Machine Learning and Materials Design
A special issue of International Journal of Molecular Sciences (ISSN 1422-0067). This special issue belongs to the section "Materials Science".
Deadline for manuscript submissions: 30 November 2024
Special Issue Editors
Interests: molecular physics; computational chemistry; fullerenes; solids and liquids; design of molecular systems-materials (ha)
Special Issues, Collections and Topics in MDPI journals
Interests: machine learning; symbolic regression; computational hydraulics; molecular dynamics; smoothed-particle hydrodynamics; multiscale modeling
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Molecular materials constitute the basis of, and are the cornerstone for, the development of materials with a plethora of applications (e.g., drug design, optoelectronics, or energy storage). Molecular materials enrich our daily lives in countless ways. Their properties depend on their exact structure; the degree of order in the way in which the molecules are aligned; and their crystalline nature. Small changes in a molecular structure can totally alter the properties of the material in bulk and fine-tune its overall characteristics. Therefore, it is of paramount importance to place emphasis on the study of design rules for molecular functional materials. The field of molecular material research includes (i) the preparation, (II) the characterization, and (iii) the modelling of potentially useful materials with enhanced physical, chemical, and biomedical properties.
Data science is currently driving the fourth industrial revolution, with material applications playing a central role. The discovery of novel materials through material informatics has been accelerated due to the advent of big data. Current approaches, from the atomic scale to the macroscale, are proposed, aided by the incorporation of existing material databases, multi-scale modelling, and experimental result analysis, with the aim of working towards reducing the time and cost required in the design and manufacturing of materials.
Machine learning (ML), as a subfield of artificial intelligence, can be successfully applied to the establishment of computational models able to reveal linear/non-linear relationships and patterns directly from material data. These predictive models are often based on classical ML algorithms, symbolic regression, deep learning methods, physics-informed machine learning methods, and, currently, generative AI-based models, among others. Explainability and interpretability are the main priorities.
Suggested topics include, but are not limited to, the following:
- ML methods for the development of hybrid organic–inorganic materials (e.g., MOFS and COFS) for technological applications (e.g., energy storage, photonic switches, and efficient optical materials);
- Multiscale approaches (ML, ab-initio, MD) investigating the physics and chemistry of molecular materials (e.g., their optical properties, spectra, charge transfers, structural modelling, catalysis, and chemical reactions);
- Machine learning in material design;
- Deep learning;
- Physics-based methods;
- Explainable AI.
Dr. Aggelos Avramopoulos
Dr. Filippos Sofos
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at mdpi.longhoe.net 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 submissions that pass pre-check are 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. International Journal of Molecular Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. There is an Article Processing Charge (APC) for publication in this open access journal. For details about the APC please see here. 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
- Molecular materials
- Molecular structure
- Machine learning
- Hybrid organic–inorganic materials
