Back to Search
Start Over
Physiochemical machine learning models predict operational lifetimes of CH3NH3PbI3 perovskite solar cells.
- Source :
- Journal of Materials Chemistry A; 4/28/2024, Vol. 12 Issue 16, p9730-9746, 17p
- Publication Year :
- 2024
-
Abstract
- Halide perovskites are promising photovoltaic (PV) materials with the potential to lower the cost of electricity and greatly expand the penetration of PV if they can demonstrate long-term stability under illumination in the presence of moisture and oxygen. The solar cell service lifetime, as quantified by T<subscript>80</subscript> (the time required for the power conversion efficiency to drop to 80% of its starting value), for utility, commercial, or residential PV systems needs to be several decades in order to yield low-cost electricity, and thus it is not practical to directly measure it. It would be useful if T<subscript>80</subscript> could be predicted from the initial dynamics of a solar cell's performance, but until now no models have been developed to do so. In this work, we report the development of machine learning models to predict T<subscript>80</subscript> of ITO/NiO<subscript>x</subscript>/CH<subscript>3</subscript>NH<subscript>3</subscript>PbI<subscript>3</subscript>/C<subscript>60</subscript>/BCP/Ag solar cells operating at maximum power point under 1-sun equivalent photon flux in air at varying temperatures and relative humidities. Efficiency losses are driven by short-circuit current and fill factor, indicating that photochemical reactions with O<subscript>2</subscript> and H<subscript>2</subscript>O are a major contributor to degradation. Spatial patterns evident from in situ dark field optical microscopy also suggest that the electric field gradient at device edges plays a significant role in perovskite decomposition. Models are trained using a menu of features from three distinct categories: (i) measurements of the initial rates of change of device parameters, (ii) ambient conditions during operation (temperature & partial pressure of H<subscript>2</subscript>O), and (iii) features based on underlying physics and chemistry. We show that a theory-based physiochemical feature derived from a model of the chemical reaction kinetics of the rate of degradation of CH<subscript>3</subscript>NH<subscript>3</subscript>PbI<subscript>3</subscript> is particularly valuable for prediction and was selected as the most dominant feature in the best performing models. With a dataset consisting of 45 degradation experiments with T<subscript>80</subscript> values ranging over a factor of almost 30, the model predicts T<subscript>80</subscript> with an average accuracy of about 40% on samples not used in training. This hybrid ML approach should be effective when applied to other compositions, device architectures, and advanced packaging schemes. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 20507488
- Volume :
- 12
- Issue :
- 16
- Database :
- Complementary Index
- Journal :
- Journal of Materials Chemistry A
- Publication Type :
- Academic Journal
- Accession number :
- 176784927
- Full Text :
- https://doi.org/10.1039/d3ta06668a