Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2512.23840 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911344766222336 |
|---|---|
| author | Monti, Edoardo Yatsyshin, Peter Gkagkas, Konstantinos Duncan, Andrew B. |
| author_facet | Monti, Edoardo Yatsyshin, Peter Gkagkas, Konstantinos Duncan, Andrew B. |
| contents | Predicting interfacial thermodynamics across molecular and continuum scales remains a central challenge in computational science. Classical density functional theory (cDFT) provides a first-principles route to connect microscopic interactions with macroscopic observables, but its predictive accuracy depends on approximate free-energy functionals that are difficult to generalize. Here we introduce a physics-informed learning framework that augments cDFT with neural corrections trained directly against molecular-dynamics data through adjoint optimization. Rather than replacing the theory with a black-box surrogate, we embed compact neural networks within the Helmholtz free-energy functional, learning local and nonlocal corrections that preserve thermodynamic consistency while capturing missing correlations. Applied to Lennard-Jones fluids, the resulting augmented excess free-energy functional quantitatively reproduces equilibrium density profiles, coexistence curves, and surface tensions across a broad temperature range, and accurately predicts contact angles and droplet shapes far beyond the training regime. This approach combines the interpretability of statistical mechanics with the adaptability of modern machine learning, establishing a general route to learned thermodynamic functionals that bridge molecular simulations and continuum-scale models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23840 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Density Functionals to Bridge Particle and Continuum Scales Monti, Edoardo Yatsyshin, Peter Gkagkas, Konstantinos Duncan, Andrew B. Computational Physics Statistical Mechanics Predicting interfacial thermodynamics across molecular and continuum scales remains a central challenge in computational science. Classical density functional theory (cDFT) provides a first-principles route to connect microscopic interactions with macroscopic observables, but its predictive accuracy depends on approximate free-energy functionals that are difficult to generalize. Here we introduce a physics-informed learning framework that augments cDFT with neural corrections trained directly against molecular-dynamics data through adjoint optimization. Rather than replacing the theory with a black-box surrogate, we embed compact neural networks within the Helmholtz free-energy functional, learning local and nonlocal corrections that preserve thermodynamic consistency while capturing missing correlations. Applied to Lennard-Jones fluids, the resulting augmented excess free-energy functional quantitatively reproduces equilibrium density profiles, coexistence curves, and surface tensions across a broad temperature range, and accurately predicts contact angles and droplet shapes far beyond the training regime. This approach combines the interpretability of statistical mechanics with the adaptability of modern machine learning, establishing a general route to learned thermodynamic functionals that bridge molecular simulations and continuum-scale models. |
| title | Learning Density Functionals to Bridge Particle and Continuum Scales |
| topic | Computational Physics Statistical Mechanics |
| url | https://arxiv.org/abs/2512.23840 |