<![CDATA[The prediction of thermal stability (TS) in zinc-based metal–organic frameworks (Zn-MOFs) is often challenged by experimental cost and distributional heterogeneity in materials datasets. This study proposes a median-based robust voting ensemble to model the TS of 151 Zn-MOF samples using four structural descriptors, nN, nZn, Het, and Lig. The framework integrates five robust linear estimators and is benchmarked against a linear kernel Support Vector Regression (SVR) model to evaluate predictive stability and generalization performance. The proposed ensemble demonstrates superior test performance (R² = 0.9986; RMSE = 0.0023) compared to SVR (R² = 0.9492; RMSE = 0.0213), indicating enhanced robustness under heterogeneous data conditions. Feature importance analysis identifies nitrogen coordination density and heteroatomic environment as the dominant contributors to TS prediction, while zinc center quantity and ligand topology exhibit comparatively minor influence. These findings confirm that median-based robust aggregation improves predictive reliability and provides chemically interpretable insight, offering a data-driven approach for the rational design and screening of thermally stable Zn-MOF materials.]]>
Copyrights © 2026
