A review of morphological studies on CuO nanostructures: comparative analysis of synthesis methods and predictions by machine learning

Copper oxide (CuO) nanostructures, including nanopowders, thin films and coatings, have been widely studied for their broad range of applications. This review provides a comprehensive analysis of synthesis methods and morphological studies on CuO nanostructures, focusing on how synthesis parameters affect particle size and shape. It emphasizes the impact of synthesis methods and parameters on their structural and functional characteristics. For nanopowders, morphologies such as cubic, dendrite-like, flower-like, nanoleaves, nanorod, nanosheet, spherical, spindle, and others can be achieved. For thin films and coatings, morphologies like flower-like microsphere, hexagonal, rod-like, polyhedral, pyramid-like, spherical, and trapezium are produced. The key synthesis parameters impacting both nanopowders and thin film and coatings types include temperature, reaction time, surfactant type, and pH, which influence particle size and morphology. For thin films and coatings specifically, deposition conditions, substrate type, and precursor choice are also critical. However, achieving reliable morphological control across different synthesis methods remains a major challenge. This study enhances the review by incorporating a machine learning model to predict the morphology of CuO nanopowders based on synthesis conditions. A Random Forest model achieved 92% accuracy and identified surfactant type, temperature, and reaction time as the most influential factors. By analyzing data from different studies, the review offers a data-driven framework to optimize synthesis processes. These insights bridge experimental knowledge with predictive modeling and provide practical guidance for tailoring CuO nanostructures to specific applications. This work is expected to serve as a useful reference for researchers aiming to design CuO-based materials with controlled morphological features.