paper-with-me

홈 › Papers

Learning to Assimilate in Chaotic Dynamical Systems

2021-11-01 · NeurIPS 2021 12 · Michael McCabe, Jed Brown

The accuracy of simulation-based forecasting in chaotic systems is heavily dependent on high-quality estimates of the system state at the time the forecast is initialized. Data assimilation methods are used to infer these initial conditions by systematically combining noisy, incomplete observations and numerical models of system dynamics to produce effective estimation schemes. We introduce amortized assimilation, a framework for learning to assimilate in dynamical systems from sequences of noisy observations with no need for ground truth data. We motivate the framework by extending powerful results from self-supervised denoising to the dynamical systems setting through the use of differentiable simulation. Experimental results across several benchmark systems highlight the improved effectiveness of our approach over widely-used data assimilation methods.

📄 PDF Abstract BibTeX arXiv:2111.01058

Code (1)

mikemccabe210/amortizedassimilation 공식 구현 pytorch

Tasks

Denoising

Similar Papers 제목 키워드 기반

Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systems

2026-03-13 · Dibyajyoti Chakraborty, Hojin Kim, Romit Maulik arxiv

High-fidelity numerical simulations of chaotic, high dimensional nonlinear dynamical systems are computationally expensive, necessitating the development of efficient surrogate models. Most surrogate models for such syst…

Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components

2021-02-15 · Alexander Wikner, Jaideep Pathak, Brian R. Hunt, Istvan Szunyogh 외

We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is in the form of noisy partial measurements of the past and present state of the dynamical system. Recently there…

BIG-bench Machine Learning

Data-Assimilated Model-Based Reinforcement Learning for Partially Observed Chaotic Flows

2025-04-23 · Defne E. Ozan, Andrea Nóvoa, Luca Magri

The goal of many applications in energy and transport sectors is to control turbulent flows. However, because of chaotic dynamics and high dimensionality, the control of turbulent flows is exceedingly difficult. Model-fr…

Model-based Reinforcement LearningReinforcement Learning (RL)State Estimation

Data-assimilated model-informed reinforcement learning

2025-06-02 · Defne E. Ozan, Andrea Nóvoa, Georgios Rigas, Luca Magri

The control of spatio-temporally chaos is challenging because of high dimensionality and unpredictability. Model-free reinforcement learning (RL) discovers optimal control policies by interacting with the system, typical…

modelreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Analysis of chaotic dynamical systems with autoencoders

2021-09-22 · N. Almazova, G. D. Barmparis, G. P. Tsironis

We focus on chaotic dynamical systems and analyze their time series with the use of autoencoders, i.e., configurations of neural networks that map identical output to input. This analysis results in the determination of …

Time SeriesTime Series Analysis