The challenge of studying perovskite solar cells’ stability with machine learning

Проблема исследования стабильности перовскитных солнечных элементов с помощью машинного обучения
Antonio Abate, Rutger Schlatmann, Eva Unger, Noor Titan Putri Hartono, Hans Köbler, T. Jesper Jacobsson, Mark Khenkin, Carolin Ulbrich, Paolo Graniero
2023-04-03

Perovskite Database ProjectRandom Forestdevice stabilitylearning curvesperovskite solar cells
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.
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.

Perovskite solar cells and their reported aging/stability data

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
Access Type
Author Information
Authors
Antonio Abate
Rutger Schlatmann
Eva Unger
Noor Titan Putri Hartono
Hans Köbler
T. Jesper Jacobsson
Mark Khenkin
Carolin Ulbrich
Paolo Graniero
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%