Feature engineering for microstructure-property mapping in organic photovoltaics

TL;DR

This paper introduces an unsupervised feature engineering framework that combines digital image processing, low-dimensional microstructure representation, and Gaussian process modeling to accurately predict charge transport properties in organic photovoltaic films.

Contribution

It presents a novel unsupervised framework integrating image analysis and statistical methods for microstructure-property mapping in OPVs, enhancing predictive accuracy.

Findings

The framework effectively captures microstructure features relevant to charge transport.

Two distance-based metrics are essential for complete microstructure quantification.

Gaussian process models accurately predict short-circuit current from microstructure features.

Abstract

Linking the highly complex morphology of organic photovoltaic (OPV) thin films to their charge transport properties is critical for achieving high performance material system that serves as a cost-efficient approach for energy harvesting. In this paper, a novel unsupervised feature engineering framework is developed and used to establish reduced-order structure-property linkages for OPV films. This framework takes advantage of digital image processing algorithms to identify the salient material features of OPVs undergoing the charge transport phenomenon. These material states are then used to obtain a low-dimensional representation of OPV microstructures via 2-point spatial correlations and principal component analysis. It is found that in addition to the material PC scores, two distance-based metrics are required to complete the microstructure quantification of complex OPVs. A localized version of the Gaussian process (laGP) is then used to link the material PC scores as well as the two distance-based metrics to the short-circuit current of OPVs. It is demonstrated that the unsupervised feature engineering framework presented in this paper in conjunction with the laGP can lead to high-fidelity and accurate data-driven structure-property linkages for OPV films.