INDEEDopt: a deep learning-based ReaxFF parameterization framework
INDEEDopt: a deep learning-based ReaxFF parameterization framework
复制标题
DOI：
10.1038/s41524-021-00534-4
复制
发表时间：
2021-05
影响因子：
9.7
通讯作者：
M. Sengul;Yao Song;Nadire Nayir;Yawei Gao;Ying Hung;Tirthankar Dasgupta;A. V. van Duin
中科院分区：
文献类型：
--
作者：
M. Sengul;Yao Song;Nadire Nayir;Yawei Gao;Ying Hung;Tirthankar Dasgupta;A. V. van Duin
经验原子间势需要优化力场参数，以调整原子间相互作用，以模拟基于量子化学的方法获得的相互作用。参数的优化是复杂的，需要开发新的技术。在这里，我们提出了一个初始设计增强的基于深度学习的优化(INDEEDopt)框架，以加速和提高ReaxFF参数化的质量。该过程从拉丁超立方体设计(LHD)算法开始，该算法用于广泛探索参数景观。LHD将探索区域的信息传递给深度学习模型，深度学习模型找到最小偏差区域并消除不可行区域，构建了对物理上有意义的参数空间更全面的理解。我们演示了镍-铬二元力场和钨-硫化物-碳-氧-氢五元力场的参数化过程。我们表明，与传统的优化方法相比，INDEEDopt在更短的开发时间内产生了更高的精度。
Empirical interatomic potentials require optimization of force field parameters to tune interatomic interactions to mimic ones obtained by quantum chemistry-based methods. The optimization of the parameters is complex and requires the development of new techniques. Here, we propose an INitial-DEsign Enhanced Deep learning-based OPTimization (INDEEDopt) framework to accelerate and improve the quality of the ReaxFF parameterization. The procedure starts with a Latin Hypercube Design (LHD) algorithm that is used to explore the parameter landscape extensively. The LHD passes the information about explored regions to a deep learning model, which finds the minimum discrepancy regions and eliminates unfeasible regions, and constructs a more comprehensive understanding of physically meaningful parameter space. We demonstrate the procedure here for the parameterization of a nickel–chromium binary force field and a tungsten–sulfide–carbon–oxygen–hydrogen quinary force field. We show that INDEEDopt produces improved accuracies in shorter development time compared to the conventional optimization method.