Simulating the microscopic world：from the Schrödinger equation to the large atomic model
-
摘要: 随着人工智能技术的飞速发展，其与物理建模的结合为微观尺度的科学研究带来了革命性的工具。文章介绍了从薛定谔方程出发的量子力学近似求解方法到大原子模型(LAM)的发展历程，并特别关注机器学习技术在原子尺度模拟中的应用。文中首先讨论人工智能与物理建模结合的理论基础，随后深入分析这一结合在原子尺度模拟中的实现方式，包括机器学习模型的构建和训练策略。还探讨了数据积累、软件工具和工程基础设施对推动该领域进步的重要性，并展望了大原子模型在未来科学研究和工业应用中的潜在影响。通过不断的技术创新和跨学科合作，大原子模型将在材料科学、化学工程、生物技术等多个领域发挥重要作用，推动科学研究和工业应用进入新的发展阶段Abstract: With the rapid advance of artificial intelligence, its integration with physical modeling has introduced revolutionary tools for scientific research at the microscopic scale. This paper delineates the development from the approximate solutions of quantum mechanics based on the Schrödinger equation to the emergence of the large atomic model (LAM), with particular emphasis on the application of machine learning in atomic-scale simulations. The theoretical foundations underlying the synergy between artificial intelligence and physical modeling are first discussed. This is followed by a comprehensive analysis of the implementation methodologies for this integration in atomic-scale simulations, including the construction and training strategies of machine learning models. Next, the critical roles of data accumulation, software tools, and engineering infrastructure in propelling advancements in this domain are examined. The potential impact of LAM on future scientific research and industrial applications is also envisioned. Through sustained technological innovation and interdisciplinary collaboration, it is anticipated that LAM will significantly contribute to many fields, including materials science, chemical engineering, and biotechnology, thereby ushering in a new era of development in basic research and applications.
-
-
[1] Feynman R P. The Feynman Lectures on Physics. http://www.feynman lectures.caltech.edu
[2] Dirac P A M. Proceedings of the Royal Society of London，series A，1929，123(792)：714
[3] Schrödinger E. Physical Review，1926，28(6)：1049
[4] Kohn W. Reviews of Modern Physics，1999，71(5)：1253
[5] Pauli W. Exclusion Principle and Quantum Mechanics. In：Writings on Physics and Philosophy，Springer，1946. pp.165—181
[6] Hartree D R. The Wave Mechanics of an Atom with a Noncoulomb Central Field. Part I. Theory and Methods. In：Mathematical Proceedings of the Cambridge Philosophical Society， Cambridge University Press，1928. pp.89—110
[7] Fock V. Zeitschrift für Physik，1930，61：126
[8] Hylleraas E A. Zeitschrift für Physik，1928，48(7)：469
[9] Čížek J. The Journal of Chemical Physics，1966，45(11)：4256
[10] Ceperley D，Chester G V，Kalos M H. Physical Review B，1977， 16(7)：3081
[11] White S R. Phys. Rev. Lett.，1992，69(19)：2863
[12] Knizia G，Chan G K L. Phys. Rev. Lett.，2012，109(18)：186404
[13] Han J Q，Zhang L F et al. Physics Today，2021，74(7)：36
[14] Born M，Oppenheimer R. Annalen der Physik，1927，389(20)： 457
[15] Hohenberg P，Kohn W. Physical Review，1964，136(3B)：B864
[16] Kohn W，Sham L J. Physical Review，1965，140(4A)：A1133
[17] Medvedev M G，Bushmarinov I S，Sun J W et al. Science，2017， 355(6320)：49
[18] Car R，Parrinello M. Phys. Rev. Lett.，1985，55(22)：2471
[19] Jia W L，Wang H，Chen M H et al. Pushing the Limit of Molecular Dynamics With ab initio Accuracy to 100 Million Atoms with Machine Learning. In：SC20：International Conference for High Performance Computing，Networking，Storage and Analysis， IEEE，2020.pp.1—14
