Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThe role of feature space in atomistic learning
241
0
0.0
(
0
)
Added by
Alexander Goscinski
Publication date
2020
fields
Physics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Eficient, physically-inspired descriptors of the structure and composition of molecules and materials play a key role in the application of machine-learning techniques to atomistic simulations. The proliferation of approaches, as well as the fact that each choice of features can lead to very different behavior depending on how they are used, e.g. by introducing non-linear kernels and non-Euclidean metrics to manipulate them, makes it difficult to objectively compare different methods, and to address fundamental questions on how one feature space is related to another. In this work we introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels, in terms of the structure of the feature space that they induce. We define diagnostic tools to determine whether alternative feature spaces contain equivalent amounts of information, and whether the common information is substantially distorted when going from one feature space to another. We compare, in particular, representations that are built in terms of n-body correlations of the atom density, quantitatively assessing the information loss associated with the use of low-order features. We also investigate the impact of different choices of basis functions and hyperparameters of the widely used SOAP and Behler-Parrinello features, and investigate how the use of non-linear kernels, and of a Wasserstein-type metric, change the structure of the feature space in comparison to a simpler linear feature space.
rate research
Read More
It would be a natural expectation that only major peaks, not all of them, would make an important contribution to the characterization of the XRD pattern. We developed a scheme that can identify which peaks are relavant to what extent by using auto-encoder technique to construct a feature space for the XRD peak patterns. Individual XRD patterns are projected onto a single point in the two-dimensional feature space constructed using the method. If the point is significantly shifted when a peak of interest is masked, then we can say the peak is relevant for the characterization represented by the point on the space. In this way, we can formulate the relevancy quantitatively. By using this scheme, we actually found such a peak with a significant peak intensity but low relevancy in the characterization of the structure. The peak is not easily explained by the physical viewpoint such as the higher-order peaks from the same plane index, being a heuristic finding by the power of machine-learning.
Glass transition temperature ($T_{text{g}}$) plays an important role in controlling the mechanical and thermal properties of a polymer. Polyimides are an important category of polymers with wide applications because of their superior heat resistance and mechanical strength. The capability of predicting $T_{text{g}}$ for a polyimide $a~priori$ is therefore highly desirable in order to expedite the design and discovery of new polyimide polymers with targeted properties and applications. Here we explore three different approaches to either compute $T_{text{g}}$ for a polyimide via all-atom molecular dynamics (MD) simulations or predict $T_{text{g}}$ via a mathematical model generated by using machine-learning algorithms to analyze existing data collected from literature. Our simulations reveal that $T_{text{g}}$ can be determined from examining the diffusion coefficient of simple gas molecules in a polyimide as a function of temperature and the results are comparable to those derived from data on polymer density versus temperature and actually closer to the available experimental data. Furthermore, the predictive model of $T_{text{g}}$ derived with machine-learning algorithms can be used to estimate $T_{text{g}}$ successfully within an uncertainty of about 20 degrees, even for polyimides yet to be synthesized experimentally.
FLAME is a software package to perform a wide range of atomistic simulations for exploring the potential energy surfaces (PES) of complex condensed matter systems. The range of methods include molecular dynamics simulations to sample free energy landscapes, saddle point searches to identify transition states, and gradient relaxations to find dynamically stable geometries. In addition to such common tasks, FLAME implements a structure prediction algorithm based on the minima hopping method (MHM) to identify the ground state structure of any system given solely the chemical composition, and a framework to train a neural network potential to reproduce the PES from $textit{ab initio}$ calculations. The combination of neural network potentials with the MHM in FLAME allows a highly efficient and reliable identification of the ground state as well as metastable structures of molecules and crystals, as well as of nano structures, including surfaces, interfaces, and two-dimensional materials. In this manuscript, we provide detailed descriptions of the methods implemented in the FLAME code and its capabilities, together with several illustrative examples.
We establish a machine learning model for the prediction of the magnetization dynamics as function of the external field described by the Landau-Lifschitz-Gilbert equation, the partial differential equation of motion in micromagnetism. The model allows for fast and accurate determination of the response to an external field which is illustrated by a thin-film standard problem. The data-driven method internally reduces the dimensionality of the problem by means of nonlinear model reduction for unsupervised learning. This not only makes accurate prediction of the time steps possible, but also decisively reduces complexity in the learning process where magnetization states from simulated micromagnetic dynamics associated with different external fields are used as input data. We use a truncated representation of kernel principal components to describe the states between time predictions. The method is capable of handling large training sample sets owing to a low-rank approximation of the kernel matrix and an associated low-rank extension of kernel principal component analysis and kernel ridge regression. The approach entirely shifts computations into a reduced dimensional setting breaking down the problem dimension from the thousands to the tens.
The design of next-generation alloys through the Integrated Computational Materials Engineering (ICME) approach relies on multi-scale computer simulations to provide thermodynamic properties when experiments are difficult to conduct. Atomistic methods such as Density Functional Theory (DFT) and Molecular Dynamics (MD) have been successful in predicting properties of never before studied compounds or phases. However, uncertainty quantification (UQ) of DFT and MD results is rarely reported due to computational and UQ methodology challenges. Over the past decade, studies have emerged that mitigate this gap. These advances are reviewed in the context of thermodynamic modeling and information exchange with mesoscale methods such as Phase Field Method (PFM) and Calculation of Phase Diagrams (CALPHAD). The importance of UQ is illustrated using properties of metals, with aluminum as an example, and highlighting deterministic, frequentist and Bayesian methodologies. Challenges facing routine uncertainty quantification and an outlook on addressing them are also presented.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
