Machine-Learned Potentials by Active Learning from Organic Crystal Structure Prediction Landscapes
Machine-Learned Potentials by Active Learning from Organic Crystal Structure Prediction Landscapes
复制标题
DOI：
10.1021/acs.jpca.3c07129
复制
发表时间：
2024-01
期刊：
影响因子：
--
通讯作者：
Patrick W V Butler;R. Hafizi;Graeme M. Day
中科院分区：
文献类型：
--
作者：
Patrick W V Butler;R. Hafizi;Graeme M. Day
有机分子晶体结构预测（CSP）的主要挑战是准确排列潜在结构的能量。虽然高级固态密度泛函理论（DFT）方法可以对低能结构进行可靠的区分，但其高计算成本是有问题的，因为需要评估数万到数十万个试验晶体结构以充分探索典型的晶体能量景观。因此，经常使用成本较低但不太准确的经验力场，有时作为涉及多个阶段的越来越准确的能量计算的分层方案的第一阶段。机器学习原子间势（MLIP）经过训练可以重现从头算方法的结果，计算成本接近力场，可以通过减少或消除昂贵的 DFT 计算来提高 CSP 的效率。在这里，我们研究了使用 CSP 数据集训练 MLIP 的主动学习方法。主动学习与 CSP 成熟的采样方法相结合，在高度自动化的工作流程中产生了潜力，该工作流程与广泛的晶体堆积空间相关。为了展示这些潜力，我们展示了基于力场的 CSP 有效地将大型、多样化的晶体结构景观重新排序到接近 DFT 的精度，从而提高了最终能量排序的可靠性。此外，我们还演示了如何通过蒙特卡罗模拟中的额外即时训练将这些势扩展到远离晶格能量最小值的更准确的模型结构。
A primary challenge in organic molecular crystal structure prediction (CSP) is accurately ranking the energies of potential structures. While high-level solid-state density functional theory (DFT) methods allow for mostly reliable discrimination of the low-energy structures, their high computational cost is problematic because of the need to evaluate tens to hundreds of thousands of trial crystal structures to fully explore typical crystal energy landscapes. Consequently, lower-cost but less accurate empirical force fields are often used, sometimes as the first stage of a hierarchical scheme involving multiple stages of increasingly accurate energy calculations. Machine-learned interatomic potentials (MLIPs), trained to reproduce the results of ab initio methods with computational costs close to those of force fields, can improve the efficiency of the CSP by reducing or eliminating the need for costly DFT calculations. Here, we investigate active learning methods for training MLIPs with CSP datasets. The combination of active learning with the well-developed sampling methods from CSP yields potentials in a highly automated workflow that are relevant over a wide range of the crystal packing space. To demonstrate these potentials, we illustrate efficiently reranking large, diverse crystal structure landscapes to near-DFT accuracy from force field-based CSP, improving the reliability of the final energy ranking. Furthermore, we demonstrate how these potentials can be extended to more accurately model structures far from lattice energy minima through additional on-the-fly training within Monte Carlo simulations.