Automated crystal structure analysis based on blackbox optimisation

In the present study,we show that time-consuming manual tuning of parameters in the Rietveld method,one of the most frequently used crystal structure analysis methods in materials science,can be automated by considering the entire trial-and-error process as a blackbox optimisation problem.The automation is successfully achieved using Bayesian optimisation,which outperforms both a human expert and an expert-system type automation despite the absence of expertise.This approach stabilises the analysis quality by eliminating human-origin variance and bias,and can be applied to various analysis methods in other areas which also suffer from similar tiresome and unsystematic manual tuning of extrinsic parameters and human-origin variance and bias.

Adaptive design of an X-ray magnetic circular dichroism spectroscopy experiment with Gaussian process modelling

Spectroscopy is a widely used experimental technique,and enhancing its efficiency can have a strong impact on materials research.We propose an adaptive design for spectroscopy experiments that uses a machine learning technique to improve efficiency.We examined X-ray magnetic circular dichroism(XMCD)spectroscopy for the applicability of a machine learning technique to spectroscopy.An XMCD spectrum was predicted by Gaussian process modelling with learning of an experimental spectrum using a limited number of observed data points.Adaptive sampling of data points with maximum variance of the predicted spectrum successfully reduced the total data points for the evaluation of magnetic moments while providing the required accuracy.The present method reduces the time and cost for XMCD spectroscopy and has potential applicability to various spectroscopies.

Automated stopping criterion for spectral measurements with active learning

The automated stopping of a spectral measurement with active learning is proposed.The optimal stopping of the measurement is realised with a stopping criterion based on the upper bound of the posterior average of the generalisation error of the Gaussian process regression.It is revealed that the automated stopping criterion of the spectral measurement gives an approximated X-ray absorption spectrum with sufficient accuracy and reduced data size.The proposed method is not only a proof-of-concept of the optimal stopping problem in active learning but also the key to enhancing the efficiency of spectral measurements for highthroughput experiments in the era of materials informatics.

Automated estimation of materials parameter from X-ray absorption and electron energy-loss spectra with similarity measures

Materials informatics has significantly accelerated the discovery and analysis of materials in the past decade.One of the key contributors to accelerated materials discovery is the use of on-the-fly data analysis with high-throughput experiments,which has given rise to the need for accelerated and accurate automated estimation of the properties of materials.In this regard,spectroscopic data are widely used for materials discovery because these data include essential information about materials.An important requirement for the realisation of the automated estimation of materials parameters is the selection of a similarity measure,or kernel function.The required measure should be robust in terms of peak shifting,peak broadening,and noise.However,the determination of appropriate similarity measures for spectra and the automated estimation of materials parameters from these spectra currently remain unresolved.We examined major similarity measures to evaluate the similarity of both X-ray absorption and electron energy-loss spectra.The similarity measures show good correspondence with the materials parameter,that is,the crystal-field parameter,in all measures.The Pearson's correlation coefficient was the highest for the robustness against noise and peak broadening.We obtained the regression model for the crystal-field parameter 10 Dq from the similarity of the spectra.The regression model enabled the materials parameter,that is,10 Dq,to be automatically estimated from the spectra.With regard to research progress in similarity measures,this methodology would make it possible to extract the materials parameter from a large-scale dataset of experimental data.