Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Abstract
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Cite
@article{arxiv.2307.08423,
title = {Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems},
author = {Xuan Zhang and Limei Wang and Jacob Helwig and Youzhi Luo and Cong Fu and Yaochen Xie and Meng Liu and Yuchao Lin and Zhao Xu and Keqiang Yan and Keir Adams and Maurice Weiler and Xiner Li and Tianfan Fu and Yucheng Wang and Alex Strasser and Haiyang Yu and YuQing Xie and Xiang Fu and Shenglong Xu and Yi Liu and Yuanqi Du and Alexandra Saxton and Hongyi Ling and Hannah Lawrence and Hannes Stärk and Shurui Gui and Carl Edwards and Nicholas Gao and Adriana Ladera and Tailin Wu and Elyssa F. Hofgard and Aria Mansouri Tehrani and Rui Wang and Ameya Daigavane and Montgomery Bohde and Jerry Kurtin and Qian Huang and Tuong Phung and Minkai Xu and Chaitanya K. Joshi and Simon V. Mathis and Kamyar Azizzadenesheli and Ada Fang and Alán Aspuru-Guzik and Erik Bekkers and Michael Bronstein and Marinka Zitnik and Anima Anandkumar and Stefano Ermon and Pietro Liò and Rose Yu and Stephan Günnemann and Jure Leskovec and Heng Ji and Jimeng Sun and Regina Barzilay and Tommi Jaakkola and Connor W. Coley and Xiaoning Qian and Xiaofeng Qian and Tess Smidt and Shuiwang Ji},
journal= {arXiv preprint arXiv:2307.08423},
year = {2025}
}
Comments
Published in Foundations and Trends in Machine Learning. Identical to the journal version except for formatting