Enhancing Dimensionality Prediction in Hybrid Metal Halides via Feature Engineering and Class-Imbalance Mitigation

TL;DR

This paper introduces a machine learning approach that combines feature engineering and class-imbalance techniques to accurately predict the structural dimensionality of hybrid metal halides, addressing dataset imbalance issues.

Contribution

The study develops a novel multi-stage workflow with interaction-based descriptors and SMOTE augmentation to enhance dimensionality prediction in imbalanced datasets.

Findings

Improved F1-scores for minority classes

Robust cross-validation performance across all classes

Effective mitigation of class imbalance effects

Abstract

We present a machine learning framework for predicting the structural dimensionality of hybrid metal halides (HMHs), including organic-inorganic perovskites, using a combination of chemically-informed feature engineering and advanced class-imbalance handling techniques. The dataset, consisting of 494 HMH structures, is highly imbalanced across dimensionality classes (0D, 1D, 2D, 3D), posing significant challenges to predictive modeling. This dataset was later augmented to 1336 via the Synthetic Minority Oversampling Technique (SMOTE) to mitigate the effects of the class imbalance. We developed interaction-based descriptors and integrated them into a multi-stage workflow that combines feature selection, model stacking, and performance optimization to improve dimensionality prediction accuracy. Our approach significantly improves F1-scores for underrepresented classes, achieving robust cross-validation performance across all dimensionalities.