اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMachine learning approaches for feature engineering of the crystal structure: Application to the prediction of the formation energy of cubic compounds
63
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this study, we present a novel approach along with the needed computational strategies for efficient and scalable feature engineering of the crystal structure in compounds of different chemical compositions. This approach utilizes a versatile and extensible framework for the quantification of a three-dimensional (3-D) voxelized crystal structure in the form of 2-point spatial correlations of multiple atomic attributes and performs principal component analysis to extract the low-dimensional features that could be used to build surrogate models for material properties of interest. An application of the proposed feature engineering framework is demonstrated on a case study involving the prediction of the formation energies of crystalline compounds using two vastly different surrogate model building strategies - local Gaussian process regression and neural networks. Specifically, it is shown that the top 25 features (i.e., principal component scores) identified by the proposed framework serve as good regressors for the formation energy of the crystalline substance for both model building strategies.
قيم البحث
اقرأ أيضاً
Harnessing the recent advance in data science and materials science, it is feasible today to build predictive models for materials properties. In this study, we employ the data of high-throughput quantum mechanics calculations based on 170,714 inorga
nic crystalline compounds to train a machine learning model for formation energy prediction. Different from the previous work, our model reaches a fairly good predictive ability (R2=0.982 and MAE=0.07 eVatom-1, DenseNet model) and meanwhile can be universally applied to the large phase space of inorganic materials. The improvement comes from several effective structure-dependent descriptors that are proposed to take the information of electronegativity and structure into account. This model can provide a useful tool to search for new materials in a vast phase space in a fast and cost-effective manner.
High-throughput density-functional calculations of solids are extremely time consuming. As an alternative, we here propose a machine learning approach for the fast prediction of solid-state properties. To achieve this, LSDA calculations are used as t
raining set. We focus on predicting metallic vs. insulating behavior, and on predicting the value of the density of electronic states at the Fermi energy. We find that conventional representations of the input data, such as the Coulomb matrix, are not suitable for the training of learning machines in the case of periodic solids. We propose a novel crystal structure representation for which learning and competitive prediction accuracies become possible within an unrestricted class of spd systems. Due to magnetic phenomena learning on d systems is found more difficult than in pure sp systems.
We propose an approach for exploiting machine learning to approximate electronic fields in crystalline solids subjected to deformation. Strain engineering is emerging as a widely used method for tuning the properties of materials, and this requires r
epeated density functional theory calculations of the unit cell subjected to strain. Repeated unit cell calculations are also required for multi-resolution studies of defects in crystalline solids. We propose an approach that uses data from such calculations to train a carefully architected machine learning approximation. We demonstrate the approach on magnesium, a promising light-weight structural material: we show that we can predict the energy and electronic fields to the level of chemical accuracy, and even capture lattice instabilities.
Drive towards improved performance of machine learning models has led to the creation of complex features representing a database of condensed matter systems. The complex features, however, do not offer an intuitive explanation on which physical attr
ibutes do improve the performance. The effect of the database on the performance of the trained model is often neglected. In this work we seek to understand in depth the effect that the choice of features and the properties of the database have on a machine learning application. In our experiments, we consider the complex phase space of carbon as a test case, for which we use a set of simple, human understandable and cheaply computable features for the aim of predicting the total energy of the crystal structure. Our study shows that (i) the performance of the machine learning model varies depending on the set of features and the database, (ii) is not transferable to every structure in the phase space and (iii) depends on how well structures are represented in the database.
The half-Heusler compound has drawn attention in a variety of fields as a candidate material for thermoelectric energy conversion and spintronics technology. This is because it has various electronic structures, such as semi-metals, semiconductors, a
nd a topological insulator. When the half-Heusler compound is incorporated into the device, the control of high lattice thermal conductivity owing to high crystal symmetry is a challenge for the thermal manager of the device. The calculation for the prediction of lattice thermal conductivity, which is an important physical parameter for controlling the thermal management of the device, requires a calculation cost of several 100 times as much as the usual density functional theory calculation. Therefore, we examined whether lattice thermal conductivity prediction by machine learning was possible on the basis of only the atomic information of constituent elements for thermal conductivity calculated by the density functional theory calculation in various half-Heusler compounds. Consequently, we constructed a machine learning model, which can predict the lattice thermal conductivity with high accuracy from the information of only atomic radius and atomic mass of each site in the half-Heusler type crystal structure. Applying our results, the lattice thermal conductivity for an unknown half-Heusler compound can be immediately predicted. In the future, low-cost and short-time development of new functional materials can be realized, leading to breakthroughs in the search of novel functional materials.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
