这篇论文用可解释神经网络从对称性角度预测原子核质量，WINN模型精度0.430 MeV，还揭示了中子滴线和超重区的新现象，值得搞核物理或AI的人看看。
这篇论文研究SU(3)和SU(4)对称性是否支配整个核素图的核结合能。作者构建了三种神经网络质量模型：FINN（点预测）、GINN（不确定性量化）和WINN（以Casimir算子为基的质量公式）。训练数据为AME2016，验证于AME2020新增核。SU(4)算子单独使均方根误差（RMSE）相较液滴基线在训练和测试集上降低近一半，在外推上降低约五分之一。WINN达到最低验证RMSE为0.430 MeV，与顶级质量模型竞争力相当。WINN还揭示中子滴线附近SU(4)二次Casimir增强（对称性恢复）和超重区四次算子意外增益。
Bridging Ab Initio Symmetries and Global Nuclear Masses with Interpretable Neural Networks
Ab initio modeling has established Wigner's SU(4) and Elliott's SU(3) as dominant symmetries of the nuclear force in light and intermediate-mass nuclei. We ask whether they also govern nuclear binding across the entire chart. Our aim is not high-precision prediction but physical insight, through interpretable, symmetry-based models. From the SU(3) and SU(4) Casimir operators we construct three neural-network (NN) mass models: Feature-Informed NN (FINN) for point predictions, Gaussian-Informed NN (GINN) adding uncertainty quantification, and Wigner-Informed NN (WINN) -- a mass formula using the Casimirs as an operator basis. All are trained on AME2016 and validated on nuclei new to AME2020. The SU(4) operators alone cut the root-mean-square error (RMSE) by nearly half on train and test data, and by about a fifth on extrapolation, relative to the liquid-drop baseline -- showing that Wigner's symmetry carries predictive information beyond bulk properties. Despite its compact form, WINN reaches the lowest validation RMSE, 0.430 MeV -- competitive with state-of-the-art mass models -- which we read less as a benchmark than as evidence that its symmetry basis captures important physics. WINN further reveals i) an enhancement of the quadratic SU(4) Casimir near the neutron dripline, signaling restoration of Wigner's symmetry, and ii) an unexpected gain of the quartic operator in the superheavy region. We thereby elevate emergent symmetries from the hidden order within individual nuclei to a governing principle of the whole nuclear chart.