English
Related papers

Related papers: Thermodynamically Consistent Latent Dynamics Ident…

200 papers

We propose a latent space dynamics identification method, namely tLaSDI, that embeds the first and second principles of thermodynamics. The latent variables are learned through an autoencoder as a nonlinear dimension reduction model. The…

Machine Learning · Computer Science 2024-03-25 Jun Sur Richard Park , Siu Wun Cheung , Youngsoo Choi , Yeonjong Shin

A parametric adaptive physics-informed greedy Latent Space Dynamics Identification (gLaSDI) method is proposed for accurate, efficient, and robust data-driven reduced-order modeling of high-dimensional nonlinear dynamical systems. In the…

Systems and Control · Electrical Eng. & Systems 2023-07-19 Xiaolong He , Youngsoo Choi , William D. Fries , Jon Belof , Jiun-Shyan Chen

Enabling fast and accurate physical simulations with data has become an important area of computational physics to aid in inverse problems, design-optimization, uncertainty quantification, and other various decision-making applications.…

Numerical Analysis · Mathematics 2022-09-07 William Fries , Xiaolong He , Youngsoo Choi

A parametric adaptive greedy Latent Space Dynamics Identification (gLaSDI) framework is developed for accurate, efficient, and certified data-driven physics-informed greedy auto-encoder simulators of high-dimensional nonlinear dynamical…

Machine Learning · Computer Science 2022-11-28 Xiaolong He , Youngsoo Choi , William D. Fries , Jonathan L. Belof , Jiun-Shyan Chen

The parametric greedy latent space dynamics identification (gLaSDI) framework has demonstrated promising potential for accurate and efficient modeling of high-dimensional nonlinear physical systems. However, it remains challenging to handle…

Computational Engineering, Finance, and Science · Computer Science 2025-06-11 Xiaolong He , April Tran , David M. Bortz , Youngsoo Choi

Numerical solving parameterised partial differential equations (P-PDEs) is highly practical yet computationally expensive, driving the development of reduced-order models (ROMs). Recently, methods that combine latent space identification…

Machine Learning · Computer Science 2024-10-08 Xinlei Lin , Dunhui 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…

Recent work in data-driven modeling has demonstrated that a weak formulation of model equations enhances the noise robustness of a wide range of computational methods. In this paper, we demonstrate the power of the weak form to enhance the…

Systems and Control · Electrical Eng. & Systems 2023-11-23 April Tran , Xiaolong He , Daniel A. Messenger , Youngsoo Choi , David M. Bortz

Optimization problems constrained by high-dimensional, time-dependent partial differential equations require repeated forward and sensitivity solves, making high-fidelity optimization computationally prohibitive in many-query design and…

Optimization and Control · Mathematics 2026-05-21 April Tran , Terry Haut , David Bortz , Youngsoo Choi

Numerically solving partial differential equations (PDEs) can be challenging and computationally expensive. This has led to the development of reduced-order models (ROMs) that are accurate but faster than full order models (FOMs). Recently,…

Computational Engineering, Finance, and Science · Computer Science 2024-05-30 Christophe Bonneville , Youngsoo Choi , Debojyoti Ghosh , Jonathan L. Belof

Non-local thermodynamic equilibrium (NLTE) calculations remain a major computational bottleneck in radiation--hydrodynamics, while most existing machine-learning surrogates treat NLTE as a static input--output mapping rather than a kinetic…

Accurate numerical solutions of partial differential equations are essential in many scientific fields but often require computationally expensive solvers, motivating reduced-order models (ROMs). Latent Space Dynamics Identification (LaSDI)…

Machine Learning · Computer Science 2025-10-07 William Anderson , Seung Whan Chung , Youngsoo Choi

Capturing sharp, evolving interfaces remains a central challenge in reduced-order modeling, especially when data is limited and the system exhibits localized nonlinearities or discontinuities. We propose LaSDI-IT (Latent Space Dynamics…

Computational Physics · Physics 2026-04-21 Seung Whan Chung , Christopher Miller , Youngsoo Choi , Paul Tranquilli , H. Keo Springer , Kyle Sullivan

Accurately solving partial differential equations (PDEs) is essential across many scientific disciplines. However, high-fidelity solvers can be computationally prohibitive, motivating the development of reduced-order models (ROMs).…

Machine Learning · Computer Science 2026-04-16 William Anderson , Seung Whan Chung , Robert Stephany , Youngsoo Choi

Predicting the evolution of systems that exhibit spatio-temporal dynamics in response to external stimuli is a key enabling technology fostering scientific innovation. Traditional equations-based approaches leverage first principles to…

Machine Learning · Computer Science 2023-05-02 Francesco Regazzoni , Stefano Pagani , Matteo Salvador , Luca Dede' , Alfio Quarteroni

Accurate characterization of the equilibrium distributions of complex molecular systems and their dependence on environmental factors such as temperature is essential for understanding thermodynamic properties and transition mechanisms.…

Machine Learning · Computer Science 2025-07-08 Yunrui Qiu , Richard John , Lukas Herron , Pratyush Tiwary

In this work, we present the novel mathematical framework of latent dynamics models (LDMs) for reduced order modeling of parameterized nonlinear time-dependent PDEs. Our framework casts this latter task as a nonlinear dimensionality…

Numerical Analysis · Mathematics 2024-12-02 Nicola Farenga , Stefania Fresca , Simone Brivio , Andrea Manzoni

State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where…

Machine Learning · Computer Science 2023-05-03 Zack Xuereb Conti , Ruchi Choudhary , Luca Magri

We propose a method for learning dynamical systems from high-dimensional empirical data that combines variational autoencoders and (spatio-)temporal attention within a framework designed to enforce certain scientifically-motivated…

Machine Learning · Computer Science 2023-06-22 Kai Lagemann , Christian Lagemann , Sach Mukherjee

In this paper, we propose a probabilistic physics-guided framework, termed Physics-guided Deep Markov Model (PgDMM). The framework targets the inference of the characteristics and latent structure of nonlinear dynamical systems from…

Machine Learning · Computer Science 2022-05-26 Wei Liu , Zhilu Lai , Kiran Bacsa , Eleni Chatzi
‹ Prev 1 2 3 10 Next ›