近日，美国埃默里大学Justin C. Burton团队报道了物理学量身定制的机器学习揭示尘埃等离子体中意想不到的物理现象。相关论文于2025年7月31日发表在《美国科学院院刊》杂志上。
等离子体是离子、电子和宏观带电粒子的混合物，通常存在于太空和行星环境中。粒子通过周围等离子体介导的库仑力相互作用，因此，粒子之间的有效力可以是非保守的和非互反的。机器学习（ML）模型是学习这些复杂力量的一个很有前景的途径，但它们的结构应该与潜在的物理约束相匹配，以提供有意义的见解。
研究组演示并实验验证了一种机器学习方法，该方法结合了物理直觉来推断实验室等离子体中的力定律。该模型在三维粒子轨迹上进行训练，考虑了粒子的固有对称性、非同一性，并以极高的精度（R2>0.99）学习了粒子之间的有效非互反力。他们通过以两种独立但一致的方式推断粒子质量来验证该模型。该模型的准确性实现了粒子电荷和筛分长度的精确测量，从而识别出与一般理论假设的较大偏差。
研究组从实验数据中识别未知物理的能力证明了机器学习驱动的方法如何在多体系统中指导科学发现的新路线。此外，研究组还预计该机器学习方法将成为从广泛的多体系统（从胶体到生物体）的动力学中推断定律的起点。
附：英文原文
Title: Physics-tailored machine learning reveals unexpected physics in dusty plasmas
Author: Yu, Wentao, Abdelaleem, Eslam, Nemenman, Ilya, Burton, Justin C.
Issue&Volume: 2025-7-31
Abstract: Dusty plasma is a mixture of ions, electrons, and macroscopic charged particles that is commonly found in space and planetary environments. The particles interact through Coulomb forces mediated by the surrounding plasma, and as a result, the effective forces between particles can be nonconservative and nonreciprocal. Machine learning (ML) models are a promising route to learn these complex forces, yet their structure should match the underlying physical constraints to provide useful insight. Here, we demonstrate and experimentally validate an ML approach that incorporates physical intuition to infer force laws in a laboratory dusty plasma. Trained on 3D particle trajectories, the model accounts for inherent symmetries, nonidentical particles, and learns the effective nonreciprocal forces between particles with exquisite accuracy (R2＞0.99). We validate the model by inferring particle masses in two independent yet consistent ways. The model’s accuracy enables precise measurements of particle charge and screening length, identifying large deviations from common theoretical assumptions. Our ability to identify unknown physics from experimental data demonstrates how ML-powered approaches can guide new routes of scientific discovery in many-body systems. Furthermore, we anticipate our ML approach to be a starting point for inferring laws from dynamics in a wide range of many-body systems, from colloids to living organisms.
DOI: 10.1073/pnas.2505725122
Source: https://www.pnas.org/doi/abs/10.1073/pnas.2505725122