Developed an automated workflow based on robotic synthesis, automated characterization, and machine learning for combinatorial discovery of metal halide perovskites (MHP) for optoelectronic applications.
Significance and Impact
The developed workflow provides an opportunity to accelerate the production of MHP materials with vast compositional spaces by several orders of magnitude.
– Robotic synthesis and rapid throughput characterization are used to explore long-term stability of MHP materials in ambient conditions.
– Non-negative matrix factorization and Gaussian process regression are used to interpolate the photoluminescent behavior of the sparse phase diagram obtained from measurements.
– Phase diagram regions with high stability are identified.
K. Higgins, S. M. Valleti, M. Ziatdinov, S. V. Kalinin, and M. Ahmadi, "Chemical Robotics Enabled Exploration of Stability in Multicomponent Lead Halide Perovskites via Machine Learning," ACS Energy Lett.5, 3426-3436 (2020). DOI: 10.1021/acsenergylett.0c01749