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

2023-07-17

arXiv.org

AI Summary

This study addresses fundamental challenges in AI-driven multiscale physical modeling—including poor interpretability, limited out-of-distribution generalization, difficulty in cross-scale knowledge transfer, and inadequate uncertainty quantification—by proposing a unified framework centered on **equivariance**. The method systematically integrates physics-informed priors (e.g., rotational/translational symmetries, conservation laws) across quantum, atomic, and continuum scales, combining equivariant neural networks, physics-constrained deep learning, foundation-model-based knowledge transfer, and rigorous uncertainty quantification. It further introduces the first taxonomy for cross-scale AI4Science methods. Key contributions include: (1) establishing the first equivariance-driven modeling paradigm spanning multiscale physical systems; (2) releasing an open-source resource index and pedagogical guidelines to advance standardization and education; and (3) providing theoretical foundations and practical pathways toward interpretable, robust, and trustworthy scientific AI.

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.

Problem

• AI enhances understanding of natural phenomena.
• Focus on quantum, atomistic, continuum systems.
• Address symmetry, explainability, generalization in deep learning.

Innovation

• AI enhances natural sciences understanding
• Deep learning captures physics principles
• Unified treatment of quantum, atomistic, continuum systems