AI assists in design of corrosion-resistant alloys

Abstract

Alloy design can potentially benefit from artificial intelligence (AI). Within the broader context of advanced materials design, researchers have explored the creation of various alloys, including ferrous, high-entropy materials, and nonferrous metallic compositions, employing data-driven methodologies. However, a significant hurdle in these endeavors has been the scarcity of extensive, machine-readable databases suitable for training AI models. To address this challenge, researchers have turned to text mining and autonomous data extraction from literature sources. However, a major challenge with this approach is that the essential materials properties and features are not necessarily known, and must be obtained from textual sources to enhance the predictive accuracy of these models.