This work focuses on advances in roll-to-roll microcontact printing by the establishment of learning-based modeling methods that guides the monitoring and control of the continuous microcontact printing process. Microcontact printing is an attractive cost-effective method of patterning micro- and nano-scale features via selective mechanical contact on flexible web substrates using stamps. Adapting microcontact printing to continuous, roll-to-roll platforms facilitates applications such as flexible electronics and wearables. However, a limitation of present continuous printing processes is that in-line metrology is unavailable for process monitoring and control. Therefore, this work aims to develop in-line metrology for print pattern quality monitoring of nano-thin monolayer print processes and use neural-network-based predictive control to control the printing processes. First, a real-time prediction of web tension based on contactless sensing and deep learning is developed. Second, a neural-network-based adaptive model predictive control for a flexure-based roll-to-roll contact printing system is designed. To further study the mechanisms of the microcontact printing process, an offline consistent optical surface inspection based on open environment droplet size-controlled condensation figures for print pattern quality monitoring is developed. Inline metrology for microcontact printing quality monitoring based on condensation figures is then applied. Finally, a case study of a novel autofocus method is presented to show the possibility of applying deep learning-based model predictive control in the control of the roll-to-roll microcontact printing process.