Advances in Machine Learning for Atomistic Simulations: Paving the Way for Next-Generation Material Design
A special issue of Crystals (ISSN 2073-4352).
Deadline for manuscript submissions: 25 October 2024 | Viewed by 107
Special Issue Editors
Interests: material science; nanostructures; thermal transport; molecular dynamics; density functional theory; density functional tight-binding; extreme conditions
Special Issue Information
Dear Colleagues,
This Special Issue focuses on recent breakthroughs in the incorporation of machine learning (ML) within atomistic simulations, driving advances in computational materials science. This Special Issue aims at showcasing the potential of ML techniques in enhancing the efficiency of atomistic simulations, offering a panorama of the field, and envisaging future trajectories.
Crucial among these is the advent of machine-learned interatomic potentials (MLIPs), which are revolutionizing the way we represent the forces between atoms of complex materials and their potential energy surfaces (PESs). By parameterizing PESs from high-level ab initio calculations, MLIPs can achieve ab initio-like accuracies but at a fraction of the computational cost, marking a notable milestone in predicting material properties.
The coupling of ML and high-throughput (HT) computational screening has expedited material discovery, with ML algorithms trained on HT data enabling the predictive modelling of novel compounds. Furthermore, a notable shift in material design methodology has been prompted by ML approaches towards ‘inverse design’, where desired properties guide the creation of materials. The integration of generative ML models with atomistic simulations has facilitated the discovery of new catalysts, photovoltaic materials, and high-entropy alloys.
Lastly, ML is aiding the interpretation of high-dimensional atomistic simulation data through dimensionality reduction techniques such as t-SNE, enabling the visualization of simulation outcomes in a human-interpretable format, and revealing patterns and structures that might be obscured in the original high-dimensional data.
We hope that this Special Issue will serve as an extensive survey for the scientific community, reporting the advancements in ML applications within atomistic simulations, and highlighting future directions in designing novel materials for real-world applications.
Dr. Riccardo Dettori
Dr. Antonio Rossi
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 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. 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 2600 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
- material science
- computer simulations
- quantum mechanical calculations
- molecular dynamics
- density functional theory
- atomic-scale modeling
- neural networks
- physical chemistry
