(108d) AI-Guided Autonomous Flow Reactor Platform for Accelerated Nanomaterial Synthesis Screening and Parameter Space Mapping | AIChE

(108d) AI-Guided Autonomous Flow Reactor Platform for Accelerated Nanomaterial Synthesis Screening and Parameter Space Mapping


Kenis, P. - Presenter, University of Illinois
Vikram, A., University of Illinois at Urbana-Champaign
Zahid, A., University of Illinois at Urbana-Champaign
The ability to precisely tune the properties colloidal quantum dots by controlling their composition, structure, size, and size distribution makes them a promising class of materials for applications including ranging from optoelectronics and photovoltaics to bioimaging. Given the vastness of synthesis parameter space, identifying optimal compositions and structures as well associated optimal synthesis recipes for these complex nanocrystals, however, remains a major hurdle for accelerated screening and discovery. The implementation of modular flow reactors, integrated with real-time reaction monitoring, automation and data science, for resource-efficient synthesis has the potential to accelerate this material discovery and synthesis screening process.

Our work utilizes a modular continuous flow reactor platform for synthesis of heavy-metal-free colloidal quantum dots with improved size-uniformity and enhanced optical properties. Our efforts, in collaboration with experts from industry and academia, have led to multiple promising insights into the synthesis of InP-based quantum dots.

The main feature of this presentation will be the development of a flow reactor platform that integrates inline spectroscopy with artificial intelligence-based feedback algorithms for efficient mapping and exploration of the full multidimensional chemical synthesis parameter space (rather than merely identifying a set of synthetic parameters to synthesize a quantum dot with a specific desired properties). This platform autonomously learns the parameter space using 44 experiments, develops a predictive model, and synthesizes InP quantum dots of targeted band gap and polydispersity all through self-driven experiments with no prior knowledge of the reaction space within 28 hours. Our results underscore the promise and critical role of data-science-assisted experimentation for not only accelerating the screening and discovery of colloidal nanocrystals but also towards maximizing synthesis insights across multidimensional parameter space for different classes of colloidal materials.