[20] Jumper J，Evans R，Pritzel A et al. Nature，2021，596(7873)：583
[21] Behler J，Parrinello M. Phys. Rev. Lett.，2007，98(14)：146401
[22] Zhang L F，Han J W，Wang H et al. Phys. Rev. Lett.，2018，120(14)：143001
[23] Schütt K，Kindermans P J，Felix H E S et al. SchNet：A Continuous-filter Convolutional Neural Network for Modeling Quantum Interactions. In：Advances in Neural Information Processing Systems 30(NIPS 2017)
[24] Artrith N，Morawietz T，Behler J. Physical Review B，2011，83(15)：153101
[25] Zhang L F，Wang H，Muniz M C et al. The Journal of Chemical Physics，2022，156(12)：124107
[26] Grisafi A，Ceriotti M. The Journal of Chemical Physics，2019， 151(20)：204105
[27] Noether E. Nachrichten von der Gesellschaft der Wissenschaften zu Göttingen，Mathematisch-Physikalische Klasse，1918，1918： 235
[28] Hellmann H. Einfuhrung in die quantenchemie. Springer，1937
[29] Feynman R P. Physical Review，1939，56(4)：340
[30] Smith J S，Nebgen B，Lubbers N et al. The Journal of Chemical Physics，2018，148(24)：241733
[31] Zhang L F，Lin D Y，Wang H et al. Physical Review Materials， 2019，3(2)：023804
[32] Zhang L F，Wang H，Car R et al. Phys. Rev. Lett.，2021，126(23)： 236001
[33] Abadi M，Barham P，Chen J M et al. TensorFlow：A System for Large-Scale Machine Learning. In：12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)， 2016. pp.265—283
[34] Paszke A，Gross S，Massa F et al. Advances in Neural Information Processing Systems，2019，32：8026
[35] Wang H，Zhang L F，Han J Q et al. Computer Physics Communications，2018，228：178
[36] Doerr S，Majewski M，Pérez A et al. Journal of Chemical Theory and Computation，2021，17(4)：2355
[37] Liu X，Han Y B，Li Z Y et al. Dflow：A Python Framework for Constructing Cloud-native Ai-for-science Workflows. 2024， arXiv：2404.18392
[38] Li Z Y，Wen T Q，Zhang Y Z et al. An Extendable Cloud-native Alloy Property Explorer. 2024，arXiv：2404.17330
[39] Deng B W，Zhong P C，Jun K et al. Nature Machine Intelligence， 2023，5(9)：1031
[40] Batatia I，Benner P，Chiang Y et al. A Foundation Model For Atomistic Materials Chemistry. 2023，arXiv：2401.00096
[41] Perdew J P，Burke K，Ernzerhof M. Phys. Rev. Lett.，1996，77(18)：3865
[42] Anisimov V I，Zaanen J，Andersen O K. Physical Review B， 1991，44(3)：943
[43] Merchant A，Batzner S，Schoenholz S S et al. Nature，2023，624： 80
[44] Batzner S，Musaelian A，Sun L X et al. SE (3)-equivariant Graph Neural Networks For Data-Efficient And Accurate Interatomic Potentials. 2021，arXiv：2101.03164
[45] Smith J S，Isayev O，Roitberg A E. Scientific Data，2017，4(1)：1
[46] Chai J D，Head-Gordon M. Physical Chemistry Chemical Physics，2008，10(44)：6615
[47] Chanussot L，Das A，Goyal S et al. ACS Catalysis，2021，11(10)： 6059
[48] Hammer B，Hansen L B，Nørskov J K. Physical Review B，1999， 59(11)：7413
[49] Becke A D. The Journal of Chemical Physics，1993，98(2)：1372
[50] Mardirossian N，Head-Gordon M. Molecular Physics，2017，115(19)：2315
[51] Sun J W，Ruzsinszky A，Perdew J P. Phys. Rev. Lett.，2015，115(3)：036402
[52] Kaplan J，McCandlish S，Henighan T et al. Scaling Laws for Neural Language Models. 2020，arXiv：2001.08361
[53] Brown T，Mann B，Ryder N et al. Advances in Neural Information Processing Systems，2020，33：1877
[54] Zhang D，Liu X，Zhang X Y et al. DPA-2：Towards a Universal Large Atomic Model for Molecular and Material Simulation. 2023，arXiv：2312.15492
计量
- 文章访问数: 967
- HTML全文浏览量: 177
- PDF下载量: 1777
下载:
