Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.
There currently exist no quantitative methods to determine
the
appropriate conditions for solid-state synthesis. This not only hinders
the experimental realization of novel materials but also complicates
the interpretation and understanding of solid-state reaction mechanisms.
Here, we demonstrate a machine-learning approach that predicts synthesis
conditions using large solid-state synthesis data sets text-mined
from scientific journal articles. Using feature importance ranking
analysis, we discovered that optimal heating temperatures have strong
correlations with the stability of precursor materials quantified
using melting points and formation energies (Δ
G
f
, Δ
H
f
). In contrast, features derived from the thermodynamics
of synthesis-related reactions did not directly correlate to the chosen
heating temperatures. This correlation between optimal solid-state
heating temperature and precursor stability extends Tamman’s
rule from intermetallics to oxide systems, suggesting the importance
of reaction kinetics in determining synthesis conditions. Heating
times are shown to be strongly correlated with the chosen experimental
procedures and instrument setups, which may be indicative of human
bias in the data set. Using these predictive features, we constructed
machine-learning models with good performance and general applicability
to predict the conditions required to synthesize diverse chemical
systems.
Digitally retouching images has become a popular trend, with people posting altered images on social media and even magazines posting flawless facial images of celebrities. Further, with advancements in Generative Adversarial Networks (GANs), now changing attributes and retouching have become very easy. Such synthetic alterations have adverse effect on face recognition algorithms. While researchers have proposed to detect image tampering, detecting GANs generated images has still not been explored. This paper proposes a supervised deep learning algorithm using Convolutional Neural Networks (CNNs) to detect synthetically altered images. The algorithm yields an accuracy of 99.65% on detecting retouching on the ND-IIITD dataset. It outperforms the previous state of the art which reported an accuracy of 87% on the database. For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99.83%.
After
nearly seven decades of development, dental composite restorations
continue to show limited clinical service. The triggering point for
restoration failure is the degradation of the bond at the tooth–biomaterial
interface from chemical, biological, and mechanical sources. Oral
biofilms form at the bonded interfaces, producing enzymes and acids
that demineralize hard tissues and damage the composite. Removing
bacteria from bonded interfaces and remineralizing marginal gaps will
increase restorations’ clinical service. To address this need,
we propose for the first time the use of piezoelectric nanoparticles
of barium titanate (BaTiO3) as a multifunctional bioactive
filler in dental resin composites, offering combined antibacterial
and (re)mineralization effects. In this work, we developed and characterized
the properties of dental piezoelectric resin composites, including
the degree of conversion and mechanical and physical properties, for
restorative applications. Moreover, we evaluated the antibacterial
and mineralization responses of piezoelectric composites in
vitro. We observed a significant reduction in biofilm growth
(up to 90%) and the formation of thick and dense layers of calcium
phosphate minerals in piezoelectric composites compared to control
groups. The antibacterial mechanism was also revealed. Additionally,
we developed a unique approach evaluating the bond strength of dentin–adhesive–composite
interfaces subjected to simultaneous attacks from bacteria and cyclic
mechanical loading operating in synergy. Our innovative bioactive
multifunctional composite provides an ideal technology for restorative
applications using a single filler with combined long-lasting nonrechargeable
antibacterial/remineralization effects.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.