arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.07895cs.LGphysics.flu-dyn
收藏

用图网络模拟液体

Simulating Liquids with Graph Networks

Jonathan Klimesch, Philipp Holl, Nils Thuerey

摘要:

使用传统模拟器模拟流体等复杂动力学在计算上具有挑战性。深度学习模型已经被提出作为一种有效的替代方案,扩展或取代传统模拟器的部分。我们研究了用于学习流体动力学的图神经网络(GNNs),发现它们的泛化能力比以前的工作所建议的更有限。我们还挑战了目前的做法,增加随机噪声的网络输入,以提高其泛化能力和仿真稳定性。我们发现,插入真实的数据分布,例如通过展开多个模拟步骤,可以提高准确性,并且从学习模型中隐藏所有特定领域的特征可以提高泛化能力。我们的研究结果表明,学习模型(如GNN)无法学习确切的潜在动态,除非训练集没有任何其他可以用作捷径的特定问题相关性。

英文摘要:

Simulating complex dynamics like fluids with traditional simulators is computationally challenging. Deep learning models have been proposed as an efficient alternative, extending or replacing parts of traditional simulators. We investigate graph neural networks (GNNs) for learning fluid dynamics and find that their generalization capability is more limited than previous works would suggest. We also challenge the current practice of adding random noise to the network inputs in order to improve its generalization capability and simulation stability. We find that inserting the real data distribution, e.g. by unrolling multiple simulation steps, improves accuracy and that hiding all domain-specific features from the learning model improves generalization. Our results indicate that learning models, such as GNNs, fail to learn the exact underlying dynamics unless the training set is devoid of any other problem-specific correlations that could be used as shortcuts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