The challenge of studying perovskite solar cells’ stability with machine learning
Проблема исследования стабильности перовскитных солнечных элементов с помощью машинного обучения
2023-04-03
SCID: 54.1/fvws3ktn
Discuss with AI
Perovskite Database ProjectRandom Forestdevice stabilitylearning curvesperovskite solar cells
Figures from the paper
Abstract (AI)
Perovskite solar cells are the most dynamic emerging photovoltaic technology and attracts the attention of thousands of researchers worldwide. Recently, many of them are targeting device stability issues–the key challenge for this technology–which has resulted in the accumulation of a significant amount of data. The best example is the “Perovskite Database Project,” which also includes stability-related metrics. From this database, we use data on 1,800 perovskite solar cells where device stability is reported and use Random Forest to identify and study the most important factors for cell stability. By applying the concept of learning curves, we find that the potential for improving the models’ performance by adding more data of the same quality is limited. However, a significant improvement can be made by increasing data quality by reporting more complete information on the performed experiments. Furthermore, we study an in-house database with data on more than 1,000 solar cells, where the entire aging curve for each cell is available as opposed to stability metrics based on a single number. We show that the interpretation of aging experiments can strongly depend on the chosen stability metric, unnaturally favoring some cells over others. Therefore, choosing universal stability metrics is a critical question for future databases targeting this promising technology.
Key Findings
1
A Random Forest analysis of 1,800 perovskite solar cells identified factors associated with device stability using data from the Perovskite Database Project.
2
Analysis of over 1,000 cells with complete aging curves showed that stability interpretations strongly depend on the selected stability metric.
3
Learning curves indicate that adding more data of comparable quality offers limited potential for improving stability-model performance.
4
More complete reporting of experimental conditions and results could substantially improve machine-learning models of perovskite solar-cell stability.
5
Universal, standardized stability metrics are critical for future perovskite-solar-cell databases because single-number metrics may favor some cells over others.
Research Object
Perovskite solar cells and their reported aging/stability data
Research Subject
The factors determining device stability, the effect of data quantity and quality on machine-learning model performance, and the dependence of aging-experiment interpretation on the chosen stability metric
Publication Details
Publication Date
2023-04-03
Journal
Publisher
ISSN
Cited by
29
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Highly stable and efficient all-inorganic lead-free perovskite solar cells with native-oxide passivation2018
Stability of Perovskite Solar Cells: Degradation Mechanisms and Remedies2021
Stability Improvement of Perovskite Solar Cells by Compositional and Interfacial Engineering2021
Stability Issues of Perovskite Solar Cells: A Critical Review2021