Deep materials informatics: Applications of deep learning in materials science

Agrawal, Ankit; Choudhary, Alok

doi:10.1557/mrc.2019.73

Cited by 176 publications

(98 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the application of traditional ML techniques such as Random Forest, Support Vector Machine and Kernel Regression, has become ubiquitous in materials science 10 – 19 , the applications of more advanced deep learning (DL) are still limited 26 – 34 . SchNet 26 used continuous filter convolutional layers to model quantum interactions in molecules for the total energy and interatomic forces that follows fundamental quantum chemical principles.…”

Section: Introductionmentioning

confidence: 99%

Enabling deeper learning on big data for materials informatics applications

Jha

Gupta

Ward

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

show abstract

Section: Introductionmentioning

confidence: 99%

Enabling deeper learning on big data for materials informatics applications

Jha

Gupta

Ward

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms 12 , especially generative adversarial networks (GANs) 13 , have demonstrated outstanding performances in synthesizing highly realistic images 14 – 16 . The material’s microstructure is often represented as micrographs from scanning electron microscopy (SEM).…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based microstructure prediction during laser sintering of alumina

Tang

Geng

Li³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Predicting material’s microstructure under new processing conditions is essential in advanced manufacturing and materials science. This is because the material’s microstructure hugely influences the material’s properties. We demonstrate an elegant machine learning algorithm that faithfully predicts the microstructure under new conditions, without the need of knowing the governing laws. We name this algorithm, RCWGAN-GP, which is regression-based conditional generative adversarial networks with Wasserstein loss function and gradient penalty. This algorithm was trained with experimental SEM micrographs from laser-sintered alumina under various laser powers. The RCWGAN-GP realistically regenerates the SEM micrographs under the trained laser powers. Impressively, it also faithfully predicts the alumina’s microstructure under unexplored laser powers. The predicted microstructure features, including the morphology of the sintered particles and the pores, match the experimental SEM micrographs very well. We further quantitatively examined the prediction accuracy of the RCWGAN-GP. We trained the algorithm with computer-created micrograph datasets of secondary-phase growth governed by the well-known Johnson–Mehl–Avrami (JMA) equation. The RCWGAN-GP accurately regenerates the micrographs at the trained time series, in terms of the grains’ shapes, sizes, and spatial distributions. More importantly, the predicted secondary phase fraction accurately follows the JMA curve.

show abstract

“…Deep learning algorithms [12], especially generative adversarial networks (GANs) [13], have demonstrated outstanding performances in synthesizing highly realistic images [14,15,16]. The material's microstructure is often represented as micrographs from scanning electron microscopy (SEM).…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-based Microstructure Prediction During Laser Sintering of Alumina: A Conditional Generative Approach

Tang

Geng

et al. 2021

Preprint

View full text Add to dashboard Cite

Predicting material’s microstructure under new processing conditions is essential in advanced manufacturing and materials science. This is because the material’s microstructure hugely influences the material’s properties. We demonstrate an elegant machine learning (ML) algorithm that faithfully predicts the microstructure under new conditions, without the need of knowing the governing laws. We name this algorithm, RCWGAN-GP, which is regression-based conditional generative adversarial networks (GANs) with Wasserstein loss function and gradient penalty. This algorithm was trained with experimental SEM micrographs from laser-sintered alumina under various laser powers. The RCWGAN-GP realistically regenerates the SEM micrographs under the trained laser powers. Impressively, it also faithfully predicts the alumina’s microstructure under unexplored laser powers. The predicted microstructure features, including the shapes, sizes, and spatial configuration of the grains and the pores, match the experimental SEM micrographs very well. We further examine the statistical features of the micrograph, which were predicted by RCWCAN-GP. We trained the algorithm with computer-created micrograph datasets of secondary-phase growth governed by the well-known Johnson-Mehl-Avrami (JMA) equation. The RCWGAN-GP accurately regenerates the micrographs at the trained time series, in terms of the grains’ shapes, sizes, and spatial distributions. More importantly, the predicted secondary phase fraction accurately follows the JMA curve.

show abstract

Deep materials informatics: Applications of deep learning in materials science

Abstract: Abstract

Cited by 176 publications

References 73 publications

Enabling deeper learning on big data for materials informatics applications

Enabling deeper learning on big data for materials informatics applications

Machine learning-based microstructure prediction during laser sintering of alumina

Machine Learning-based Microstructure Prediction During Laser Sintering of Alumina: A Conditional Generative Approach

Contact Info

Product

Resources

About