2000 character limit reached
On the feasibility of foundational models for the simulation of physical phenomena (2410.14645v1)
Published 4 Oct 2024 in cs.CE
Abstract: We explore the feasibility of foundation models for the simulation of physical phenomena, with emphasis on continuum (solid and fluid) mechanics. Although so-called learned simulators have shown some success when applied to specific tasks, it remains to be studied to what extent they are able to undergo severe changes in domain shape, boundary conditions and/or constitutive laws and still provide robust (i.e., hallucination-free) and accurate results. In this paper we perform an exhaustive study of these features, put ourselves in the worst-case scenario and study their resistance to such strong changes in their domain of application.
- Learned simulators for turbulence. In International conference on learning representations, 2021.
- Physical design using differentiable learned simulators. arXiv preprint arXiv:2202.00728, 2022.
- Learning interactive real-world simulators. arXiv preprint arXiv:2310.06114, 2023.
- Graph neural networks in particle physics. Machine Learning: Science and Technology, 2(2):021001, 2020.
- Neuralsim: Augmenting differentiable simulators with neural networks. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 9474–9481. IEEE, 2021.
- Alice Cicirello. Physics-enhanced machine learning: a position paper for dynamical systems investigations. arXiv preprint arXiv:2405.05987, 2024.
- Discovering symbolic models from deep learning with inductive biases. Advances in neural information processing systems, 33:17429–17442, 2020.
- Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261, 2018.
- Introducing the center for research on foundation models (crfm). https://hai.stanford.edu/news/introducing-center-research-foundation-models-crfm. Accessed: 2024-09-17.
- A comprehensive survey on pretrained foundation models: A history from bert to chatgpt. arXiv preprint arXiv:2302.09419, 2023.
- A foundation model for clinician-centered drug repurposing. medRxiv, 2024.
- Aurora: A foundation model of the atmosphere. arXiv preprint arXiv:2405.13063, 2024.
- Hype, sustainability, and the price of the bigger-is-better paradigm in ai. https://arxiv.org/abs/2409.14160, 2024.
- The compute divide in machine learning: A threat to academic contribution and scrutiny? arXiv preprint arXiv:2401.02452, 2024.
- Geometric deep learning: Going beyond euclidean data. IEEE Signal Processing Magazine, 34(4):18?42, July 2017.
- A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020.
- Graph neural networks: Taxonomy, advances, and trends. ACM Transactions on Intelligent Systems and Technology (TIST), 13(1):1–54, 2022.
- Learning to simulate complex physics with graph networks. In International conference on machine learning, pages 8459–8468. PMLR, 2020.
- Learning mesh-based simulation with graph networks. arXiv preprint arXiv:2010.03409, 2020.
- Deep learning of thermodynamics-aware reduced-order models from data. Computer Methods in Applied Mechanics and Engineering, 379:113763, June 2021.
- Thermodynamics-informed graph neural networks. arXiv preprint arXiv:2203.01874, 2022.
- A thermodynamics-informed active learning approach to perception and reasoning about fluids. Computational Mechanics, 72(3):577–591, 2023.
- Computational sensing, understanding, and reasoning: An artificial intelligence approach to physics-informed world modeling. Archives of Computational Methods in Engineering, 31(4):1897–1914, 2024.
- A comparison of single-and double-generator formalisms for thermodynamics-informed neural networks. arXiv preprint arXiv:2404.01060, 2024.
- Learning mesh-based simulation with graph networks, 2021.
- Dynamics and thermodynamics of complex fluids. i. development of a general formalism. Phys. Rev. E, 56:6620–6632, Dec 1997.
- Graph neural networks informed locally by thermodynamics. arXiv preprint arXiv:2405.13093, 2024.
- Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems. Computational Mechanics, 72(3):553–561, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.