Predicting residual stress of aluminum nitride thin-film by incorporating manifold learning and tree-based ensemble classifier

The optical emission spectroscopy (OES) data provide multi-featured and high-dimension data, which exhibit rich physical phenomena. The novel unsupervised learning uniform manifold approximation and projection (UMAP) and t-distributed stochastic neighborhood embedding (t-SNE) are implemented to deal with OES data and keeping data structure during the aluminum nitride (AlN) film deposition process on Si (100) substrate. After dimensionality reduction, we hand over data to a tree-based ensemble model for training, and the performance of the model through indicators such as recall, precision, and F1-score was also determined. The optimal testing results of this study of compressive and tensile stress classification prediction were presented by UMAP including true positive (TP) 34.32%, false positive (FP) 0.21%, false negative (FN) 0.71%, and true negative (TN) 64.76%. Critical indicators were also evaluated with excellent results such as recall 0.9797, precision 0.9939, and F1-score 0.9867. Therefore, we proved a residual stress prediction with machine learning studies would become workable in the thin film deposition process.