Machine Learning-Enhanced High-Throughput Fabrication and Optimization of Quasi-2D Ruddlesden-Popper Perovskite Solar Cells
Dr Nastaran Meftahi
- RMIT University
Thursday 24 November, 3pm
Abstract
Organic-inorganic perovskite solar cells (PSCs) are promising candidates for next-generation, inexpensive solar panels due to their commercially competitive cost and high-power conversion efficiency. However, PSCs suffer from poor stability.
A new and vast subset of PSCs, quasi-two-dimensional Ruddlesden-Popper PSCs (quasi-2D RP PSCs) has improved photostability and superior resilience to environmental conditions compared to three-dimensional metal-halide PSCs.
To accelerate the search for new quasi-2D RP PSCs we report a combinatorial, machine learning (ML) enhanced high-throughput perovskite film fabrication and optimization study.
We designed a bespoke experimental strategy and produced perovskite films with a range of different compositions using only spin-coating free, reproducible robotic fabrication processes.
The performance and characterization data of these solar cells were used to train a ML model that allowed for material parameter optimization and directed design of improved materials.
The ML optimized new quasi-2D RP perovskite films yielded solar cells with power conversion efficiencies reaching 16.9%.
About the speaker
Nastaran has extensive experience with computational methods such as machine-learning techniques and molecular dynamic simulations.
Her research focuses on applying advanced linear and nonlinear machine learning techniques such as multiple linear regression and artificial neural networks to explore the relationship between structure and photo-luminescent properties for photovoltaic materials.
She also uses classical molecular dynamics simulations and ab initio techniques to examine the mutual orientation and properties of organic photo-dyes in solar cell matrices.
