Assessing machine learning predictions of austenitic steel compositions for optimum mechanical response
Source abstract
Abstract
Understanding and predicting mechanical properties such as proof stress (yield strength), ultimate tensile strength, elongation to failure, and reduction in area are essential for screening the application of austenitic stainless steels in adverse chemomechanical environments. However, experimental determination of these properties is time-consuming, labor-intensive, and costly—especially under extreme conditions, which requires advanced experimental capabilities. In this study, we leverage a large-scale, curated dataset comprising 2180 experimental entries of austenitic alloys to develop machine learning (ML) models capable of predicting these key mechanical properties as functions of composition, solution treatment condition, and testing temperature . We systematically evaluate a range of ML algorithms, namely linear regression, kernel ridge regression, extreme gradient boosting, and artificial neural network. Among these, the extreme gradient boosting achieves the highest predictive accuracy, with R 2 scores of 0.946 and 0.985 for proof stress and ultimate tensile strength, respectively. To further enhance model performance, we explore ensemble learning and transfer learning strategies. The transfer learning approach that leverages interdependencies between mechanical properties reduces the mean percentage error by 21.0% and increases R 2 score by 3.1% in predicting reduction in area, compared to the original artificial neural network model. Our results show that ML models trained on well-structured experimental data can serve as an efficient and reliable tool for exploring the effect of composition on screening metrics. This work highlights the potential of data-driven approaches to accelerate the design and optimization of high-performance austenitic alloys. Furthermore, obtaining feature importance and insights from extreme gradient boosting using Shapley Additive Explanation tool provides valuable understanding of how features contribute to the prediction of mechanical properties.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Microstructure and Mechanical Properties of Steels · Hydrogen embrittlement and corrosion behaviors in metals
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (32)
Show source-provided references
1. https://obamawhitehouse.archives.gov/mgi.
2. Machine learning for alloys10.1038/s41578-021-00340-w ↗
3. Machine learning in materials chemistry: An invitation
4. Fully automatized optimization of ring-opening reactions in lactone derivatives via two-step machine learning10.1021/acs.jpca.3c05887 ↗
5. Machine learning prediction of mechanical properties in metal additive manufacturing
6. Harnessing machine learning for predicting mechanical properties of lightweight Mg alloys10.1016/j.matlet.2024.137597 ↗
7. Materials Algorithms Project (MAP), Program Library, in: Austenitic Stainless Steel Dataset, University of Cambridge, Available at: https://www.phase-trans.msm.cam.ac.uk/map/data/materials/austenitic.data.html. (Accessed 1 2025).
8. Prediction and analysis of tensile properties of austenitic stainless steel using artificial neural network10.3390/met10020234 ↗
9. Spring research presentation: A theoretical foundation for inductive transfer
10. ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost10.1039/C6SC05720A ↗
11. Graph neural network modeling of grain-scale anisotropic elastic behavior using simulated and measured microscale data10.1038/s41524-022-00952-y ↗
12. Array programming with NumPy10.1038/s41586-020-2649-2 ↗
13. Matplotlib: A 2D graphics environment10.1109/MCSE.2007.55 ↗
14. Wes McKinney, Data structures for statistical computing in Python, in: Proc. of the 9th Python in Science Conf. (Scipy 2010), vol. 445, 2010, pp. 51–56.10.25080/Majora-92bf1922-00a ↗
15. Scikit-learn: Machine learning in Python
16. Tianqi Chen, Carlos Guestrin, XGBoost: A Scalable Tree Boosting System, in: Proc. of the 22nd ACM SIGKDD International Conf. on Knowledge Discovery and Data Mining, San Francisco, California, USA, 2016, pp. 785–794, http://dx.doi.org/10.1145/2939672.2939785.10.1145/2939672.2939785 ↗
17. Chollet · 2015
18. https://shap.readthedocs.io/en/latest/.
19. Scott M. Lundberg, Su-In Lee, A unified approach to interpreting model predictions, in: Proc. of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 4768–4777.
20. Empirical validation of size effects in sub-sized tensile specimens for nuclear structural materials10.1038/s41598-025-98849-5 ↗
21. Effects of specimen thickness and grain size on the mechanical properties of types 304 and 316 austenitic stainless steel
22. Deep learning-driven prediction of mechanical properties of 316l stainless steel metallographic by laser powder bed fusion10.3390/mi15091167 ↗
23. Optimal design of the austenitic stainless-steel composition based on machine learning and genetic algorithm10.3390/ma16165633 ↗
24. Frehser · 1963 · 370
25. Gavriljuk · 1999
26. Investigation of nitrogen containing austenitic stainless steel10.4028/www.scientific.net/MSF.989.152 ↗
27. Effects of nitrogen on the microstructure and mechanical properties of an austenitic stainless steel with incomplete recrystallization annealing10.1016/j.mtcomm.2023.105799 ↗
28. On the strengthening mechanisms of high nitrogen austenitic stainless steels10.1016/j.matlet.2022.133502 ↗
29. Effect of nitrogen content on mechanical properties of 316L(N) austenitic stainless steel10.1016/j.msea.2023.145549 ↗
30. Effects of boric acid and lithium hydroxide on the corrosion behaviors of 316ln stainless steel in simulating hot functional test high-temperature pressurized water10.1016/j.corsci.2022.110157 ↗
31. Sofronis · 2025
32. Yurek · 2025