A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Jingqiao, Bausback, Ryan, Bao, Feng, Zhang, Guannan, Huynh, Phuoc-Toan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915865477251072
author Tang, Jingqiao
Bausback, Ryan
Bao, Feng
Zhang, Guannan
Huynh, Phuoc-Toan
author_facet Tang, Jingqiao
Bausback, Ryan
Bao, Feng
Zhang, Guannan
Huynh, Phuoc-Toan
contents We introduce a score-filter-enhanced data assimilation framework designed to reduce predictive uncertainty in machine learning (ML) models for data-driven dynamical system forecasting. Machine learning serves as an efficient numerical model for predicting dynamical systems. However, even with sufficient data, model uncertainty remains and accumulates over time, causing the long-term performance of ML models to deteriorate. To overcome this difficulty, we integrate data assimilation techniques into the training process to iteratively refine the model predictions by incorporating observational information. Specifically, we apply the Ensemble Score Filter (EnSF), a generative AI-based training-free diffusion model approach, for solving the data assimilation problem in high-dimensional nonlinear complex systems. This leads to a hybrid data assimilation-training framework that combines ML with EnSF to improve long-term predictive performance. We shall demonstrate that EnSF-enhanced ML can effectively reduce predictive uncertainty in ML-based Lorenz-96 system prediction and the Korteweg-De Vries (KdV) equation prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14863
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems
Tang, Jingqiao
Bausback, Ryan
Bao, Feng
Zhang, Guannan
Huynh, Phuoc-Toan
Dynamical Systems
Machine Learning
Probability
We introduce a score-filter-enhanced data assimilation framework designed to reduce predictive uncertainty in machine learning (ML) models for data-driven dynamical system forecasting. Machine learning serves as an efficient numerical model for predicting dynamical systems. However, even with sufficient data, model uncertainty remains and accumulates over time, causing the long-term performance of ML models to deteriorate. To overcome this difficulty, we integrate data assimilation techniques into the training process to iteratively refine the model predictions by incorporating observational information. Specifically, we apply the Ensemble Score Filter (EnSF), a generative AI-based training-free diffusion model approach, for solving the data assimilation problem in high-dimensional nonlinear complex systems. This leads to a hybrid data assimilation-training framework that combines ML with EnSF to improve long-term predictive performance. We shall demonstrate that EnSF-enhanced ML can effectively reduce predictive uncertainty in ML-based Lorenz-96 system prediction and the Korteweg-De Vries (KdV) equation prediction.
title A Score Filter Enhanced Data Assimilation Framework for Data-Driven Dynamical Systems
topic Dynamical Systems
Machine Learning
Probability
url https://arxiv.org/abs/2603.14863