical behavior of heterogeneous materials has applications ranging from topology optimization to multi-scale structural analysis. However, full-fidelity simulation techniques such as Finite Element Analysis can be prohibitively computationally expensive when they are used to explore the massive input parameter space of heterogeneous materials. Therefore, there has been significant recent interest in machine learning-based models that, once trained, can predict mechanical behavior at a fraction of the computational cost. Over the past several years, research in this area has been focused mainly on predicting single Quantities of Interest (QoIs). However, there has recently been an increased interest in a more challenging problem: predicting full-field QoI (e.g., displacement/strain fields, damage fields) for mechanical problems. Due to the added complexity of full-field information, network architectures that perform well on single QoI problems may perform poorly in the full-field QoI problem setting. The work presented in this paper is twofold. First, we made a significant extension to the Mechanical MNIST dataset designed to enable the investigation of full field QoI prediction. Specifically, we added Finite Element simulation results of quasi-static brittle fracture in a heterogeneous material captured with the phase-field method. Second, we established strong baseline performance for predicting full-field QoI with MultiRes-WNet architecture. In addition to presenting the results in this paper, we have released our model implementation and the Mechanical MNIST Crack Path dataset under open-source licenses. We anticipate that future researchers will directly use our model architecture on related datasets and potentially design models that exceed the baseline performance for predicting full-field QoI established in this paper.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 27 of its 83 references that are in the map. First posted on arXiv 24 Jul 2021.

Builds on

27 of 83 references.

References · 27

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  10. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  11. 2015Recent Advances in Convolutional Neural Networkscited by 360
  12. 2019MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentationcited by 195
15 more
  1. 2019Transfer learning enhanced physics informed neural network for phase-field modeling of fracturecited by 116
  2. 2017W-Net: A Deep Model for Fully Unsupervised Image Segmentationcited by 57
  3. 2018Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removalcited by 56
  4. 2019Simulation of hyperelastic materials in real-time using Deep Learningcited by 35
  5. 2017Application of Convolutional Neural Network to Predict Airfoil Lift Coefficientcited by 26
  6. 2020Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulationscited by 24
  7. 2020Data-driven topology optimization of spinodoid metamaterials with seamlessly tunable anisotropycited by 22
  8. 2018Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learningcited by 19
  9. 2019Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructurescited by 17
  10. 2021Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamicscited by 14
  11. 2020Exploring the potential of transfer learning for metamodels of heterogeneous material deformationcited by 9
  12. 2017A machine learning approach for efficient uncertainty quantification using multiscale methodscited by 8
  13. 2020Scale bridging materials physics: Active learning workflows and integrable deep neural networks for free energy function representations in alloyscited by 6
  14. 2020Difference-Based Deep Learning Framework for Stress Predictions in Heterogeneous Mediacited by 4
  15. 2021A Data-Driven Approach to Full-Field Damage and Failure Pattern Prediction in Microstructure-Dependent Composites using Deep Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

10 papers.

  1. 2022Towards out of distribution generalization for problems in mechanicscited by 11
  2. 2024A finite operator learning technique for mapping the elastic properties of microstructures to their mechanical deformationscited by 10
  3. 2022Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Datasetcited by 7
  4. 2022Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networkscited by 6
  5. 2024A spatiotemporal deep learning framework for prediction of crack dynamics in heterogeneous solids: efficient mapping of concrete microstructures to its fracture propertiescited by 3
  6. 2022Investigating Deep Learning Model Calibration for Classification Problems in Mechanicscited by 2
  7. 2023Segmenting mechanically heterogeneous domains via unsupervised learningcited by 2
  8. 2025Towards Robust Surrogate Models: Benchmarking Machine Learning Approaches to Expediting Phase Field Simulations of Brittle Fracturecited by 1
  9. 2022Computational Discovery of Energy-Efficient Heat Treatment for Microstructure Design using Deep Reinforcement Learningcited by 0
  10. 2026Diffusion-based Generative Machine Learning Model for Predicting Crack Propagation in Aluminum Nitride at the Atomic Scalecited by 0