Proceedings of Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics (IPEROP24)
DOI: https://doi.org/10.29363/nanoge.iperop.2024.051
Publication date: 18th October 2023
The urgent need to mitigate climate change defines a pressing need for new high-performance energy materials and, along with this, new accelerated strategies to discover them. The field of computational materials discovery has picked up significant momentum over the past years and now calls for equally effective methods to experimentally validate their theoretical predictions. In this presentation I will present a new experimental platform, which is in the final stages of assembly at the Mebourne Centre for Nanofabrication (Australia). I will introduce the different tools which will allow us to formulate coating solutions, convert those coating solutions into thin films and subsequently characterise their optical, electrical and structural properties. This process can operate autonomous for 24 hours at a clock -speed of 5 minutes. Machine learning will be a vital tool to help extract valuable information from big data and also to help guide the discovery process. I will present a recent proof-of-concept study where we use machine learning to enhanced the high-throughput fabrication and optimization of quasi-2D Ruddlesden-Popper perovskite solar cells [1] and speak about our plans to integrate this process into our materials discovery strategy.
The authors thank the Australian Centre for Advanced Photovoltaics (ACAP), the Australian Renewable Energy Agency, the Australian Research Council, and the ARC Centre of Excellence in Exciton Science (ACEX; CE170100026), for their financial support.