Lu-H-N Phase Diagram from First-Principles Calculations

Employing a comprehensive structure search and high-throughput first-principles calculation method on 1561 compounds,the present study reveals the phase diagram of Lu-H-N.In detail,the formation energy landscape of Lu-H-N is derived and utilized to assess the thermodynamic stability of each compound that is created via element substitution.The result indicates that there is no stable ternary structure in the Lu-H-N chemical system,however,metastable ternary structures,such as Lu_(20)H_(2)N_(17)(C2/m)and Lu_(2)H_(2)N(P3m1),are observed to have small E_(hull)(<100 meV/atom).It is also found that the energy convex hull of the Lu-H-N system shifts its shape when applying hydrostatic pressure up to 10 GPa,and the external pressure stabilizes a couple of binary phases such as LuN_9 and Lu_(10)H_(21).Additionally,interstitial voids in LuH_(2)are observed,which may explain the formation of Lu_(10)H_(21)and LuH_(3-δ)N_ε.To provide a basis for comparison,x-ray diffraction patterns and electronic structures of some compounds are also presented.

MatCloud, a high-throughput computational materials infrastructure： Present, future visions, and challenges

MatCloud provides a high-throughput computational materials infrastructure for the integrated management of materials simulation, data, and computing resources. In comparison to AFLOW, Material Project, and NoMad, MatCloud delivers two-fold functionalities： a computational materials platform where users can do on-line job setup, job submission and monitoring only via Web browser, and a materials properties simulation database. It is developed under Chinese Materials Genome Initiative and is a China own proprietary high-throughput computational materials infrastructure. MatCloud has been on line for about one year, receiving considerable registered users, feedbacks, and encouragements. Many users provided valuable input and requirements to MatCloud. In this paper, we describe the present MatCloud, future visions, and major challenges. Based on what we have achieved, we will endeavour to further develop MatCloud in an open and collaborative manner and make MatCloud a world known China-developed novel software in the pressing area of high-throughput materials calculations and materials properties simulation database within Material Genome Initiative.

一种预测无机晶体形成能的高精度泛化模型

随着数据科学和材料科学的进步,人们如今可构建出较为准确的人工智能模型,用于材料性质预测.本文中,我们以170,714个无机晶体化合物的高通量第一性原理计算数据集为基础,训练得到了可精确预测无机化合物形成能的机器学习模型.相比于同类工作,本项研究以超大数据集为出发点,构建出无机晶体形成能的高精度泛化模型,可外推至广阔相空间,其中的Dense Net神经网络模型精度可以达到R^(2)=0.982和平均绝对误差(MAE)=0.072 eV atom^(-1).上述模型精度的提升源自一系列新型特征描述符,这些描述符可有效提取出原子与领域原子间的电负性和局域结构等信息,从而精确捕捉到原子间的相互作用.本文为新材料搜索提供了一种高效、低成本的结合能预测手段.