A Transferable, Explainable AI Framework for Composition–Structure–Property Mapping from Steel Micrographs
Authors:
- Gerfried MillnerGMGerfried Millner
- Tzu-Wei WangTWTzu-Wei Wang
- Shangkun ShenSSShangkun Shen
- Yingxi LiYLYingxi Li
- Yi-Sheng ChenYCYi-Sheng Chen
Preprint
- 11 September 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
We develop a transferable framework for microstructure- and chemistry-aware, explain- able prediction of tensile properties across metallic systems. Using peer-reviewed stain- less steel literature, we curate a dataset in which optical microscopy (OM) and scanning electron microscopy (SEM) images provide microstructural information that is comple- mented by compositional data to predict yield strength, ultimate tensile strength and elongation at fracture. Diverse image-based descriptors are used to extract information on microstructure and texture from micrographs, and model performance is evaluated both in-distribution via cross-validation and out-of-distribution via an independent ex- perimental dataset. Feature importance analyses identify the dominant compositional and microstructural factors controlling the investigated properties, and comparison with established metallurgical knowledge supports the physical plausibility of the learned relationships. Finally, we demonstrate the transferability of the proposed approach by applying instance-reweighted transfer learning from stainless steels to a dual-phase steel literature dataset, showing that the framework remains stable under domain shift and is suitable as a general template for composition–structure–property mapping from both OM and SEM micrographs.Keywords
This publication has 42 references indexed in Scilit:
- An Explainable Deep Learning Model Based on Multi-scale Microstructure Information for Establishing Composition–Microstructure–Property Relationship of Aluminum AlloysIntegrating Materials and Manufacturing Innovation, 2024
- Review of Microstructure–Mechanical Property Relationships in Cast and Wrought Ni‐Based Superalloys with Boron, Carbon, and Zirconium Microalloying AdditionsAdvanced Engineering Materials, 2022
- Experimental methods in chemical engineering: Scanning electron microscopy andX‐ray ultra‐microscopy—SEMandXuMThe Canadian Journal of Chemical Engineering, 2022
- Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statisticsActa Materialia, 2017
- Stacking fault energies in austenitic stainless steelsActa Materialia, 2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Microstructure reconstructions from 2-point statistics using phase-recovery algorithmsActa Materialia, 2008
- A Statistical Theory of Solid Solution HardeningPhysica Status Solidi (b), 1970
- Solution hardeningActa Metallurgica, 1961
- Das ElektronenmikroskopThe European Physical Journal A, 1932