Machine Learning and Materials Informatics

Dear Colleagues,

Propelled by multiple big data repositories and algorithmic development, machine-learning- and deep-learning-focused methods are becoming almost indispensable for predicting novel materials and their properties, which are otherwise difficult to measure experimentally or problematic to compute accurately. These methods often rely on the use of already existing datasets to train a machine (computer) and map it to new materials or the material property of interest. Some of the earlier prediction endeavors include machine learning models for the thermodynamic, mechanical, and thermal properties of materials, such as the estimation of formation enthalpies, free energies, defect energetics, melting temperatures, mechanical properties, thermal conductivity, catalytic activity, and radiation damage resistance. Multiple global efforts are also underway to identify the states of the functional art materials, such as novel shape memory alloys, improved piezoelectrics, and novel perovskites and halide perovskites relevant to electronics and energy applications. The evolution of high-performance computing has also increased the efficiency of image-based characterization techniques, as well as complex statistical calculations. Today, high dimensional raw data can be extracted from experimental micrographs to study existing numerous nanoparticle and thin film surface properties. Data generated from sophisticated atomic-scale resolution instruments, such as atomic force, scanning, and transmission electron microscope images, are being used to train, test, and predict the shape and important characteristic features of nanomaterials. These whole new image data lead us to various powerful characterization algorithm techniques, which tremendously save experimental time and cost, thus eventually contributing to the development of materials processing research.

We are looking forward to putting together a comprehensive set of research publications aiming to highlight the latest findings in material science using machine learning and deep learning algorithms. We welcome original research articles involving material discovery, structure–property prediction, material characterization, and software development for the broader scientific community. We are seeking contributions involving the development, characterization, and simulation studies of nanomaterials, biomaterials, and electronic materials. We expect to bring awareness to the physical science and informatics communities, especially focusing on what challenges lie in the acquisition, processing, storage, and analyses of the material data sets. Novel methods for data cleaning, feature extraction, and analysis will also be considered and highlighted in this Special Issue.

Prof. Dr. Yuqing Lin
Dr. Shruba Gangopadhyay
Dr. Aniruddha Dutta
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. Data 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 1600 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.

• Material informatics
• Machine learning
• Material characterization
• Image processing
• Microscopy
• Deep learning
• Neural network
• Pattern recognition
• Material discovery
• Nanomaterials
• Electronic materials
• Biomaterials