Exploiting redundancy in large materials datasets for efficient machine learning with less data.

Extensive efforts to gather materials data have largely overlooked potential data redundancy. In this study, we present evidence of a significant degree of redundancy across multiple large datasets for various material properties, by revealing that up to 95% of data can be safely removed from machine learning training with little impact on in-distribution prediction performance. The redundant data is related to over-represented material types and does not mitigate the severe performance degradation on out-of-distribution samples.

High-Throughput Electrochemistry to Study Materials Degradation in Extreme Environments.

Electrochemistry has been used for decades to study materials' degradation in situ in corrosive environments, whether it is in room-temperature chemically aggressive solutions containing halide ions or in high-temperature oxidizing media such as pressurized water, liquid metals, or molten salts. Thus, following the recent surge in high-throughput techniques in materials science, it seems quite natural that high-throughput electrochemistry is being considered to study materials' degradation in extreme environments, with the objective to reduce corrosion resistant alloy development time by orders of magnitude and identify complex degradation mechanisms. However, while there has been considerable interest in the development of high-throughput methods for accelerating the discovery of corrosion resistant materials in different environments, these extreme environments propose formidable and exciting challenges for high-throughput electrochemical instrumentation, characterization, and data analysis.

Integrated High-Throughput and Machine Learning Methods to Accelerate Discovery of Molten Salt Corrosion-Resistant Alloys.

Insufficient availability of molten salt corrosion-resistant alloys severely limits the fruition of a variety of promising molten salt technologies that could otherwise have significant societal impacts. To accelerate alloy development for molten salt applications and develop fundamental understanding of corrosion in these environments, here an integrated approach is presented using a set of high-throughput (HTP) alloy synthesis, corrosion testing, and modeling coupled with automated characterization and machine learning. By using this approach, a broad range of CrFeMnNi alloys are evaluated for their corrosion resistances in molten salt simultaneously demonstrating that corrosion-resistant alloy development can be accelerated by 2 to 3 orders of magnitude.

Aggressively optimizing validation statistics can degrade interpretability of data-driven materials models.

One of the key factors in enabling trust in artificial intelligence within the materials science community is the interpretability (or explainability) of the underlying models used. By understanding what features were used to generate predictions, scientists are then able to critically evaluate the credibility of the predictions and gain new insights. Here, we demonstrate that ignoring hyperparameters viewed as less impactful to the overall model performance can deprecate model explainability.