MaterialsAtlas.org: a materials informatics web app platform for materials discovery and survey of state-of-the-art

Hu, Jianjun; Stanislav, Stefanov,; Song, Yuqi; Omee, Sadman Sadeed; Louis, Steph-Yves M.; Siriwardane, Edirisuriya M. Dilanga; Zhao, Yong

doi:10.1038/s41524-022-00750-6

Cited by 37 publications

(29 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe such fast CSP web apps are critical to the materials science community, as demonstrated by the bioinformatics field, which has more than 9000 web servers. 39 Here we propose a TCSP algorithm and its companion web server for fast and quick CSP. Because of the widely observed structure similarity across many materials families such as perovskites in the materials database, TCSP achieves a strong prediction performance, as benchmarked on the whole Materials Project structure using leave-one-out evaluation due to its flexible template selection algorithm using prototype and oxidation information.…”

Section: Discussionmentioning

confidence: 99%

“…However, large-scale fast prediction of crystal structures is challenging, and user-friendly web apps are missing for such an important function despite the availability of some public software that needs expensive high-performance computing resources and an expertise of computational materials. We believe such fast CSP web apps are critical to the materials science community, as demonstrated by the bioinformatics field, which has more than 9000 web servers . Here we propose a TCSP algorithm and its companion web server for fast and quick CSP.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery

Wei

Siriwardane

et al. 2022

Inorg. Chem.

Self Cite

View full text Add to dashboard Cite

Fast and accurate crystal structure prediction (CSP) algorithms and web servers are highly desirable for the exploration and discovery of new materials out of the infinite chemical design space. However, currently, the computationally expensive first-principles calculation-based CSP algorithms are applicable to relatively small systems and are out of reach of most materials researchers. Several teams have used an element substitution approach for generating or predicting new structures, but usually in an ad hoc way. Here we develop a template-based crystal structure prediction (TCSP) algorithm and its companion web server, which makes this tool accessible to all materials researchers. Our algorithm uses elemental/chemical similarity and oxidation states to guide the selection of template structures and then rank them based on the substitution compatibility and can return multiple predictions with ranking scores in a few minutes. A benchmark study on the 98290 formulas of the Materials Project database using leave-one-out evaluation shows that our algorithm can achieve high accuracy (for 13145 target structures, TCSP predicted their structures with root-mean-square deviation < 0.1) for a large portion of the formulas. We have also used TCSP to discover new materials of the Ga–B–N system, showing its potential for high-throughput materials discovery. Our user-friendly web app TCSP can be accessed freely at on our MaterialsAtlas.org web app platform.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery

Wei

Siriwardane

et al. 2022

Inorg. Chem.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Uncertainty quantification is desired in our MVOF-ML framework since it is used to guide the fusion of the opinions. Therefore, we trained our CNN using the principle of evidential deep learning 33,34 . The uncertainty is explicitly…”

Section: A Mvof-ml Framework For Automated Crystal System Identificat...mentioning

confidence: 99%

Automated crystal system identification from electron diffraction patterns using multiview opinion fusion machine learning

Chen¹,

Zhang²,

Wahl³

et al. 2023

Preprint

View full text Add to dashboard Cite

A bottleneck in high-throughput nanomaterials discovery is the pace at which new materials can be structurally characterized. Although current machine learning (ML) methods show promise for the automated processing of electron diffraction patterns (DPs), they fail in high-throughput experiments where DPs are collected from crystals with random orientations. Inspired by the human decision-making process, a framework for automated crystal system classification from DPs with arbitrary orientations was developed. A convolutional neural network was trained using evidential deep learning, and the predictive uncertainties were quantified and leveraged to fuse multiview predictions. Using vector map representations of DPs, the framework achieves an unprecedented testing accuracy of 0.94 in the examples considered, is robust to noise, and retains remarkable accuracy using experimental data. This work highlights the ability of ML be used to accelerate experimental high-throughput materials data analytics.

show abstract

“…In material sciences, one of the earliest implementations was to predict crystal structures for binary ionic compounds − in the 1920s. Currently, ML is utilized in almost all materials-related fields in what is known as material informatics. − However, as very common in computer-aided applications like those in computational sciences and machine learning , it is evident that many calculations are conducted using “black box” implementations. Besides losing interpretability, such implementations can easily lead to computational artifacts and wrong conclusions. − This motivated many to call for “physics-guided” or “physics-informed” ML implementations in physical sciences where each feature should be physically meaningful .…”

Section: Introductionmentioning

confidence: 99%

Accelerating Materials Discovery through Machine Learning: Predicting Crystallographic Symmetry Groups

Alghofaili,

Alghadeer,

Alsaui

et al. 2023

J. Phys. Chem. C

View full text Add to dashboard Cite

Predicting crystal structure from the chemical composition is one of the most challenging and long-standing problems in condensed matter physics. This problem resides at the interface between materials sciences and physics. With reliable data and proper physics-guided modeling, machine learning (ML) can provide an alternative venue to undertake and reduce the problem's complexity. In this work, very robust ML classifiers for crystallographic symmetry groups were developed and applied for ternary (A l B m C n ) and binary (A l B m ) materials starting only from the chemical formula. This is the first essential step toward predicting full geometry. Such a problem is highly multi-label and multi-class from an ML perspective and requires careful preprocessing due to the size imbalance of the data. The resulting predictive models are highly accurate for all symmetry groups, including crystal systems, point groups, Bravais lattices, and space groups, with weighted balanced accuracies exceeding 95%. The models were developed with only a small set of ionic and compositional features, namely, stoichiometry, ionic radii, ionization energies, and oxidation states for each element in the ternary and binary compounds. Considering such minimal feature space, the obtained high accuracies ascertain that the physics is well captured. This is even further confirmed as we demonstrate that the accuracy of our approach is limited only by the size of data by comparing the size of ternary and binary materials with the accuracy of developed models. The presented work could effectively contribute to accelerating new materials discovery and development.

show abstract

MaterialsAtlas.org: a materials informatics web app platform for materials discovery and survey of state-of-the-art

Cited by 37 publications

References 93 publications

TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery

TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery

Automated crystal system identification from electron diffraction patterns using multiview opinion fusion machine learning

Accelerating Materials Discovery through Machine Learning: Predicting Crystallographic Symmetry Groups

Contact Info

Product

Resources

About