Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling

• URL: http://arxiv.org/abs/2504.20110v1
• Date: Sun, 27 Apr 2025 17:10:13 GMT
• Title: Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling
• Authors: Yu-hsuan Chen, Jing Bi, Cyril Ngo Ngoc, Victor Oancea, Jonathan Cagan, Levent Burak Kara,
• Abstract summary: AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing.<n>This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models.
• Score: 6.34618828355523
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing. These models leverage data-driven methods to predict physical quantities traditionally requiring computationally expensive simulations. However, the scarcity of labeled CAD-to-simulation datasets has driven recent advancements in self-supervised and foundation models, where geometric representation learning is performed offline and later fine-tuned for specific downstream tasks. While these approaches have shown promise, their effectiveness is limited in applications requiring fine-scale geometric detail preservation. This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models. Unlike traditional end-to-end surrogate models, this approach decouples geometric feature extraction from downstream physics tasks, learning a latent space embedding guided by geometric reconstruction losses. Key elements include the essential use of near-zero level sampling and the innovative batch-adaptive attention-weighted loss function, which enhance the encoding of intricate design features. The proposed method is validated through case studies in structural mechanics, demonstrating strong performance in capturing design features and enabling accurate few-shot physics predictions. Comparisons with traditional parametric surrogate modeling highlight its potential to bridge the gap between geometric and physics-based representations, providing an effective solution for surrogate modeling in data-scarce scenarios.

Related papers

• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems [52.93983926934641]
  This paper proposes a geometry-aware active learning framework for modeling dynamic systems.<n>We develop an adaptive active learning strategy to strategically identify spatial locations for data collection and further maximize the prediction accuracy.
  arXiv  Detail & Related papers  (2025-04-26T19:56:38Z)
• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Physics-Informed Geometric Operators to Support Surrogate, Dimension Reduction and Generative Models for Engineering Design [38.00713966087315]
  We propose a set of physics-informed geometric operators (GOs) to enrich the geometric data provided for training surrogate/discriminative models. GOs exploit the differential and integral properties of shapes to infuse high-level intrinsic geometric information and physics into the feature vector used for training.
  arXiv  Detail & Related papers  (2024-07-10T12:50:43Z)
• Bayesian Mesh Optimization for Graph Neural Networks to Enhance Engineering Performance Prediction [1.6574413179773761]
  In engineering design, surrogate models are widely employed to replace computationally expensive simulations. We propose a Bayesian graph neural network (GNN) framework for a 3D deep-learning-based surrogate model. Our framework determines the optimal size of mesh elements through Bayesian optimization, resulting in a high-accuracy surrogate model.
  arXiv  Detail & Related papers  (2024-06-04T06:27:48Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• Weighted Unsupervised Domain Adaptation Considering Geometry Features and Engineering Performance of 3D Design Data [2.306144660547256]
  We propose a bi-weighted unsupervised domain adaptation approach that considers the geometry features and engineering performance of 3D design data. The proposed model is tested on a wheel impact analysis problem to predict the magnitude of the maximum von Mises stress and the corresponding location of 3D road wheels.
  arXiv  Detail & Related papers  (2023-09-08T00:26:44Z)
• Toward Mesh-Invariant 3D Generative Deep Learning with Geometric Measures [2.167843405313757]
  3D generative modeling is accelerating as the technology allowing the capture of geometric data is developing. Many generative learning algorithms require correspondence between each point when comparing the predicted shape and the target shape. We propose an architecture able to cope with different parameterizations, even during the training phase.
  arXiv  Detail & Related papers  (2023-06-27T19:27:15Z)
• Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning [60.69217130006758]
  We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns. We perform shape optimization experiments on 2D airfoils and discuss the applicable scenarios for the two models.
  arXiv  Detail & Related papers  (2023-05-03T13:45:40Z)
• Graph Neural Network Based Surrogate Model of Physics Simulations for Geometry Design [0.20315704654772412]
  We develop graph neural networks (GNNs) as fast surrogate models for physics simulation. We utilize an encoder-processor-decoder-type architecture which can flexibly make prediction at both node level and graph level. The performance of our proposed GNN-based surrogate model is demonstrated on 2 example applications.
  arXiv  Detail & Related papers  (2023-02-01T16:23:29Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.