Department of Astrophysical Sciences, Princeton University, Princeton, NJ 08 544;
Department of Astrophysical Sciences, Princeton University, Princeton, NJ 08 544.
Proc Natl Acad Sci U S A. 2021 Oct 5;118(40). doi: 10.1073/pnas.2026053118.
We introduce a Bayesian neural network model that can accurately predict not only if, but also when a compact planetary system with three or more planets will go unstable. Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three. Despite being trained on compact resonant and near-resonant three-planet configurations, the model demonstrates robust generalization to both nonresonant and higher multiplicity configurations, in the latter case outperforming models fit to that specific set of integrations. The model computes instability estimates up to [Formula: see text] times faster than a numerical integrator, and unlike previous efforts provides confidence intervals on its predictions. Our inference model is publicly available in the SPOCK (https://github.com/dtamayo/spock) package, with training code open sourced (https://github.com/MilesCranmer/bnn_chaos_model).
我们引入了一个贝叶斯神经网络模型，该模型不仅可以准确预测是否，还可以预测具有三个或更多行星的紧凑行星系统何时会变得不稳定。我们的模型直接从原始轨道要素的短 N 体时间序列中进行训练，在预测不稳定时间方面比分析估算器准确两个数量级以上，同时还将现有机器学习算法的偏差降低了近三分之二。尽管该模型是在紧凑的共振和近共振的三行星配置上进行训练的，但它在非共振和更高多重性配置方面表现出了强大的泛化能力，在后一种情况下，它的表现优于针对该特定集成集拟合的模型。该模型的不稳定估计计算速度比数值积分器快 [Formula: see text] 倍，并且与以前的工作不同，它提供了对其预测的置信区间。我们的推理模型在 SPOCK（https://github.com/dtamayo/spock）包中公开可用，训练代码也已开源（https://github.com/MilesCranmer/bnn_chaos_model）。
