arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.12199physics.ao-phnlin.AOphysics.comp-phphysics.data-an
收藏

通过多层随机分层延迟模型的混合贝叶斯学习解决涌现拍频模式

Resolving Emergent Beat Patterns Through Hybrid Bayesian Learning of Multilayered Stochastic Hierarchical Delay Models

University of California, Los Angeles(加州大学洛杉矶分校);Weizmann Institute of Science(魏茨曼科学研究所);University of Colorado, Boulder(科罗拉多大学博尔德分校);National Oceanic and Atmospheric Administration (NOAA)(美国国家海洋和大气管理局);Virginia Tech(弗吉尼亚理工大学)

Mickaël D. Chekroun, Tom Dror, Ilan Koren, Honghu Liu

AI总结:

该研究针对复杂系统多尺度模式建模难题,提出MSHDMs模型,采用混合离线-在线贝叶斯优化框架校准,仅用6个超参数即可捕获云场湍流系统的时空相干性,为跨学科领域解决潜AM-FM拍频模式提供通用工具。

摘要:

对复杂系统中涌现的多尺度模式进行建模仍是一个持续存在的跨学科挑战,尤其是在从极为有限的数据中解读瞬态、高度耦合的动力学过程时。为克服标准有限维随机模型固有的频谱稀疏性,我们提出了多层随机分层延迟模型(Multilayered Stochastic Hierarchical Delay Models,MSHDMs)。通过将动力学嵌入分层延迟结构中,MSHDMs利用无限维相空间来构建生成复杂调幅-调频(AM-FM)动力学所需的高频谱密度,避免了数据密集型的神经网络参数化。为了从短时间观测记录中可靠地校准这些敏感结构,我们采用了一种混合离线-在线贝叶斯优化框架。该算法绕过了传统轨迹匹配的失效点,通过严格遵循与经验全局小波谱(Global Wavelet Spectrum)的频谱一致性,自主学习最优潜坐标和连续分数延迟。将该方法应用于大陆云场的高分辨率卫星观测,所得随机模拟器仅用6个超参数就捕获了湍流系统的完整时空相干性。小波标量图显示,该模型天然生成了涌现的波包动力学和跨尺度能量级联,恢复了半日、中尺度及单个云的时间尺度。凭借严谨的数学基础和稳健的数据驱动校准,MSHDMs为解决跨学科领域的潜AM-FM拍频模式提供了一种高度可压缩的通用工具。

英文摘要:

Modeling emergent, multiscale patterns in complex systems remains a persistent interdisciplinary challenge, particularly when deciphering transient, highly coupled dynamics from severely limited data. To overcome the inherent spectral sparsity of standard finite-dimensional stochastic models, we introduce Multilayered Stochastic Hierarchical Delay Models (MSHDMs). By embedding dynamics within a hierarchical delay structure, MSHDMs leverage an infinite-dimensional phase space to engineer the high spectral density required for generating complex Amplitude-Frequency Modulation (AM-FM) dynamics, avoiding data-heavy neural network parameterizations. To reliably calibrate these sensitive structures from short observational records, we deploy a hybrid offline-online Bayesian optimization framework. Bypassing the failure points of traditional trajectory matching, our algorithm autonomously learns optimal latent coordinates and continuous fractional delays by strictly enforcing spectral consistency against the empirical Global Wavelet Spectrum. Applying this methodology to high-resolution satellite observations of continental cloud fields, the resulting stochastic emulator captures the full spatiotemporal coherence of the turbulent system using just 6 hyperparameters. The wavelet scalograms demonstrate how the model natively generates emergent wave-packet dynamics and cross-scale energy cascades, recovering semidiurnal, mesoscale, and individual cloud timescales. Supported by rigorous mathematical foundations and robust data-driven calibrations, MSHDMs thus provide a highly compressible, general-purpose tool for resolving latent AM-FM beat patterns across diverse disciplines.

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。

↑