In Situ Photoluminescence Dataset for Exploring Material and Processing Variabilities in Blade-Coated Perovskite Photovoltaics

Content:

This dataset contains time-resolved in situ data acquired during the formation of blade-coated perovskite thin films, which were subsequently processed into functional perovskite solar cells. The time series data capture the vacuum quenching process - a critical step in perovskite layer formation - using photoluminescence (PL) and diffuse reflection imaging. The dataset is intended to support deep learning applications for predicting both material-level properties (e.g., precursor composition) and device-level performance metrics (e.g., power conversion efficiency, PCE).

Unlike the previous dataset, this dataset includes perovskite solar cells fabricated under varied process conditions. Specifically, the quenching duration, precursor solution molarity, and molar ratio were systematically changed to enhance the diversity of the data.

To monitor the vacuum quenching process, a PL imaging setup captured four channels of time series image data (2D+t), including one diffuse reflection channel and three PL spectrum channels filtered for different wavelengths. All images were cropped into 65x56 pixel patches, isolating the active area of individual solar cells. However, currently, the dataset provides only the time transients of these four channels, where the spatial mean intensity was calculated for each time step. This dimensionality reduction transforms the high-dimensional video data into compact temporal transients, highlighting the critical dynamics of thin-film formation.

The dataset consists of two parts: 

Samples finalized into functional solar cells:

Includes photovoltaic (PV) performance metrics as target variables:(1) power conversion efficiency (PCE),(2) open-circuit voltage (VOC),(3) short-circuit current density (JSC),(4) fill factor (FF), measured in forward and backward sweeps.

Samples not finalized into functional solar cells:

Does not include PV metrics. These samples are suitable for classification tasks, such as predicting precursor solution molarity and molar ratio.

Further information on the experimental procedure and data processing is detailed in the corresponding paper: Deep learning for augmented process monitoring of scalable perovskite thin-film fabrication. Please cite this paper when using the dataset.

Columns in the data.h5 file:

Identifiers: date, expID, patchID (sample identifiers).

Input features: ND, LP725, LP780, SP775 (signal transients from vacuum quenching).

Material properties: ratio, molarity (precursor solution properties).

Process parameters: evac_duration (vacuum quenching duration).

Photovoltaic performance metrics:

PCE_forward, PCE_backward, VOC_forward, VOC_backward, JSC_forward, JSC_backward, FF_forward, FF_backward.

Photoluminescence measurements: plqyWL, lumFluxDens (PL spectra after vacuum quenching).

Electrical characteristics:

RSHUNT_forward, RSHUNT_backward, RS_forward, RS_backward (shunt and series resistances from jV curves).

Derived parameters: PLQY, iVOC, jscPLQY, egPLQY (calculated from PLQY measurements).

Usage:

The dataset is structured for machine learning applications to improve understanding of the complex perovskite thin-film formation from solution. The corresponding paper tackles these challenges:

Material classification: Using ND, LP725, LP780, and SP775 as inputs to predict ratio and molarity.

Device performance regression: Using ND, LP725, LP780, and SP775 with a variable process parameter (evac_duration) as inputs to predict PCE_backward.

Process control recommendations: Forecasting monitoring signals (ND, LP725, LP780, SP775) as a function of a variable process parameter (evac_duration) and predicting the corresponding device performance metric PCE_backward.

Scripts for generating the same train-test splits and cross-validation folds as in the corresponding paper are provided in the GitHub repository:

00a_generate_Material_train_test_folds.ipynb

00b_generate_PCE_train_test_folds.ipynb

Additionally, random forest models used for forecasting are included in forecasting_models.zip.