内爆模拟仅用于设计的高斯过程代理模型的物理状态监督
Physical-state supervision for design-only Gaussian process surrogates of implosion simulations
AI总结:
该研究提出物理状态监督的高斯过程代理模型,从设计变量学习内爆模拟的物理诊断,在有限数据下显著降低预测误差,开源实现可复现结果,专家专业化需通过验证选择。
摘要:
模拟过程中记录的物理诊断可组织出急剧变化的响应,但将其用作代理模型输入通常需要在预测时进行额外计算。我们构建了一种物理状态监督的高斯过程代理模型,该模型从设计变量中学习这些诊断信息。交叉拟合的状态估计补充了保留的设计表示;全局高斯过程以及可选的响应带专家的软混合使用相同的输入。在包含1987对一维内爆的数据库上,从无α粒子加热的计算中学习到的 burn-weighted 状态,使全局预测器在随机留出集和设计空间外推上的均方对数响应误差分别降低了60.25%和52.98%。随机投影和打乱状态的监督无法重现这些增益。对于CH,匹配输入比较显示,在较小的训练预算下专家有帮助,但在该表示下使用1000个设计时专家贡献很小。热反馈基准验证了完整的学习状态程序,而3000个新计算的Be/Cocktail设计则暴露出较弱的外推增益以及专家降低准确性的情况。条件状态误差界将编码敏感性与路由效应区分开。一个开源Python实现可重现存档的预测,并随数据、每个设计的结果以及测量成本一同发布。因此,物理状态监督是有限数据代理模型的有用表示,而专家专业化应通过验证来选择。
英文摘要:
Physical diagnostics recorded during simulation can organize a sharply varying response, but using them as surrogate inputs normally requires another calculation at prediction. We construct a physical-state-supervised Gaussian process surrogate that learns these diagnostics from design variables. Cross-fitted state estimates augment a retained design representation; a global Gaussian process and an optional soft mixture of response-band experts use identical inputs. On a database of 1,987 paired one-dimensional implosions, learned burn-weighted states from calculations without alpha-particle heating reduce mean squared log-response error by 60.25% and 52.98% for the global predictor on random holdout and design-space extrapolation. Random-projection and shuffled-state supervision do not reproduce these gains. For CH, matched-input comparisons show that experts help at smaller training budgets but contribute little at 1,000 designs with this representation. A thermal-feedback benchmark validates the complete learned-state procedure, while 3,000 newly calculated Be/Cocktail designs expose weaker extrapolation gains and cases where experts degrade accuracy. A conditional state-error bound separates encoding sensitivity from routing effects. An open Python implementation reproduces the archived predictions and is released with the data, per-design results, and measured costs. Physical-state supervision is thus a useful representation for finite-data surrogates, whereas expert specialization should be selected by validation.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。