Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems

• DOI: 10.48550/arxiv.2307.08423
• Publication Date: 2023-01-01
• Authors: Xuan Zhang; Limei Wang; Jacob Helwig; Youzhi Luo; Cong Fu; Yaochen Xie; Meng Liu; Yuchao Lin; Xu Zhao; Keqiang Yan; Keir Adams; Maurice Weiler; Xiner Li; Tianfan Fu; Yucheng Wang; Haiyang Yu; Yuqing Xie; Xiang Fu; Alex Strasser; Shenglong Xu; Yi Liu; Yuanqi Du; Alexandra Saxton; Hongyi Ling; Hannah R. Lawrence; H. Stärk; Shurui Gui; Carl N. Edwards; Nicholas Gao; Adriana Ladera; Tailin Wu; Elyssa F. Hofgard; Aria Mansouri Teh...; Rui Wang; Ameya Daigavane; Montgomery Bohde; Jerry Kurtin; Qian Huang; Tuong Phung; Minkai Xu; Chaitanya K. Joshi; Simon V. Mathis; Kamyar Azizzadene...; Ada Fang; Alán Aspuru‐Guzik; Erik J. Bekkers; Michael M. Bronstein; Marinka Žitnik; Anima Anandkumar; Stefano Ermon; Píetro Lió; Rose Yu; Stephan Günnemann; Jure Leskovec; Heng Ji; Jimeng Sun; Regina Barzilay; Tommi Jaakkola; Connor W. Coley; Xiaoning Qian; Xiaofeng Qian; Tess Smidt; Shuiwang Ji
• Keywords: Subatomic particle

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries natural sciences. Today, AI has started to advance sciences by improving, accelerating, and enabling our understanding phenomena at wide range spatial temporal scales, giving rise area research known as for science (AI4Science). Being an emerging paradigm, AI4Science is unique that it enormous highly interdisciplinary area. Thus, unified technical treatment this field needed yet challenging. This work aims provide technically thorough account subarea AI4Science; namely, quantum, atomistic, continuum systems. These areas aim the physical world from subatomic (wavefunctions electron density), atomic (molecules, proteins, materials, interactions), macro (fluids, climate, subsurface) scales form important AI4Science. A advantage focusing on these they largely share common set challenges, thereby allowing foundational treatment. key challenge how capture physics first principles, especially symmetries, systems deep learning methods. We in-depth intuitive techniques achieve equivariance symmetry transformations. also discuss other including explainability, out-of-distribution generalization, knowledge transfer with foundation large language models, uncertainty quantification. To facilitate education, we categorized lists resources found be useful. strive hope initial effort may trigger more community interests efforts further