Predicting properties from a material’s composition or structure is of great interest for materials design. Deep learning has recently garnered considerable interest in materials predictive tasks with low model errors when dealing with large materials data. However, deep learning models suffer in the small data regime that is common in materials science. Here we develop the AtomSets framework, which utilizes universal compositional and structural descriptors extracted from pre-trained graph network deep learning models with standard multi-layer perceptrons to achieve consistently high model accuracy for both small compositional data (<400) and large structural data (>130,000). The AtomSets models show lower errors than the graph network models at small data limits and other non-deep-learning models at large data limits. They also transfer better in a simulated materials discovery process where the targeted materials have property values out of the training data limits. The models require minimal domain knowledge inputs and are free from feature engineering. The presented AtomSets model framework can potentially accelerate machine learning-assisted materials design and discovery with less data restriction.
- Award ID(s):
- 1651668
- PAR ID:
- 10248527
- Date Published:
- Journal Name:
- Annual Review of Materials Research
- Volume:
- 50
- Issue:
- 1
- ISSN:
- 1531-7331
- Page Range / eLocation ID:
- 27 to 48
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
null (Ed.)Structural materials have lagged behind other classes in the use of combinatorial and high-throughput (CHT) methods for rapid screening and alloy development. The dual complexities of composition and microstructure are responsible for this, along with the need to produce bulk-like, defect-free materials libraries. This review evaluates recent progress in CHT evaluations for structural materials. High-throughput computations can augment or replace experiments and accelerate data analysis. New synthesis methods, including additive manufacturing, can rapidly produce composition gradients or arrays of discrete alloys-on-demand in bulk form, and new experimental methods have been validated for nearly all essential structural materials properties. The remaining gaps are CHT measurement of bulk tensile strength, ductility, and melting temperature and production of microstructural libraries. A search strategy designed for structural materials gains efficiency by performing two layers of evaluations before addressing microstructure, and this review closes with a future vision of the autonomous, closed-loop CHT exploration of structural materials. Expected final online publication date for the Annual Review of Materials Science, Volume 51 is August 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.more » « less
-
With the development of high-speed computers, networks, and huge storage, researchers can utilize a large volume and wide variety of materials data generated by experimental facilities and computations. The emergence of these big data and advanced analytical techniques has opened unprecedented opportunities for materials research. The discovery of many kinds of materials, such as energy-harvesting materials, structural materials, catalysts, optoelectronic materials, and magnetic materials, have been greatly accelerated through high-throughput screening. The utility of data-centric science for materials research is likely to grow significantly in the future. Unraveling the complexities inherent in big data could lead to novel design rules as well as new materials and functionalities.more » « less
-
more » « less
Abstract Detailed studies of interfacial gas-phase chemical reactions are important for understanding factors that control materials synthesis and environmental conditions that govern materials performance and degradation. Out of the many materials characterization methods that are available for interpreting gas–solid reaction processes,
in situ andoperando transmission electron microscopy (TEM) is perhaps the most versatile, multimodal materials characterization technique. It has successfully been utilized to study interfacial gas–solid interactions under a wide range of environmental conditions, such as gas composition, humidity, pressure, and temperature. This stems from decades of R&D that permit controlled gas delivery and the ability to maintain a gaseous environment directly within the TEM column itself or through specialized side-entry gas-cell holders. Combined with capabilities for real-time, high spatial resolution imaging, electron diffraction and spectroscopy, dynamic structural and chemical changes can be investigated to determine fundamental reaction mechanisms and kinetics that occur at site-specific interfaces. This issue ofMRS Bulletin covers research in this field ranging from technique development to the utilization of gas-phase microscopy methods that have been used to develop an improved understanding of multilength-scaled processes incurred during materials synthesis, catalytic reactions, and environmental exposure effects on materials properties.Graphical abstract -
more » « less
Abstract Direct ink writing is a facile method that enables biological, structural, and functional materials to be printed in three dimensions (3D). To date, this extrusion‐based method has primarily been used to soft materials in a layer‐wise manner on planar substrates. However, many emerging applications would benefit from the ability to conformally print materials of varying composition on substrates with arbitrary topography. Here, a high throughput platform based on multimaterial multinozzle adaptive 3D printing (MMA‐3DP) that provides independent control of nozzle height and seamless switching between inks is reported. To demonstrate the MMA‐3DP platform, conformally pattern viscoelastic inks composed of triblock copolymer, gelatin, and photopolymerizable polyacrylate materials onto complex substrates of varying topography, including those with surface defects that mimic skin abrasions or deep gouges. This platform opens new avenues for rapidly patterning soft materials for structural, functional, and biomedical applications.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1146/annurev-matsci-110519-094700
