Improving Data and Prediction Quality of High-Throughput Perovskite Synthesis with Model Fusion

Abstract

Combinatorial fusion analysis (CFA) is an approach for combining multiple scoring systems using the rank-score characteristic function and cognitive diversity measures to combine different machine learning models to achieve better prediction quality. In this work, we apply CFA to the synthesis of metal halide perovskites containing organic ammonium cations via inverse temperature crystallization. Using a dataset generated by high-throughput experimentation, four individual models (support vector machines, random forests, weighted logistic classifier, and gradient boosted trees) were developed. We characterize each of these scoring systems and explore 66 possible combinations of the models. When measured by the precision on predicting crystal formation, the majority of the combination models improves the individual model results. The best combination models outperform the best individual models by 3.9 percentage points in precision. In addition to improving prediction quality, we demonstrate how the fusion models can be used to identify mislabeled input data and address issues of data quality. In particular, we identify example cases where all single models and all fusion models do not give the correct prediction. Experimental replication of these syntheses reveals that these compositions are sensitive to modest temperature variations across the different locations of the heating element that can hinder or enhance the crystallization process. In summary, we demonstrate that model fusion using CFA can not only identify a previous unconsidered influence on reaction outcome but also be used as a form of quality control for high-throughput experimentation.

Improving SDG Classification Precision Using Combinatorial Fusion

“…The results of the current paper are in line with those findings. Namely, the pattern matches the results from three other recent publications [1,15,31] where model fusion and cognitive diversity were used to perform combinatorial fusion. The combined models perform consistently as well as, and in many cases outperform, the best of the two individual models.…”

Using automated serendipity to discover how trace water promotes and inhibits lead halide perovskite crystal formation

“…Paired experiments were placed in a mirror symmetric ("butterfly") pattern on the 96-well microplate, depicted in Figure S2, to eliminate any effects of temperature variations across the plate during heating. 28 To define our notation, Npairs is the total number of unique pairs of experiments performed (one each with and without addition of water), and Nwet+ and Ndry+ are the number of crystals observed for experiments with and without water added, respectively. Concordant outcomes-when both the wet and dry pairs yield a crystal (N++ ) or not (N--)-are uninformative.…”

Using automated serendipity to discover how trace water promotes and inhibits lead halide perovskite crystal formation

“…Paired experiments were placed in a mirror symmetric ("butterfly") pattern on the 96-well microplate, depicted in Figure S2, to eliminate any effects of temperature variations across the plate during heating. 28 To define our notation, Npairs is the total number of unique pairs of experiments performed (one each with and without addition of water), 30 which is avoided by using the exact unconditional form. 31 ) The relative number of the discordant outcomes reveals the directionality and magnitude of the effect.…”