Automated Analysis of Internal Quantum Efficiency Measurements of GaAs Solar Cells Using Machine Learning

Investigating the internal quantum efficiency (IQE) of solar cells is essential for identifying performance limitations and improving their efficiency. However, fitting IQE measurements of gallium arsenide solar cells using numerical simulation programs can be a laborious and tedious process, often limiting the depth of the analysis to only qualitative levels. In this study, we propose the use of machine learning to automate the fitting process and enable the extraction of key electrical quantities that represent the performance-limiting mechanisms of the cells. This novel method can help unlock the full potential of IQE measurements as a powerful characterization tool for further research and development of gallium arsenide solar cells.