By integrating AI tools, such as ML and LLM, with experimental insights, we aim to discover functional materials that are stable, unique, and new. The outcomes will help build intelligent, closed-loop systems coupled directly with experimental efforts. Above is the workflow we developed to design 2D hybrid perovskites with targeted energetics.

By implementing lab automation, we aim to navigate the composition-synthesis space and accelerate the innovation and exploration of high-performance optoelectronic materials and devices. The automated spin-Bot shown above and the liquid-handling robot, coupled with in-situ optical characterization tools, integrated with data-driven decision-making, will facilitate rapid and efficient exploration of material solutions.

Our main focus is to develop self-assembled molecules as stable and efficient charge-selective layers to optimize the hidden interfaces of inverted perovskite solar cells. Our objectives include:

(1) Maximizing surface coverage via suppressing the aggregation of SAMs;

(2) Enhancing the interfacial contact between perovskite and SAMs;

(3) Improving the energy-level alignment to perovskite.

We investigate efficient cost-effective approaches towards the advanced manufacture of large-scale ordered nano (quantum dots) and micro crystals of hybrid materials. The hierarchical ordering at different length scales will bring about emergent optical and electronic properties.