X-ray Diffraction analysis is crucial for understanding material structures but is hindered by complex patterns and the need for expert interpretation.Deep learning offers automation in phase identification but faces ...X-ray Diffraction analysis is crucial for understanding material structures but is hindered by complex patterns and the need for expert interpretation.Deep learning offers automation in phase identification but faces challenges such as data scarcity,overconfidence in predictions and lack of interpretability.This study addresses these by employing Template Element Replacement to generate a perovskite chemical space containing physically unstable virtual structures,enhancing model understanding of XRD-crystal structure relationships and improving classification accuracy by~5%.A Bayesian-VGGNet model was developed,achieving 84%accuracy on simulated spectra and 75%on external experimental data,while simultaneously estimating prediction uncertainty.Evaluation using Bayesian methods revealed low entropy values,indicating high model confidence.Quantifying the importance of input features to crystal symmetry,aligning significant features of seven crystal systems with physical principles.These approaches enhance the model’s robustness and reliability,making it suitable for practical applications.展开更多
基金support from the National Key Research and Development Program of China(grant nos.2021YFA1200904,2020YFA0710700)the National Natural Science Foundation of China(grant nos.12375326)+1 种基金the Innovation Program for IHEP(grant nos.E35457U210)the Postdoctoral Fellowship Program and China Postdoctoral Science Foundation(grant nos.BX20240205),and the directional institutionalized scientific research platform relying on Beijing Synchrotron Radiation Facility of Chinese Academy of Sciences.
文摘X-ray Diffraction analysis is crucial for understanding material structures but is hindered by complex patterns and the need for expert interpretation.Deep learning offers automation in phase identification but faces challenges such as data scarcity,overconfidence in predictions and lack of interpretability.This study addresses these by employing Template Element Replacement to generate a perovskite chemical space containing physically unstable virtual structures,enhancing model understanding of XRD-crystal structure relationships and improving classification accuracy by~5%.A Bayesian-VGGNet model was developed,achieving 84%accuracy on simulated spectra and 75%on external experimental data,while simultaneously estimating prediction uncertainty.Evaluation using Bayesian methods revealed low entropy values,indicating high model confidence.Quantifying the importance of input features to crystal symmetry,aligning significant features of seven crystal systems with physical principles.These approaches enhance the model’s robustness and reliability,making it suitable for practical applications.
