Smart Systems for Material and Process Designing in Direct Nanoimprint Lithography Using Hybrid Deep Learning

A hybrid smart process and material design system for nanoimprinting is proposed, which is combined with a learning system based on experimental and numerical simulation results. Instead of carrying out extensive learning experiments for various conditions, the simulation learning results are partially complimented when the results can theoretically be predicted by numerical simulation. In other words, the data that are lacking in experimental learning are complimented by simulation-based learning results. Therefore, the prediction of nanoimprint results without experimental learning could be realized under various conditions, even for unknown materials. In this study, material and process designs are demonstrated for a low-temperature nanoimprint process using glycerol-containing polyvinyl alcohol. The experimental results under limited conditions were learned to investigate the optimum glycerol concentrations and process temperatures. Simulation-based learning was used to predict the dependence on press pressure and shape parameters. The prediction results for unknown glycerol concentrations agreed well with the follow-up experiments.