Sol-gel grown Zinc Oxide thin film Investigation: Wavelet analysis and Neural Network optimized X-ray reflectivity

Artificial neural networks and the Wavelet analysis are combined to calculate the thickness and roughness of Zinc Oxide thin film from X-ray reflectivity data. XRD measurements showed nanostructured ZnO thin films with well-defined orientations. This methodology combines the Wavelet analysis with the high computational efficiency of Neural Networks to solve complex characterization problems in real time. There are numerous basic methods to the design of thin film multi-layer coatings. Many traditional optimization techniques, including Simplex, Gradient, and Damped lest-squares method, have been used in this field. Neural network is a set of simple, highly interconnected processing elements imitating the action of the brain, which are capable of learning information presented to them. Modeling the X-ray reflectivity of a film with a Parrat model and its optimization allows to determining of both thickness and roughness of thin films. The results show that the physical or material properties can be predicted by the models using the large dimension of the data.