Predicting Mechanical Properties of Carbon Nanotube (CNT) Images Using Multi-Layer Synthetic Finite Element Model Simulations

• Published in: 2023 IEEE International Conference on Image Processing (ICIP) pp. 3264 - 3268
• Main Authors: Safavigerdini, Kaveh, Nouduri, Koundinya, Surya, Ramakrishna, Reinhard, Andrew, Quinlan, Zach, Bunyak, Filiz, Maschmann, Matthew R., Palaniappan, Kannappan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.10.2023
• Subjects: Computational modeling; Forestry; Prediction of Mechanical Properties; Predictive models; Quasi-images; Random Forest; ResNeXt; Scanning electron microscopy; Self-assembly; SEM Images; Solid modeling; Three-dimensional displays

We present a pipeline for predicting mechanical properties of vertically-oriented carbon nanotube (CNT) forest images using a deep learning model for artificial intelligence (AI)-based materials discovery. Our approach incorporates an innovative data augmentation technique that involves the use of m...