<p>Thermal Barrier Coating (TBC) play a vital role in improving the performance of high-temperature components in power-generating systems, such as turbine engines on ships and aircraft. Thermal conductivity is an essential property in determining the quality of TBC materials. Therefore, an accurate prediction of the TBC thermal conductivity is required for optimizing their performance and design. Traditional methods for determining the TBC thermal conductivity are costly and time-consuming. Yttria-stabilized zirconia (YSZ) is one of the most popular TBC materials, and their properties are affected by porosity percentage and yttria content. This work aims to develop different machine learning (ML) models that predict the thermal conductivity of YSZ TBC. For that purpose, six ML models were applied and examined, including Support Vector Regression (SVR), K Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosting Tree (GBT), and Linear Regression (LR). These models were assessed using mean square error (MSE), mean absolute error (MAE), and training and testing accuracy scores. The results show that the testing accuracy scores of the SVR, KNN, DT, RF, GBT, and LR models were 97.4%, 93.3%, 97.4%, 97.8%, 97.4%, and 46.5%, respectively. The results indicated that all developed models can predict the thermal conductivity of YSZ TBC accurately, except the LR model.</p>