Learning from Imperfect Data: Robust Inference of Dynamic Systems Using Simulation-Based Generative Model

Read full text Summarise with VIRAT
Authors: Hyunwoo Cho, Hyeontae Jo, H. J. Hwang
Cited by: 0
References: 33

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

System inference for nonlinear dynamic models, represented by ordinary differential equations (ODEs), remains a significant challenge in many fields, particularly when the data are noisy, sparse, or partially observable. In this paper, we propose a Simulation-based Generative Model for Imperfect Data (SiGMoID), that enables precise and robust inference for dynamic systems. The proposed approach integrates two key methods: (1) HyperPINN, and (2) W-GAN. We demonstrate that SiGMoID quantifies data noise, estimates system parameters, and infers unobserved system components. Its effectiveness is validated by analyzing examples based on realistic experiments, showcasing its broad applicability in various domains, from scientific research to engineered systems, and enabling the discovery of full system dynamics.

Fields of Study & Subjects

Model Reduction and Neural Networks Gaussian Processes and Bayesian Inference Control Systems and Identification

Publication details

Journal / source
Proceedings of the AAAI Conference on Artificial Intelligence
Volume
40
Issue
43
Pages
36645–36653
Publication date
14 March 2026
Language
EN