Advanced analysis of internal quantum efficiency measurements using machine learning

Abstract

The internal quantum efficiency (IQE) is given as the ratio between the externally collected electron current and the photon current absorbed by the device. Spectral analysis of IQE measurements is a powerful method to identify performance‐limiting mechanisms in solar cells. It also enables the extraction of key electrical and optical parameters. However, the potential of IQE measurements is only rarely fully utilized, presumably due to the significant complexity associated with the fitting process and its sensitivity to noise. In this study, machine learning is proposed as an efficient method to extract quantitative information from IQE measurements. The extraction method is automated and easy to use, providing an array of specific device parameters. By simplifying the analytical process, the developed machine learning algorithms also extract the parasitic absorption of the antireflection coating, a key parameter that is difficult to obtain by traditional methods. Although the method has been developed for and tested on silicon solar cells, it can be adapted and applied to other types of solar cells.

Physics-based extraction of material parameters from perovskite experiments via Bayesian optimization

“…13,15 Machine learning (ML) has emerged recently as a viable technique to assist semiconductor characterization, in which material properties are generally extracted from new data-based models that are trained by a massive theoretical/physical dataset. [20][21][22][23][24] For TRPL characterization, researchers have built a massive database for ML and can extract at least 4 material parameters from TRPL measurements on a single perovskite material, 22 which includes 2 fundamental parameters, i.e., the radiative recombination coefficient and equilibrium hole concentration, and 2 composite parameters, i.e., ambipolar carrier mobility (a function of individual electron/hole mobility) and non-radiative carrier lifetime. This approach heavily relies on the dataset production, which requires highperformance computation and re-production if researchers change theoretical models, materials structures, or experiments, leading to difficulty for use in everyday research.…”

“…Machine learning (ML) has emerged recently as a viable technique to assist semiconductor characterization, in which material properties are generally extracted from new data-based models that are trained by a massive theoretical/physical dataset. 20–24 For TRPL characterization, researchers have built a massive database for ML and can extract at least 4 material parameters from TRPL measurements on a single perovskite material, 22 which includes 2 fundamental parameters, i.e. , the radiative recombination coefficient and equilibrium hole concentration, and 2 composite parameters, i.e.…”