Machine Learning Enabled Prediction of Electromagnetic Interference Shielding Effectiveness of Poly(Vinylidene Fluoride)/Mxene Nanocomposites

Abstract

Using machine learning (ML) approaches for the design and manufacturing of materials becomes an emerging technology that may possibly allow us to systematically discover novel materials with promising electromagnetic interference (EMI) shielding properties. Herein, we explored the correlation between input variables such as MXene loading, thickness of nanocomposites films, frequency, and predicted EMI shielding effectiveness (ES) of poly (vinylidene fluoride)/MXene (PVDF/MXene) nanocomposites materials via ML. Two different models of ML including Gaussian process regression (GPR) and support vector machine (SVM) were considered and compared. The results showed that the predicted data by the two models are in good agreement with the experimental values, indicating that the developed ML models are appropriate for predicting properties of nanocomposites materials for EMI shielding applications.