arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.09829physics.comp-ph
收藏

原子间相互作用势精确性和可传递性的训练数据选择

Training Data Selection for Accuracy and Transferability of Interatomic Potentials

David Montes de Oca Zapiain, Mitchell A. Wood, Nicholas Lubbers, Carlos Z. Pereyra, Aidan P. Thompson, Danny Perez

摘要:

机器学习(ML)技术的进步使得原子间势的发展成为可能,这些势既保证了第一原理方法的准确性,又保证了经验势的低成本、线性缩放和并行效率。尽管在过去几年中取得了快速进展,但基于ML的电位通常难以实现可转移性,即,在与用于训练模型的配置显著不同的配置之间提供一致的精度。为了真正实现基于ML的原子间势的承诺,因此必须开发系统的和可扩展的方法来生成不同的训练集,以确保广泛覆盖原子环境的空间。这项工作探索了一种通过构造来多样化的方法,该方法利用原子描述符的熵的优化来以自动化的方式为钨创建非常大的($>2\cdot10^{5}$配置,$>7\cdot10^{6}$原子环境)训练集,即,没有任何人为干预。该数据集用于训练多项式以及具有不同结构的多个神经网络势。为了进行比较,还在专家策划的钨数据集上训练了相应的电位族。与专家策划的模型相比,经过熵优化数据训练的模型表现出了非常优越的可移植性。此外,虽然用大量用户输入训练的模型(即,领域专业知识)在类似配置上测试时产生最低的错误,当模型在故意多样化的训练数据集上训练时,样本外预测显着更鲁棒。在这里,我们使用自动化和数据驱动的方法来生成大型和多样化的训练集,展示了准确和可转移的ML潜力的发展。

英文摘要:

Advances in machine learning (ML) techniques have enabled the development of interatomic potentials that promise both the accuracy of first principles methods and the low-cost, linear scaling, and parallel efficiency of empirical potentials. Despite rapid progress in the last few years, ML-based potentials often struggle to achieve transferability, that is, to provide consistent accuracy across configurations that significantly differ from those used to train the model. In order to truly realize the promise of ML-based interatomic potentials, it is therefore imperative to develop systematic and scalable approaches for the generation of diverse training sets that ensure broad coverage of the space of atomic environments. This work explores a diverse-by-construction approach that leverages the optimization of the entropy of atomic descriptors to create a very large ($>2\cdot10^{5}$ configurations, $>7\cdot10^{6}$ atomic environments) training set for tungsten in an automated manner, i.e., without any human intervention. This dataset is used to train polynomial as well as multiple neural network potentials with different architectures. For comparison, a corresponding family of potentials were also trained on an expert-curated dataset for tungsten. The models trained to entropy-optimized data exhibited vastly superior transferability compared to the expert-curated models. Furthermore, while the models trained with heavy user input (i.e., domain expertise) yield the lowest errors when tested on similar configurations, out-sample predictions are dramatically more robust when the models are trained on a deliberately diverse set of training data. Herein we demonstrate the development of both accurate and transferable ML potentials using automated and data-driven approaches for generating large and diverse training sets.

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。

↑