Generative models have been successfully
used to synthesize completely
novel images, text, music, and speech. As such, they present an exciting
opportunity for the design of new materials for functional applications.
So far, generative deep-learning methods applied to molecular and
drug discovery have yet to produce stable and novel 3-D crystal structures
across multiple material classes. To that end, we, herein, present
an autoencoder-based generative deep-representation learning pipeline
for geometrically optimized 3-D crystal structures that simultaneously
predicts the values of eight target properties. The system is highly
general, as demonstrated through creation of novel materials from
three separate material classes: binary alloys, ternary perovskites,
and Heusler compounds. Comparison of these generated structures to
those optimized via electronic-structure calculations shows that our
generated materials are valid and geometrically optimized.
Magnetic materials
play an important role in a wide variety of
everyday applications, and they are critical components in many devices
used for energy conversion. However, there are very few materials
known to exhibit magnetism of any kind, and the slow process of experimentally
driven magnetic-materials discovery has limited the development of
devices for functional applications. In this work, a complete magnetic-materials
discovery pipeline is presented that uses natural language processing
(NLP), machine learning, and generative models to predict ferromagnetic
compounds in the Heusler alloy family. Using the “chemistry-aware”
NLP toolkit, ChemDataExtractor, a database of 2910 magnetocaloric
compounds is autogenerated by sourcing from the scientific literature.
These data are then used to train property-prediction models for key
figures of merit that describe the magnetocaloric effect. The predictive
models are applied to novel Heusler alloy material candidates that
have been created using deep generative representation learning. Convex-hull
meta-stability analysis and ab initio validation
of these candidates identify six potential materials for solid-state
refrigeration applications.
The efficient transport
of electrons from the sunlight-harvesting
dye molecules into the electrical circuit of a dye-sensitized solar
cell (DSSC) is imperative to its effective operation. A dye···semiconductor
interface comprises the working electrode of a DSSC. Dye molecules
adsorb onto the semiconductor surface, whereupon they transfer electronic
charge into the conduction band of the semiconductor; this process
initiates the electrical circuit. It is therefore important to characterize
this interfacial structure in order to understand how efficiently
the dye binds, or anchors, onto the semiconductor surface and imparts
charge transfer to it. Armed with such knowledge, the performance
of DSSCs may then be improved systematically. The structural determination
of a thin-film interface is nonetheless a challenging task. We herein
report the results of a glancing-angle pair distribution function
(gaPDF) experiment that generated synchrotron X-ray diffraction patterns
of DSSC working electrodes sensitized by the archetypal ruthenium-based
DSSC dye complexes N3 and N749. This gaPDF
experimental approach represents the first diffraction-based strategy
for the characterization of intact DSSC working electrodes. The gaPDF
structural signatures were compared with PDFs simulated from possible
interfacial structures that were computed using density functional
theory. The differences between the experimental observation and these
simulated structures revealed a preference for each dye, N3 and N749, to adopt a bidentate-bridging dye anchoring
mode when sensitized onto TiO2. Our results also suggest
that this anchoring mode is sometimes supported by an auxiliary anchor,
in the form of a monodentate carboxylic acid. This work not only demonstrates
the successful application of a gaPDF method to DSSC research, but
it also advocates the applicability of a gaPDF to many types of thin-film
samples.
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.