Convolutional Neural Networks for Crystal Material Property Prediction Using Hybrid Orbital-Field Matrix and Magpie Descriptors

Cao, Zhuo; Dan, Yabo; Xiong, Zheng; Niu, Chengcheng; Li, Xiang; Qian, Songrong; Hu, Jianjun

doi:10.3390/cryst9040191

Cited by 49 publications

(30 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RF algorithms have demonstrated strong prediction performance when combined with composition features in our previous studies. 13 In our RF regression models, “mse” was used as our criterion. The number of trees, max features, max depth, min samples split, and min samples leaf were set to 100, 70, 32, 8, and 1, respectively, in the RF algorithm which was implemented using the Scikit-Learn library in Python 3.6.…”

Section: Methodsmentioning

confidence: 99%

Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning

Yang

Dong

et al. 2021

ACS Omega

Self Cite

View full text Add to dashboard Cite

Lattice constants such as unit cell edge lengths and plane angles are important parameters of the periodic structures of crystal materials. Predicting crystal lattice constants has wide applications in crystal structure prediction and materials property prediction. Previous work has used machine learning models such as neural networks and support vector machines combined with composition features for lattice constant prediction and has achieved a maximum performance for cubic structures with an average coefficient of determination ( R 2 ) of 0.82. Other models tailored for special materials family of a fixed form such as ABX 3 perovskites can achieve much higher performance due to the homogeneity of the structures. However, these models trained with small data sets are usually not applicable to generic lattice parameter prediction of materials with diverse compositions. Herein, we report MLatticeABC, a random forest machine learning model with a new descriptor set for lattice unit cell edge length ( a , b , c ) prediction which achieves an R 2 score of 0.973 for lattice parameter a of cubic crystals with an average R 2 score of 0.80 for a prediction of all crystal systems. The R 2 scores are between 0.498 and 0.757 over lattice b and c prediction performance of the model, which could be used by just inputting the molecular formula of the crystal material to get the lattice constants. Our results also show significant performance improvement for lattice angle predictions. Source code and trained models can be freely accessed at .

show abstract

Section: Methodsmentioning

confidence: 99%

Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning

Yang

Dong

et al. 2021

ACS Omega

Self Cite

View full text Add to dashboard Cite

show abstract

“…An exemplar of the CBFV method is the Magpie [1] descriptor. This domain-derived approach (CBFV) has been successfully employed in materials informatics studies for years [2][3][4][5][6][7]. Not only has it been successful, but the information it contains is also human-readable, allowing for physically interpretable results.…”

Section: Introductionmentioning

confidence: 99%

Is Domain Knowledge Necessary for Machine Learning Materials Properties?

Murdock

Kauwe

Wang

et al. 2020

Integr Mater Manuf Innov

View full text Add to dashboard Cite

New methods for describing materials as vectors in order to predict their properties using machine learning are common in the field of material informatics. However, little is known about the comparative efficacy of these methods. This work sets out to make clear which featurization methods should be used across various circumstances. Our findings include, surprisingly, that simple one-hot encoding of elements can be as effective as traditional and new descriptors when using large amounts of data. However, in the absence of large datasets or data that is not fully representative we show that domain knowledge offers advantages in predictive ability.

show abstract

“…The aim of this review has been to highlight the recent advancements in the construction of structural features that can be leveraged by machine learning algorithms to accurately predict the property of interest. Over years of development, a vast number of descriptors 100,119,154–167 have emerged for encoding the structures of various classes of materials, which makes it hardly possible to enumerate and discuss all of them. By summarizing the studies on structure graph, Coulomb matrix, topological descriptor, and diffraction fingerprint, we can come to a better understanding of how to effectively represent crystalline solids.…”

Section: Discussionmentioning

confidence: 99%

Encoding the atomic structure for machine learning in materials science

Liu

Dong

et al. 2021

WIREs Comput Mol Sci

View full text Add to dashboard Cite

In recent years, we have witnessed a widespread application of machine learning techniques in the field of materials science, owing to the increased availability of research data and sophisticated algorithms. At the core of this technology lies the ability to encode material structures into descriptors that are understandable for a computer. Although significant advances have been made in this area, there is a continued need to explore efficient structure‐encoding strategies so as to maximize the predictive power of the machine learning models. Here we present a revision of the exciting progress in four representative structural features that are capable of describing the structures of diverse materials: structure graph, Coulomb matrix, topological descriptor, and diffraction fingerprint. Particular attention is given to the studies of crystalline solids, which appear more challenging to be encoded than molecules. By summarizing previous works and presenting critical appraisals of these descriptors, this review could offer some guideline for the selection of structural features and stimulate inspiration for the design of powerful descriptors suited towards different tasks. This article is categorized under: Structure and Mechanism > Computational Materials Science Data Science > Artificial Intelligence/Machine Learning

show abstract

Convolutional Neural Networks for Crystal Material Property Prediction Using Hybrid Orbital-Field Matrix and Magpie Descriptors

Cited by 49 publications

References 28 publications

Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning

Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning

Is Domain Knowledge Necessary for Machine Learning Materials Properties?

Encoding the atomic structure for machine learning in materials science

Contact Info

Product

Resources

About