SugarcaneNet: an optimized ensemble of LASSO-regularized pre-trained models for accurate sugarcane disease classification

Sugarcane, a key crop for the world’s sugar industry, is prone to several diseases that have a substantial negative influence on both its yield and quality. To effectively manage and implement preventative initiatives, diseases must be detected promptly and accurately. In this study, we have presented a novel approach called SugarcaneNet that outperforms previous methods for automatically and quickly detecting sugarcane disease through leaf image processing. Our proposed approach consolidates an optimized weighted average ensemble of seven customized and LASSO-regularized pre-trained models, particularly InceptionV3, InceptionResNetV2, DenseNet201, DenseNet169, Xception, and ResNet152V2. Initially, we added more dense layers with LASSO regularization, dropout layers, and batch normalizations with renormalization at the bottom of these pre-trained models to improve the performance. The performance of sugarcane leaf disease classification was greatly improved by this addition. Following this, several comparative studies between the average ensemble and individual models were carried out, indicating that the ensemble technique performed better. The average ensemble of all modified pre-trained models achieved a better outcome with 99% F1 score, 99% precision, and 99.33% accuracy. Performance was further enhanced by the implementation of an optimized weighted average ensemble technique incorporated with grid search technique. This optimized “SugarcaneNet” model performed the best for detecting sugarcane diseases, having achieved accuracy, precision, recall, and F1 score of 99.60%, 100%, 100%, and 100%, respectively. Comprehensive analysis of the approach, including sensitivity and recent advancements, has enhanced the effectiveness and reliability of SugarcaneNet.