English
Related papers

Related papers: Real-time forecasting of chaotic dynamics from spa…

200 papers

Chaos arises in many complex dynamical systems, from weather to power grids, but is difficult to accurately model using data-driven emulators, including neural operator architectures. For chaotic systems, the inherent sensitivity to initial…

Machine Learning · Statistics 2026-04-24 Gabriel Melo , Leonardo Santiago , Peter Y. Lu

Reduced order modeling (ROM) is a field of techniques that approximates complex physics-based models of real-world processes by inexpensive surrogates that capture important dynamical characteristics with a smaller number of degrees of…

Machine Learning · Computer Science 2021-08-30 Rachel Cooper , Andrey A. Popov , Adrian Sandu

Multiscale dynamical systems characterized by interacting fast and slow processes are ubiquitous across scientific domains, from climate dynamics to fluid mechanics. Accurate modeling of such systems requires capturing both the long-term…

Chaotic Dynamics · Physics 2025-11-07 Giulio Del Felice , Ludovico Theo Giorgini

Rapid prediction of the aeroacoustic response is a key component in the design of aircraft and turbomachinery. While it is possible to achieve accurate predictions using direct solution of the compressible Navier-Stokes equations,…

Fluid Dynamics · Physics 2023-05-31 Elnaz Rezaian , Karthik Duraisamy

The paper proposes a systematic framework for building data-driven stochastic differential equation (SDE) models from sparse, noisy observations. Unlike traditional parametric approaches, which assume a known functional form for the drift,…

Machine Learning · Statistics 2025-08-18 Arnab Ganguly , Riten Mitra , Jinpu Zhou

A data-driven algorithm is proposed that employs sparse data from velocity and/or scalar sensors to forecast the future evolution of three dimensional turbulent flows. The algorithm combines time-delayed embedding together with Koopman…

Fluid Dynamics · Physics 2026-03-04 George Papadakis , Shengqi Lu

Spatiotemporal chaotic systems are difficult to characterize in a model-free manner because of their high dimensionality, strong nonlinearity, and sensitivity to initial conditions. Coupled map lattices, as a representative class of…

Chaotic Dynamics · Physics 2026-04-15 Xiaoqi Lei , Zixiang Yan , Jian Gao , Yueheng Lan , Jinghua Xiao

Numerical solvers of partial differential equations (PDEs) have been widely employed for simulating physical systems. However, the computational cost remains a major bottleneck in various scientific and engineering applications, which has…

The accurate forecasting of complex, high-dimensional dynamical systems from observational data is a fundamental task across numerous scientific and engineering disciplines. A significant challenge arises from noise-corrupted measurements,…

Machine Learning · Computer Science 2026-04-14 Xuyang Li , John Harlim , Dibyajyoti Chakraborty , Romit Maulik

Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the…

Machine Learning · Computer Science 2025-07-04 Indranil Nayak , Ananda Chakrabarty , Mrinal Kumar , Fernando Teixeira , Debdipta Goswami

Low-dimensional chaotic systems such as the Lorenz-63 model are commonly used to benchmark system-agnostic methods for learning dynamics from data. Here we show that learning from noise-free observations in such systems can be achieved up…

Chaotic Dynamics · Physics 2025-07-15 Christof Schötz , Niklas Boers

Nonintrusive projection-based reduced order models (ROMs) are essential for dynamics prediction in multi-query applications where access to the source of the underlying full order model (FOM) is unavailable; that is, FOM is a black-box.…

Computational Physics · Physics 2024-10-16 Aviral Prakash , Yongjie Jessica Zhang

Recently, machine learning techniques, particularly deep learning, have demonstrated superior performance over traditional time series forecasting methods across various applications, including both single-variable and multi-variable…

Machine Learning · Computer Science 2025-10-02 Huaiyuan Rao , Yichen Zhao , Qiang Lai

We introduce a data-driven forecasting method for high-dimensional chaotic systems using long short-term memory (LSTM) recurrent neural networks. The proposed LSTM neural networks perform inference of high-dimensional dynamical systems in…

Computational Physics · Physics 2019-09-20 Pantelis R. Vlachas , Wonmin Byeon , Zhong Y. Wan , Themistoklis P. Sapsis , Petros Koumoutsakos

Dynamical systems are ubiquitous and are often modeled using a non-linear system of governing equations. Numerical solution procedures for many dynamical systems have existed for several decades, but can be slow due to high-dimensional…

Machine Learning · Computer Science 2021-09-14 Kaushik Balakrishnan , Devesh Upadhyay

This paper introduces a novel data-driven convergence booster that not only accelerates convergence but also stabilizes solutions in cases where obtaining a steady-state solution is otherwise challenging. The method constructs a…

Fluid Dynamics · Physics 2025-04-09 Xukun Wang , Yilang Liu , Xiang Yang , Weiwei Zhang

We investigate the ability to discover data assimilation (DA) schemes meant for chaotic dynamics with deep learning. The focus is on learning the analysis step of sequential DA, from state trajectories and their observations, using a simple…

Despite advancements in high-performance computing and modern numerical algorithms, computational cost remains prohibitive for multi-query kinetic plasma simulations. In this work, we develop data-driven reduced-order models (ROMs) for…

Numerical Analysis · Mathematics 2025-02-05 Ping-Hsuan Tsai , Seung Whan Chung , Debojyoti Ghosh , John Loffeld , Youngsoo Choi , Jonathan L. Belof

Deep Learning Reduced Order Models (ROMs) are becoming increasingly popular as surrogate models for parametric partial differential equations (PDEs) due to their ability to handle high-dimensional data, approximate highly nonlinear…

Machine Learning · Computer Science 2026-04-09 Iva Mikuš , Boris Muha , Domagoj Vlah

Machine learning and artificial intelligence algorithms typically require large amount of data for training. This means that for nonlinear aeroelastic applications, where small training budgets are driven by the high computational burden…