Porosity characterization in metallic alloys is a fundamental aspect of materials engineering due to its influence on mechanical and structural properties. This study presents a method based on digital image processing for detecting and analyzing porosity in the AlSi10Mg aluminum alloy, additively manufactured using laser powder bed fusion (L-PBF). X-ray computed tomography, segmentation algorithms and filtering techniques were employed to identify and quantify the porosity present in the material’s microstructure. The research demonstrates that combining numerical methods with qualitative analysis provides a comprehensive understanding of porosity characteristics. Notably, the effectiveness of the proposed image processing methods was validated by comparing the results with actual material density measurements. However, challenges such as the need for proper calibration and potential imaging artifacts affecting accuracy were identified. This study represents a significant advancement in materials engineering, offering a detailed methodology for porosity analysis in aluminum alloys that not only enhances quality control and process optimization, but also improves segmentation accuracy and facilitates the reliable detection of small and interconnected pores in complex additively manufactured geometries.

Magnetic shape memory alloys based on the Ni–Mn–Ga system are of strategic interest for aerospace and robotics applications due to their ability to respond to both thermal and magnetic stimuli. However, the NASA Shape Memory Materials Database a key resource for the community exhibits significant gaps in functional parameters, with up to 93.7% of records missing critical properties such as the Curie temperature, and over 88% lacking complete magnetic data. To address this limitation, this study proposes a data imputation strategy based on a stacking ensemble comprising twelve machine learning models (LGBM, XGBoost, CatBoost, GradientBoosting, RandomForest, MLP, BayesianRidge, KNN, SVR, GPR, MICE, and AutoEncoder), optimized via Optuna and evaluated using ten random seeds with 10 repetitions each. The approach was applied to reconstruct missing entries in NASA’s database. For heat treatment 1, the method achieved coefficients of determination ($R^2$) of 0.95 for duration (h) and 0.88 for temperature (°C), respectively. For the phase transformation temperatures (Mf, Ms, As, and Af), the method yielded $R^2$ values of 0.83, 0.82, 0.79, and 0.80, respectively. Magnetic properties saturation magnetization and maximum magnetic field were imputed with an $R^2$ of 0.92. In contrast, the Curie temperature exhibited limited predictive performance ($R^2$ = 0.15–0.35), primarily due to insufficient data availability. Overall, the proposed methodology integrates machine learning based imputation with physically supported constraints, providing a viable alternative to enhance the completeness and utility of materials databases.