In The Journal of chemical physics
Machine learning techniques are seeing increased usage for predicting new materials with targeted properties. However, widespread adoption of these techniques is hindered by the relatively greater experimental efforts required to test the predictions. Furthermore, because failed synthesis pathways are rarely communicated, it is difficult to find prior datasets that are sufficient for modeling. This work presents a closed-loop machine learning-based strategy for colloidal synthesis of nanoparticles, assuming no prior knowledge of the synthetic process, in order to show that synthetic discovery can be accelerated despite limited data availability.
Fong Anthony Y, Pellouchoud Lenson, Davidson Malcolm, Walroth Richard C, Church Carena, Tcareva Ekaterina, Wu Liheng, Peterson Kyle, Meredig Bryce, Tassone Christopher J