Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention

2025-03-03

AI Summary

Soybean leaf diseases exhibit highly similar symptoms, and conventional recognition methods suffer from limited interpretability and accuracy. To address this, we propose a CNN-GNN sequential interpretable framework: MobileNetV2 extracts local lesion features; a cosine similarity graph—enhanced by adaptive neighborhood sampling—is constructed to capture inter-sample symptom correlations, which are modeled via GraphSAGE; a cross-modal attention mechanism improves decision interpretability, while Grad-CAM and Eigen-CAM are fused to generate dual-granularity lesion heatmaps. Evaluated on a ten-class soybean disease dataset, our method achieves 97.16% classification accuracy—substantially outperforming standalone CNNs (≤95.04%) and traditional machine learning approaches (≤77.05%). With only 2.3 million parameters, the framework enables real-time inference on edge devices.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Soybean leaf disease detection is critical for agricultural productivity but faces challenges due to visually similar symptoms and limited interpretability in conventional methods. While Convolutional Neural Networks (CNNs) excel in spatial feature extraction, they often neglect inter-image relational dependencies, leading to misclassifications. This paper proposes an interpretable hybrid Sequential CNN-Graph Neural Network (GNN) framework that synergizes MobileNetV2 for localized feature extraction and GraphSAGE for relational modeling. The framework constructs a graph where nodes represent leaf images, with edges defined by cosine similarity-based adjacency matrices and adaptive neighborhood sampling. This design captures fine-grained lesion features and global symptom patterns, addressing inter-class similarity challenges. Cross-modal interpretability is achieved via Grad-CAM and Eigen-CAM visualizations, generating heatmaps to highlight disease-influential regions. Evaluated on a dataset of ten soybean leaf diseases, the model achieves $97.16%$ accuracy, surpassing standalone CNNs ($le95.04%$) and traditional machine learning models ($le77.05%$). Ablation studies validate the sequential architecture's superiority over parallel or single-model configurations. With only 2.3 million parameters, the lightweight MobileNetV2-GraphSAGE combination ensures computational efficiency, enabling real-time deployment in resource-constrained environments. The proposed approach bridges the gap between accurate classification and practical applicability, offering a robust, interpretable tool for agricultural diagnostics while advancing CNN-GNN integration in plant pathology research.

Problem

• Detects soybean leaf diseases with high accuracy and interpretability.
• Addresses inter-class similarity challenges in disease classification.
• Ensures computational efficiency for real-time agricultural diagnostics.

Innovation

• Hybrid CNN-GNN framework for disease detection
• MobileNetV2 and GraphSAGE with cross-modal attention
• Lightweight model for real-time agricultural diagnostics