非线性系统
高斯分布
数学
算法
匹配(统计)
计算机科学
功能(生物学)
分数
数学优化
应用数学
概率分布
生成模型
特征(语言学)
概率密度函数
高斯过程
混合模型
估计理论
随机过程
噪音(视频)
线性模型
人工智能
随机建模
分布(数学)
生成语法
高斯随机场
统计模型
先验概率
流量(数学)
机器学习
作者
L. T. Giorgini,Fabrizio Falasca,Andre N. Souza
标识
DOI:10.1073/pnas.2509578122
摘要
We present a flexible data-driven framework for estimating the response of higher-order moments of nonlinear stochastic systems to small external perturbations. The classical generalized fluctuation-dissipation theorem (GFDT) links the unperturbed steady-state distribution to the system's linear response. While standard implementations relying on Gaussian approximations can predict the mean response, they often fail to capture changes in higher-order moments. To overcome this, we combine GFDT with score-based generative modeling to estimate the system's score function directly from data. We demonstrate the framework's versatility by employing two complementary score estimation techniques tailored to the system's characteristics: i) a clustering-based algorithm (K-means Gaussian Mixture Modeling) for systems with low-dimensional effective dynamics, and ii) a denoising score matching method implemented with a U-Net architecture for high-dimensional, spatially extended systems where reduced-order modeling is not feasible. Our method is validated on several stochastic models relevant to climate dynamics: three reduced-order models of increasing complexity and a 2D Navier-Stokes model representing a turbulent flow with a localized perturbation. In all cases, the approach accurately captures strongly nonlinear and non-Gaussian features of the system's response, significantly outperforming traditional Gaussian approximations.
科研通智能强力驱动
Strongly Powered by AbleSci AI