一种完全可微的框架用于训练周期系统中的代理交换关联函数
A fully differentiable framework for training proxy Exchange Correlation Functionals for periodic systems
AI总结:
本文提出一种可微框架,用于训练周期系统中的代理交换关联函数,通过整合机器学习模型提升DFT计算效率,实验结果显示相对误差在5-10%范围内。
摘要:
密度泛函理论(DFT)被广泛用于化学和材料科学中的从头原理模拟,但其计算成本仍然是大系统的主要限制因素。受近期基于机器学习的交换-关联(XC)函数的进展启发,本文介绍了一种可微框架,将机器学习模型整合到密度泛函理论(DFT)中,用于固体和其他周期系统。该框架为神经网络模型定义了一个干净的API,这些模型可以作为传统交换-关联(XC)函数的直接替代品,并使梯度能够通过完整的自洽DFT工作流程流动。该框架使用Python和PyTorch后端实现,使其完全可微,并且易于与标准深度学习工具结合使用。我们将其与DeepChem库集成,以促进已建立模型的重用,并降低实验的门槛。在与已建立的电子结构包(GPAW和PySCF)的初步基准测试中,我们的模型在相对误差上达到5-10%的顺序。
英文摘要:
Density Functional Theory (DFT) is widely used for first-principles simulations in chemistry and materials science, but its computational cost remains a key limitation for large systems. Motivated by recent advances in ML-based exchange-correlation (XC) functionals, this paper introduces a differentiable framework that integrates machine learning models into density functional theory (DFT) for solids and other periodic systems. The framework defines a clean API for neural network models that can act as drop in replacements for conventional exchange-correlation (XC) functionals and enables gradients to flow through the full self-consistent DFT workflow. The framework is implemented in Python using a PyTorch backend, making it fully differentiable and easy to use with standard deep learning tools. We integrate the implementation with the DeepChem library to promote the reuse of established models and to lower the barrier for experimentation. In initial benchmarks against established electronic structure packages (GPAW and PySCF), our models achieve relative errors on the order of 5-10%.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。