SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases

TL;DR

This paper introduces SugarcaneShuffleNet, a lightweight, fast convolutional neural network optimized for real-time sugarcane leaf disease diagnosis on resource-constrained devices, supported by a new dataset and a deployment app.

Contribution

The paper presents a novel lightweight CNN model, SugarcaneShuffleNet, along with a curated dataset and a practical web app for effective on-field sugarcane disease diagnosis in low-resource settings.

Findings

SugarcaneShuffleNet achieved 98.02% accuracy and 4.14 ms inference time.

Compared to other models, it offers a better speed-accuracy trade-off for low-resource deployment.

The integrated app provides explainable AI with Grad-CAM in field conditions.

Abstract

Despite progress in AI-based plant diagnostics, sugarcane farmers in low-resource regions remain vulnerable to leaf diseases due to the lack of scalable, efficient, and interpretable tools. Many deep learning models fail to generalize under real-world conditions and require substantial computational resources, limiting their use in resource-constrained regions. In this paper, we present SugarcaneLD-BD, a curated dataset for sugarcane leaf-disease classification; SugarcaneShuffleNet, an optimized lightweight model for rapid on-device diagnosis; and SugarcaneAI, a Progressive Web Application for field deployment. SugarcaneLD-BD contains 638 curated images across five classes, including four major sugarcane diseases, collected in Bangladesh under diverse field conditions and verified by expert pathologists. To enhance diversity, we combined SugarcaneLD-BD with two additional datasets, yielding a larger and more representative corpus. Our optimized model, SugarcaneShuffleNet, offers the best trade-off between speed and accuracy for real-time, on-device diagnosis. This 9.26 MB model achieved 98.02% accuracy, an F1-score of 0.98, and an average inference time of 4.14 ms per image. For comparison, we fine-tuned five other lightweight convolutional neural networks: MnasNet, EdgeNeXt, EfficientNet-Lite, MobileNet, and SqueezeNet via transfer learning and Bayesian optimization. MnasNet and EdgeNeXt achieved comparable accuracy to SugarcaneShuffleNet, but required significantly more parameters, memory, and computation, limiting their suitability for low-resource deployment. We integrate SugarcaneShuffleNet into SugarcaneAI, delivering Grad-CAM-based explanations in the field. Together, these contributions offer a diverse benchmark, efficient models for low-resource environments, and a practical tool for sugarcane disease classification. It spans varied lighting, backgrounds and devices used on-farm