Internship/Master project: Optimization Strategies for Novel Materials

Work Activities

Advances in Artificial intelligence have accelerated the prediction of new materials, while laboratory automation has increased the speed at which these materials can be synthesized. Automated thin-film fabrication pipelines, such as robotic spin-coating systems integrated with high-throughput characterization, can now produce hundreds of samples per day. However, for newly predicted materials the optimal synthesis conditions are usually unknown. 

The goal of this project is to develop and test optimization strategies to identify suitable synthesis conditions for novel perovskite compositions. Genetic algorithms, Bayesian optimization, or hybrid approaches will be used in a closed-loop system to search for synthesis parameters that improve material performance, quantified through absorption and photoluminescence yield using hyperspectral imaging, while chemical comp...