Machine Learning Framework For Characterizing Processing–Structure Relationship In Block Copolymer Thin Films

Authors

• Bradley Lamb, University of Southern Mississippi
• Saroj Upreti, University of Southern Mississippi
• Yunfei Wang, University of Southern Mississippi
• Daniel Struble, University of Southern Mississippi
• Chenhui Zhu, Advanced Light Source, Berkeley
• Guillaume Freychet, Brookhaven National Laboratory
• Xiaodan Gu, University of Southern Mississippi
• Boran Ma, University of Southern Mississippi

Document Type

Article

Publication Date

1-27-2026

School

Polymer Science and Engineering

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 (R² > 0.75), while AFM-based property predictions were less accurate (R² < 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.

Publication Title

Macromolecules

Volume

59

Issue

2

First Page

714

Last Page

727

Recommended Citation

Lamb, B., Upreti, S., Wang, Y., Struble, D., Zhu, C., Freychet, G., Gu, X., Ma, B. (2026). Machine Learning Framework For Characterizing Processing–Structure Relationship In Block Copolymer Thin Films. Macromolecules, 59(2), 714-727.
Available at: https://aquila.usm.edu/fac_pubs/21948