![[2602.23142] Prediction of Diffusion Coefficients in Mixtures with Tensor Completion](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.23142] Prediction of Diffusion Coefficients in Mixtures with Tensor Completion
Summary
This paper presents a hybrid tensor completion method for predicting temperature-dependent diffusion coefficients in binary mixtures, enhancing accuracy through machine learning and active learning strategies.
Why It Matters
The ability to accurately predict diffusion coefficients is essential for various scientific and industrial applications. This research addresses the limitations of existing models by leveraging machine learning techniques, potentially leading to more efficient experimental designs and better material properties understanding.
Key Takeaways
- Introduces a hybrid tensor completion method for diffusion coefficient prediction.
- Achieves improved accuracy over traditional semi-empirical models.
- Utilizes active learning to expand experimental data for better predictions.
- Demonstrates applicability across a range of temperatures (268 K to 378 K).
- Highlights the integration of ML methods with experimental data acquisition.
Computer Science > Machine Learning arXiv:2602.23142 (cs) [Submitted on 26 Feb 2026] Title:Prediction of Diffusion Coefficients in Mixtures with Tensor Completion Authors:Zeno Romero, Kerstin Münnemann, Hans Hasse, Fabian Jirasek View a PDF of the paper titled Prediction of Diffusion Coefficients in Mixtures with Tensor Completion, by Zeno Romero and 3 other authors View PDF HTML (experimental) Abstract:Predicting diffusion coefficients in mixtures is crucial for many applications, as experimental data remain scarce, and machine learning (ML) offers promising alternatives to established semi-empirical models. Among ML models, matrix completion methods (MCMs) have proven effective in predicting thermophysical properties, including diffusion coefficients in binary mixtures. However, MCMs are restricted to single-temperature predictions, and their accuracy depends strongly on the availability of high-quality experimental data for each temperature of interest. In this work, we address this challenge by presenting a hybrid tensor completion method (TCM) for predicting temperature-dependent diffusion coefficients at infinite dilution in binary mixtures. The TCM employs a Tucker decomposition and is jointly trained on experimental data for diffusion coefficients at infinite dilution in binary systems at 298 K, 313 K, and 333 K. Predictions from the semi-empirical SEGWE model serve as prior knowledge within a Bayesian training framework. The TCM then extrapolates linearly to any t...