Willow Soohaeng Yoo, Kim Dong Geon, Sundheep R, Hajibabaei Amir, Kim Kwang S, Myung Chang Woo
Department of Energy Science, Sungkyunkwan University, Seobu-ro 2066, Suwon 16419, Korea.
Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge CB2 1EW, UK.
Phys Chem Chem Phys. 2024 Aug 22;26(33):22073-22082. doi: 10.1039/d4cp01801j.
Recent advancements in machine learning potentials (MLPs) have significantly impacted the fields of chemistry, physics, and biology by enabling large-scale first-principles simulations. Among different machine learning approaches, kernel-based MLPs distinguish themselves through their ability to handle small datasets, quantify uncertainties, and minimize over-fitting. Nevertheless, their extensive computational requirements present considerable challenges. To alleviate these, sparsification methods have been developed, aiming to reduce computational scaling without compromising accuracy. In the context of isothermal and isobaric ML molecular dynamics (MD) simulations, achieving precise pressure estimation is crucial for reproducing reliable system behavior under constant pressure. Despite progress, sparse kernel MLPs struggle with precise pressure prediction. Here, we introduce a virial kernel function that significantly enhances the pressure estimation accuracy of MLPs. Additionally, we propose the active sparse Bayesian committee machine (BCM) potential, an on-the-fly MLP architecture that aggregates local sparse Gaussian process regression (SGPR) MLPs. The sparse BCM potential overcomes the steep computational scaling with the kernel size, and a predefined restriction on the size of kernel allows for fast and efficient on-the-fly training. Our advancements facilitate accurate and computationally efficient machine learning-enhanced MD (MLMD) simulations across diverse systems, including ice-liquid coexisting phases, LiGe(PS) lithium solid electrolyte, and high-pressure liquid boron nitride.
机器学习势（MLP）的最新进展通过实现大规模第一性原理模拟，对化学、物理和生物学领域产生了重大影响。在不同的机器学习方法中，基于核的MLP通过其处理小数据集、量化不确定性和最小化过拟合的能力脱颖而出。然而，它们广泛的计算需求带来了相当大的挑战。为了缓解这些问题，已经开发了稀疏化方法，旨在在不影响准确性的情况下降低计算规模。在等温等压ML分子动力学（MD）模拟的背景下，实现精确的压力估计对于在恒压下再现可靠的系统行为至关重要。尽管取得了进展，但稀疏核MLP在精确压力预测方面仍存在困难。在这里，我们引入了一种维里核函数，它显著提高了MLP的压力估计精度。此外，我们提出了主动稀疏贝叶斯委员会机器（BCM）势，这是一种实时MLP架构，它聚合了局部稀疏高斯过程回归（SGPR）MLP。稀疏BCM势克服了与核大小相关的陡峭计算规模，并且对核大小的预定义限制允许快速高效的实时训练。我们的进展促进了跨多种系统的准确且计算高效的机器学习增强MD（MLMD）模拟，包括冰 - 液共存相、LiGe(PS)锂固体电解质和高压液态氮化硼。
