Special Issue "Machine-Learning and Deep Learning Applications in Crystalline Materials Science and Computational Mechanics"

A special issue of Crystals (ISSN 2073-4352). This special issue belongs to the section "Crystal Engineering".

Deadline for manuscript submissions: 20 October 2021.

Special Issue Editors

Dr. Jaka Fajar Fatriansyah
E-Mail Website
Guest Editor
Department of Metallurgical and Materials Engineering, Universitas Indonesia, Depok 16424, Indonesia
Interests: soft materials; molecular dynamics; machine learning in materials science
Prof. Dr. Amir H. Mosavi
E-Mail Website1 Website2 Website3
Guest Editor
1. Faculty of Civil Engineering, Technische Universität Dresden, 01069 Dresden, Germany
2. Institute of Structural Mechanics, Bauhaus Universität-Weimar, 99423 Weimar, Germany
Interests: machine learning; deep learning; data science; big data; sustainable concrete; materials informatics
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Machine-learning (ML) has recently attracted much attention from materials researchers. ML has become an integral part of how materials scientists and engineers conduct research, ranging from material discovery to the optimization of materials processing. Generally, ML is a paradigm in data science, which is building the analytical model by statistical data analyses. ML capable of learning from a set of data (databases) to identify, classify, cluster, diagnose, and prescribe with almost no or minimal human intervention.

The availability of materials information on databases ranging from the structure, characteristics, and potential applications is not a problem currently. Furthermore, the extraction of materials data from scientific journals can be a future possibility for materials design and selection. This opportunity is a just-right recipe for the successful future for ML in applications in materials science and engineering. In the old days, experiments were the primary key to discovering new materials and optimizing the characteristics of materials. Not until the 1960s was this position was challenged by computational methods ranging from Density Functional Theory (DFT), Monte Carlo (MC) simulation, Molecular Dynamics (MD), and many others. However, the computational power still has a limitation in predicting the new behaviour of materials.

In the computational approach, the paradigm of the complete understanding mechanism of a phenomenon through an analytical model, instead of advantage, is actually a barrier in discovering new materials. In the ML paradigm, instead of searching for a complete understanding of what is happening in the system, the interpolation of a new phenomenon from large data sets is the primary key. ML treats a complex model as a mere black box, which speeds the discovery of the latest materials and the optimization of existing materials.

Dr. Jaka Fajar Fatriansyah
Prof. Dr. Amir H. Mosavi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Crystals is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Machine-learning
  • Materials discovery
  • Materials science
  • Optimization
  • Design and selection of materials
  • Artificial intelligence
  • Deep learning
  • Data science
  • Big data

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Crystal Structure Prediction of the Novel Cr2SiN4 Compound via Global Optimization, Data Mining, and the PCAE Method
Crystals 2021, 11(8), 891; https://doi.org/10.3390/cryst11080891 - 30 Jul 2021
Viewed by 367
Abstract
A number of studies have indicated that the implementation of Si in CrN can significantly improve its performance as a protective coating. As has been shown, the Cr-Si-N coating is comprised of two phases, where nanocrystalline CrN is embedded in a Si3 [...] Read more.
A number of studies have indicated that the implementation of Si in CrN can significantly improve its performance as a protective coating. As has been shown, the Cr-Si-N coating is comprised of two phases, where nanocrystalline CrN is embedded in a Si3N4 amorphous matrix. However, these earlier experimental studies reported only Cr-Si-N in thin films. Here, we present the first investigation of possible bulk Cr-Si-N phases of composition Cr2SiN4. To identify the possible modifications, we performed global explorations of the energy landscape combined with data mining and the Primitive Cell approach for Atom Exchange (PCAE) method. After ab initio structural refinement, several promising low energy structure candidates were confirmed on both the GGA-PBE and the LDA-PZ levels of calculation. Global optimization yielded six energetically favorable structures and five modifications possible to be observed in extreme conditions. Data mining based searches produced nine candidates selected as the most relevant ones, with one of them representing the global minimum in the Cr2SiN4. Additionally, employing the Primitive Cell approach for Atom Exchange (PCAE) method, we found three more promising candidates in this system, two of which are monoclinic structures, which is in good agreement with results from the closely related Si3N4 system, where some novel monoclinic phases have been predicted in the past. Full article
Show Figures

Figure 1

Back to TopTop