A robust low data solution: dimension prediction of semiconductor nanorods

TL;DR

This paper introduces a deep neural network regression approach combined with SMOTE-REG for accurate dimension prediction of semiconductor nanorods using limited data, validated by experimental results and interpretability analysis.

Contribution

It presents a novel application of SMOTE-REG with deep learning for nanorod dimension prediction from scarce data, along with interpretability via LIME.

Findings

High prediction accuracy on original and synthetic data

Effective interpretation of variable importance correlating with experiments

Validated model performance with additional experimental data

Abstract

Precise control over dimension of nanocrystals is critical to tune the properties for various applications. However, the traditional control through experimental optimization is slow, tedious and time consuming. Herein a robust deep neural network-based regression algorithm has been developed for precise prediction of length, width, and aspect ratios of semiconductor nanorods (NRs). Given there is limited experimental data available (28 samples), a Synthetic Minority Oversampling Technique for regression (SMOTE-REG) has been employed for the first time for data generation. Deep neural network is further applied to develop regression model which demonstrated the well performed prediction on both the original and generated data with a similar distribution. The prediction model is further validated with additional experimental data, showing accurate prediction results. Additionally, Local Interpretable Model-Agnostic Explanations (LIME) is used to interpret the weight for each variable, which corresponds to its importance towards the target dimension, which is approved to be well correlated well with experimental observations.