<![CDATA[This study aims to develop a predictive model for the thermal stability of Zinc-based Metal-Organic Frameworks (Zn-MOFs), which are crucial in high-temperature applications. The approach used is stacking ensemble learning, which integrates several base models, including Ridge Regression, Lasso Regression, K-Nearest Neighbors (KNN) Regression, Support Vector Regression (SVR), Linear Regression, RANSAC (Random Sample Consensus), Huber Regression, and Gaussian Process Regression, with the meta-model TheilSenRegressor. Experimental results indicate that the stacking model delivers high-accuracy predictions, evidenced by a Root Mean Squared Error (RMSE) of 0.0025 and a coefficient of determination (R²) of 0.9993 on the training data, and an RMSE of 0.0023 and an R² of 0.9994 on the test data, demonstrating the model's excellent generalization capability. A comparison with the Robust Regression model shows that the stacking model is more stable and consistent in providing accurate predictions for both the training and test sets. These findings suggest that the machine learning-based stacking ensemble learning approach can serve as a more efficient and faster alternative to conventional experimental methods in predicting the thermal stability of Zn-MOFs.]]>
Copyrights © 2025
