Deep learning spectral classification of spatial twins in three cotton breeding lines

The increasing popularity of cotton as a personal clothing material has made fire resistance testing of cotton fibers crucial. Current methods for testing fire resistance in cotton textiles involve destructive open flame and smoldering tests. Due to advancements in spectroscopic sensor technologies and deep learning (DL) frameworks, non-destructive flame resistance testing has been made possible. This study investigates the effectiveness of hyperspectral sensors for spectral classification of lint from three breeding lines of cotton fibers: SG 747 (a commercial cultivar), RIL 385 (a fire-resistant breeding line), and RIL 225 (a fire-susceptible breeding line). Spectral data was collected in the visible near-infrared range (300–1000 nm) and the shortwave infrared region (900–1700 nm). A one-dimensional convolutional neural network (1D-CNN) was developed as the foundational model in this study. Machine learning frameworks, including neural architectural search, hyperparameter tuning, and distributed learning, were applied to develop an optimized DL model architecture with hyper-tuned parameters. This systematic approach enabled fine-tuning of the model to achieve improved performance in cotton fire resistance classification tasks. The performance of the hyper-tuned model in the 900–1700 nm range was found to be higher than that of the base model, achieving a test accuracy of 86% compared to the base model's 84% accuracy. This study demonstrates the potential for non-destructive fire resistance testing in cotton fibers with the successful implementation of DL modeling for spectral classification of spatial twins. • Imaging-based hyperspectral classification of spatially twin cotton cultivar samples. • Implementation of neural architecture search (NAS) and hyperparameter tuning (HPT) to enhance deep learning model performance. • Development of a 1D-CNN framework for classifying cotton fibers by fire resistance, susceptibility, and cultivar lines.