paper-with-me

홈 › Papers

Advancing Thermodynamic Group-Contribution Methods by Machine Learning: UNIFAC 2.0

2024-07-25 · Nicolas Hayer, Thorsten Wendel, Stephan Mandt, Hans Hasse, Fabian Jirasek

Accurate prediction of thermodynamic properties is pivotal in chemical engineering for optimizing process efficiency and sustainability. Physical group-contribution (GC) methods are widely employed for this purpose but suffer from historically grown, incomplete parameterizations, limiting their applicability and accuracy. In this work, we overcome these limitations by combining GC with matrix completion methods (MCM) from machine learning. We use the novel approach to predict a complete set of pair-interaction parameters for the most successful GC method: UNIFAC, the workhorse for predicting activity coefficients in liquid mixtures. The resulting new method, UNIFAC 2.0, is trained and validated on more than 224,000 experimental data points, showcasing significantly enhanced prediction accuracy (e.g., nearly halving the mean squared error) and increased scope by eliminating gaps in the original model's parameter table. Moreover, the generic nature of the approach facilitates updating the method with new data or tailoring it to specific applications.

📄 PDF Abstract BibTeX arXiv:2408.05220

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

SPT-NRTL: A physics-guided machine learning model to predict thermodynamically consistent activity coefficients

2022-09-09 · Benedikt Winter, Clemens Winter, Timm Esper, Johannes Schilling 외

The availability of property data is one of the major bottlenecks in the development of chemical processes, often requiring time-consuming and expensive experiments or limiting the design space to a small number of known…

PredictionProperty Prediction

Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse

2021-11-22 · Kim A. Nicoli, Christopher Anders, Lena Funcke, Tobias Hartung 외

Estimating the free energy, as well as other thermodynamic observables, is a key task in lattice field theories. Recently, it has been pointed out that deep generative models can be used in this context [1]. Crucially, t…

BIG-bench Machine Learning

Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges

2024-11-22 · Siya Zhu, Raymundo Arróyave, Doğuhan Sarıtürk

Accurate phase diagram prediction is crucial for understanding alloy thermodynamics and advancing materials design. While traditional CALPHAD methods are robust, they are resource-intensive and limited by experimentally …

Learning to design protein-protein interactions with enhanced generalization

2023-10-27 · Anton Bushuiev, Roman Bushuiev, Petr Kouba, Anatolii Filkin 외

Discovering mutations enhancing protein-protein interactions (PPIs) is critical for advancing biomedical research and developing improved therapeutics. While machine learning approaches have substantially advanced the fi…

Thermodynamic Performance Limits for Score-Based Diffusion Models

2025-10-07 · Nathan X. Kodama, Michael Hinczewski arxiv

We establish a fundamental connection between score-based diffusion models and non-equilibrium thermodynamics by deriving performance limits based on entropy rates. Our main theoretical contribution is a lower bound on t…