Machine Learning Framework for Characterizing Processing–Structure Relationship in Block Copolymer Thin Films

TL;DR

This paper introduces a machine learning framework to analyze block copolymer thin film structures using X-ray and microscopy data, enabling high-throughput and interpretable predictions of material morphology.

Contribution

A novel ML framework combining GISAXS and AFM data with SHAP interpretability for high-throughput analysis of BCP thin film morphology.

Findings

A convolutional neural network achieved 97% accuracy in classifying AFM images by surface features.

ML models predicted domain orientation with R² > 0.75 for GISAXS data but lower accuracy for AFM data.

SHAP analysis showed additive ratio is the most influential parameter for morphological predictions.

Abstract

The morphology of block copolymers (BCPs) critically
influences
material properties and applications. This work introduces a machine
learning (ML)-enabled, high-throughput framework for analyzing grazing
incidence small-angle X-ray scattering (GISAXS) data and atomic force
microscopy (AFM) images to characterize BCP thin film morphology.
A convolutional neural network was trained to classify AFM images
by surface features, achieving 97% testing accuracy. Classified images
were then analyzed to extract 2D grain size measurements from the
samples in a high-throughput manner. ML models were trained to predict
domain orientation based on processing parameters such as solvent
ratio, additive type, and additive ratio. GISAXS-based properties
were predicted with strong performances (R
2 > 0.75), while AFM-based property predictions were less accurate
(R
2 < 0.60), likely due to the localized
nature of AFM measurements compared to the bulk information captured
by GISAXS. Beyond model performance, interpretability was addressed
using SHapley Additive exPlanations (SHAP). SHAP analysis revealed
that the additive ratio had the largest impact on morphological predictions,
where additive provides the BCP chains with increased volume to rearrange
into thermodynamically favorable morphologies. This interpretability
helps validate model predictions and offers insight into parameter
importance. Altogether, the presented framework combining high-throughput
characterization and interpretable ML offers an approach to exploring
and optimizing BCP thin film morphology across a broad processing
landscape.

Figures