Optimizing Laser-Induced Graphene Production

Abstract

A lot of technological advances depend on next-generation materials, such as graphene, which enables better electronics, to name but one example. Manufacturing such materials is often difficult, in particular, producing graphene at scale is an open problem. We apply state-of-the-art machine learning to optimize the production of laser-induced graphene, an established manufacturing method that has shown great promise. We demonstrate improvements over previous results in terms of the quality of the produced graphene from a variety of different precursor materials. We use Bayesian model-based optimization to quickly improve outcomes based on little initial data and show the robustness of our approach to different experimental conditions, tackling a small-data problem in contrast to the more common big-data applications of machine learning. We analyze the learned surrogate models with respect to the quality of their predictions and learned relationships that may be of interest to domain experts and improve our understanding of the processes governing laser-induced graphene production.

Efficient Computation Using Spatial-Photonic Ising Machines: Utilizing Low-Rank and Circulant Matrix Constraints

“…The demand for computational power to solve largescale optimization problems is continually increasing in fields such as synthetic biology [1], drug discovery [2], machine learning [3], and materials science [4,5]. However, many optimization problems of practical interest are NPhard, meaning the resources required to solve them grow exponentially with problem size [6].…”

Predicting the sheet resistance of laser-induced graphitic carbon using machine learning

“…Machine learning is an alternative approach to modeling the LIGC process. Using Bayesian model-based optimization, a notable improvement of the Raman G/D ratio, which indicates the degree of graphitization in the LIG patterns, was achieved by a factor of four [19,20]. Furthermore, to monitor the process of LIG formation, computer vision and deep transfer learning models were developed [21].…”