Predicting material properties by integrating high-throughput experiments, high-throughput ab-initio calculations, and machine learning

Mixed oxide growth on combinatorial aluminium–gadolinium alloys — a thermodynamic and first-principles approach

Metal surfaces covered with oxides have attracted considerable scientific attention in various applications. In particular, anodic films fabricated by cost-effective anodizing have been widely used in nano-structured engineering to provide various surface functionalities. However, understanding of alloy film stability, having individual elements with widely varying structures and morphologies, is very limited due to lack of thermodynamic information and effects of electrolyte chemistry. This requires many tedious efforts on a trial and error basis in selecting suitable electrolytes that can produce the protective film at high efficiency on alloys having mixed chemistries. It is, therefore, crucial to develop a combination of high throughput theoretical analysis and automated rapid localized electrochemical probing that provides a fast and simple solution for electrolyte choice and paves the way to the remarkable expansion of industrial applications of oxides. Herein, we demonstrate that combinatorial Al–Gd alloys covering 1.0 to 10.0 at.% Gd can be oxidized into ultra-thin anodic films of controlled thickness through a selection of electrolyte based on thermodynamics (phosphate buffer with a pH of 8.20). We propose that growth of anodic films on alloys at high efficiency is possible if Gibbs free energy minimization criteria would be systematically contemplate.

Graphical abstract

Stacking fault energy prediction for austenitic steels: thermodynamic modeling vs. machine learning

Stacking fault energy (SFE) is of the most critical microstructure attribute for controlling the deformation mechanism and optimizing mechanical properties of austenitic steels, while there are no accurate and straightforward computational tools for modeling it. In this work, we applied both thermodynamic modeling and machine learning to predict the stacking fault energy (SFE) for more than 300 austenitic steels. The comparison indicates a high need of improving low-temperature CALPHAD (CALculation of PHAse Diagrams) databases and interfacial energy prediction to enhance thermodynamic model reliability. The ensembled machine learning algorithms provide a more reliable prediction compared with thermodynamic and empirical models. Based on the statistical analysis of experimental results, only Ni and Fe have a moderate monotonic influence on SFE, while many other elements exhibit a complex effect that their influence on SFE may change with the alloy composition.