@inproceedings{kotthoff_ai_2019,
  title = {{AI} for {Materials} {Science}: {Tuning} {Laser}-{Induced} {Graphene} {Production}},
  abstract = {AI has advanced the state of the art in many application domains, including ones not ordinarily associated with computer science. We present an application of automated parameter tuning to materials science, in particular, we use surrogate models for automated parameter tuning to optimize the fabrication of laser-induced graphene. This process allows to create microscopic conductive lines in thin layers of insulating material, enabling the development of next-generation nano-circuits. Optimizing the parameters that control the laser irradiation process is crucial to creating high-quality graphene that is suitable for this purpose. Through the application of state-of-the-art parameter tuning techniques, we are able to achieve improvements of up to a factor of two compared to existing approaches in the literature and to what human experts are able to achieve. Our results are reproducible across different experimental specimen and the deployed application can be used by domain scientists without a background in AI or machine learning.},
  booktitle = {Data {Science} {Meets} {Optimisation} {Workshop} at {IJCAI} 2019},
  author = {Kotthoff, Lars and Jain, Vivek and Tyrrell, Alexander and Wahab, Hud and Johnson, Patrick},
  month = aug,
  year = {2019},
  month_numeric = {8}
}