Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917218820816896 |
|---|---|
| author | Pornpatcharapong, Wasut |
| author_facet | Pornpatcharapong, Wasut |
| contents | Free energy reconstruction methods such as Gaussian Process Regression (GPR) require Jacobians of the collective variables (CVs), a bottleneck that restricts the use of complex or machine-learned CVs. We introduce a neural network surrogate framework that learns CVs directly from Cartesian coordinates and uses automatic differentiation to provide Jacobians, bypassing analytical forms. On an MgCl2 ion-pairing system, our method achieved high accuracy for both a simple distance CV and a complex coordination-number CV. Moreover, Jacobian errors also followed a near-Gaussian distribution, making them suitable for GPR pipelines. This framework enables gradient-based free energy methods to incorporate complex and machine-learned CVs, broadening the scope of biochemistry and materials simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01396 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems Pornpatcharapong, Wasut Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics Computational Physics Free energy reconstruction methods such as Gaussian Process Regression (GPR) require Jacobians of the collective variables (CVs), a bottleneck that restricts the use of complex or machine-learned CVs. We introduce a neural network surrogate framework that learns CVs directly from Cartesian coordinates and uses automatic differentiation to provide Jacobians, bypassing analytical forms. On an MgCl2 ion-pairing system, our method achieved high accuracy for both a simple distance CV and a complex coordination-number CV. Moreover, Jacobian errors also followed a near-Gaussian distribution, making them suitable for GPR pipelines. This framework enables gradient-based free energy methods to incorporate complex and machine-learned CVs, broadening the scope of biochemistry and materials simulations. |
| title | Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2510.01396 |