Chapter 4: Machine Learning in Emerging Nanofabrication Processes: From Imprinting and Tip-Based to Ion-Beam, Laser, and Capillary Approaches

Kapitola, resp. kapitoly v odborné knize

en

Machine learning is increasingly revolutionizing emerging nanofabrication processes by enabling predictive modeling, process optimization, and autonomous control at the nanoscale. This review systematically examines machine learning applications across five representative techniques — nanoimprinting, tip-based nanofabrication, focused ion beam nanofabrication, nanocapillary force lithography, and laser nanofabrication. Fifteen key studies employing 26 machine learning algorithms were analyzed and demonstrated significant improvements in accuracy, defect reduction, and process adaptability compared with conventional methods. The review identifies artificial neural network, support vector regression, and general regression neural network as top performers in precision and efficiency, while highlighting critical challenges such as limited datasets, interpretability, and scalability. Future research directions emphasize data-efficient hybrid models, explainable artificial intelligence, and real-time adaptive control. Overall, machine learning-assisted nanofabrication represents a paradigm shift toward intelligent, sustainable, and high-precision nanofabrication, bridging computational intelligence with experimental nanoscale engineering.

atomic force microscopy; ion beam; machine learning; nanocapillary force lithography; nanofabrication; nanoimprinting; scanning probe microscopy; tip-based nanofabrication

2026-06-14

World Scientific Publishing

978-981-98-3075-6

Nanofabrication in the Era of Machine Learning: Advances and Emerging Frontiers

149–208

60