Re-experiment Smart: a Novel Method to Enhance Data-driven Prediction of Mechanical Properties of Epoxy Polymers

TL;DR

This paper introduces a new method combining multi-algorithm outlier detection and selective re-experimentation to improve data quality and prediction accuracy of polymer properties with minimal additional experiments.

Contribution

It presents a scalable approach to enhance dataset quality for polymer property prediction by efficiently identifying and re-measuring unreliable data points.

Findings

Significant reduction in prediction RMSE across multiple models

Improved prediction accuracy with only 5% re-measurement

Validated approach on a new dataset of 701 measurements

Abstract

Accurate prediction of polymer material properties through data-driven approaches greatly accelerates novel material development by reducing redundant experiments and trial-and-error processes. However, inevitable outliers in empirical measurements can severely skew machine learning results, leading to erroneous prediction models and suboptimal material designs. To address this limitation, we propose a novel approach to enhance dataset quality efficiently by integrating multi-algorithm outlier detection with selective re-experimentation of unreliable outlier cases. To validate the empirical effectiveness of the approach, we systematically construct a new dataset containing 701 measurements of three key mechanical properties: glass transition temperature ($T_g$), tan $\delta$ peak, and crosslinking density ($v_{c}$). To demonstrate its general applicability, we report the performance improvements across multiple machine learning models, including Elastic Net, SVR, Random Forest, and TPOT, to predict the three key properties. Our method reliably reduces prediction error (RMSE) and significantly improves accuracy with minimal additional experimental work, requiring only about 5% of the dataset to be re-measured. These findings highlight the importance of data quality enhancement in achieving reliable machine learning applications in polymer science and present a scalable strategy for improving predictive reliability in materials science.