paper-with-me

Papers

Thermodynamics-Consistent Graph Neural Networks

2024-07-08 · Jan G. Rittig, Alexander Mitsos

We propose excess Gibbs free energy graph neural networks (GE-GNNs) for predicting composition-dependent activity coefficients of binary mixtures. The GE-GNN architecture ensures thermodynamic consistency by predicting the molar excess Gibbs free energy and using thermodynamic relations to obtain activity coefficients. As these are differential, automatic differentiation is applied to learn the activity coefficients in an end-to-end manner. Since the architecture is based on fundamental thermodynamics, we do not require additional loss terms to learn thermodynamic consistency. As the output is a fundamental property, we neither impose thermodynamic modeling limitations and assumptions. We demonstrate high accuracy and thermodynamic consistency of the activity coefficient predictions.

📄 PDF Abstract BibTeX arXiv:2407.18372

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bond Graphs Unify Stoichiometric Analysis and Thermodynamics

2020-07-31 · Peter J. Gawthrop

Whole-cell modelling is constrained by the laws of nature in general and the laws of thermodynamics in particular. This paper shows how one prolific source of information, stoichiometric models of biomolecular systems, c…

A Test of the Thermodynamics of Evolution

2024-05-20 · Daniel Sadasivan, Cole Cantu, Cecilia Marsh, Andrew Graham

Recent research has extended methods from the fields of thermodynamics and statistical mechanics into other disciplines. Most notably, one recent work creates a unified theoretical framework to understand evolutionary bi…

Graph neural networks informed locally by thermodynamics

2024-05-21 · Alicia Tierz, Iciar Alfaro, David González, Francisco Chinesta 외

Thermodynamics-informed neural networks employ inductive biases for the enforcement of the first and second principles of thermodynamics. To construct these biases, a metriplectic evolution of the system is assumed. This…

Computational Efficiency

Physically Consistent Neural ODEs for Learning Multi-Physics Systems

2022-11-11 · Muhammad Zakwan, Loris Di Natale, Bratislav Svetozarevic, Philipp Heer 외

Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, they might consequently make physically in…

From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics

2025-08-29 · Anna Geißler, Luca-Sophie Bien, Friedrich Schöppler, Tobias Hertel arxiv

Large language models (LLMs) are increasingly considered as tutoring aids in science education. Yet their readiness for unsupervised use in undergraduate instruction remains uncertain, as reliable teaching requires more …

Question Answering