arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.13282cs.LGcs.AI
收藏

RefreshNet:通过分层刷新学习多尺度动力学

RefreshNet: Learning Multiscale Dynamics through Hierarchical Refreshing

National Institute of Technology Srinagar(斯利那加国立理工学院);Islamic University of Science and Technology(伊斯兰科技大学);ETH Zurich(苏黎世联邦理工学院)

Junaid Farooq, Danish Rafiq, Pantelis R. Vlachas, Mohammad Abid Bazaz

AI总结:

本文提出多尺度框架 RefreshNet,利用卷积自编码器、多时间分辨率 RNN 与分层“刷新”机制缓解长期动力学预测中的误差累积,并在三个基准上显著提升精度与速度。

摘要:

预测复杂系统动力学,尤其是长期预测,始终受到误差累积和计算负担的阻碍。本研究提出了 RefreshNet,这是一个为克服这些挑战而开发的多尺度框架,在计算效率与预测精度之间实现了前所未有的平衡。RefreshNet 结合卷积自编码器来识别降阶潜空间,以捕捉动力学的基本特征,并在潜空间内策略性地采用多个以不同时间分辨率运行的循环神经网络(RNN)模块,从而能够在多个时间尺度上捕捉潜动力学。RefreshNet 中独特的“刷新”机制允许较粗粒度模块重置较细粒度模块的输入,从而有效控制并缓解误差累积。该设计在计算效率和预测精度方面,尤其在长期预测中,展现出相对于现有技术的优越性。该框架通过三个基准应用得到验证:FitzHugh-Nagumo 系统、反应-扩散方程以及 Kuramoto-Sivashinsky 动力学。RefreshNet 在长期预测精度和速度上显著优于最先进方法,标志着复杂系统建模的重大进展,并为理解和预测其行为开辟了新途径。

英文摘要:

Forecasting complex system dynamics, particularly for long-term predictions, is persistently hindered by error accumulation and computational burdens. This study presents RefreshNet, a multiscale framework developed to overcome these challenges, delivering an unprecedented balance between computational efficiency and predictive accuracy. RefreshNet incorporates convolutional autoencoders to identify a reduced order latent space capturing essential features of the dynamics, and strategically employs multiple recurrent neural network (RNN) blocks operating at varying temporal resolutions within the latent space, thus allowing the capture of latent dynamics at multiple temporal scales. The unique "refreshing" mechanism in RefreshNet allows coarser blocks to reset inputs of finer blocks, effectively controlling and alleviating error accumulation. This design demonstrates superiority over existing techniques regarding computational efficiency and predictive accuracy, especially in long-term forecasting. The framework is validated using three benchmark applications: the FitzHugh-Nagumo system, the Reaction-Diffusion equation, and Kuramoto-Sivashinsky dynamics. RefreshNet significantly outperforms state-of-the-art methods in long-term forecasting accuracy and speed, marking a significant advancement in modeling complex systems and opening new avenues in understanding and predicting their behavior.

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。

↑