Materials discovery is often compared to the challenge of finding a needle in a haystack. While much work has focused on accurately predicting the properties of candidate materials with machine learning (ML), which amounts to evaluating whether a given candidate is a piece of straw or a needle, less attention has been paid to a […]
In many materials development projects, scientists and research heads make decisions to guide the project direction. For example, scientists may decide which processing steps to use, what elements to include in their material selection, or from what suppliers to source their materials. Research heads may decide whether to invest development effort in reducing the environmental […]
Discovering novel materials can be greatly accelerated by iterative machine learning-informed proposal of candidates—active learning. However, standard global error metrics for model quality are not predictive of discovery performance, and can be misleading. We introduce the notion of Pareto shell error to help judge the suitability of a model for proposing material candidates. Further, through […]
The drive for greater efficiency in turbomachinery has led to increasingly stringent specifications for the materials used. Current methods for optimizing alloy composition and processing to meet these requirements typically rely on a combination of expert judgment and trial and error. Machine learning offers an alternative approach that leverages data resources to significantly accelerate the […]
In general, data-driven approaches aim to identify objectively (relying largely on the available data) the embedded correlations among selected inputs and outputs needed to study or model a given phenomenon. Data-driven approaches are particularly advantageous when a full, physics-based understanding of relevant phenomena is lacking, and also when gathering new experimental data is particularly slow […]
Advances in renewable and sustainable energy technologies critically depend on our ability to design and realize materials with optimal properties. Materials discovery and design efforts ideally involve close coupling between materials prediction, synthesis and characterization. Increased use of computational tools, the generation of materials databases, and advances in experimental methods have substantially accelerated these activities. […]
Ongoing, rapid innovations in fields ranging from microelectronics, aerospace, and automotive to defense, energy, and health demand new advanced materials at even greater rates and lower costs. Traditional materials R&D methods offer few paths to achieve both outcomes simultaneously. Materials informatics, while a nascent field, offers such a promise through screening, growing databases of materials […]
Traditional machine learning (ML) metrics overestimate model performance for materials discovery. We introduce (1) leave-one-cluster-out cross-validation (LOCO CV) and (2) a simple nearest-neighbor benchmark to show that model performance in discovery applications strongly depends on the problem, data sampling, and extrapolation. Our results suggest that ML-guided iterative experimentation may outperform standard high-throughput screening for discovering […]
Data-driven materials research requires two key supporting components: data infrastructure and informatics. In this chapter, we review the state of the art in materials data infrastructure, focusing in detail on four infrastructure projects spanning academia, government, and industry. We also discuss data standards as an enabling step on the path to community-scale materials data infrastructure. […]
In this paper, we describe and compare three techniques for transfer learning: multi-task, difference, and explicit latent variable architectures.
