FloraSyntropy-Net: Scalable Deep Learning with Novel FloraSyntropy Archive for Large-Scale Plant Disease Diagnosis

2025-08-25

AI Summary

Existing AI models for early plant disease diagnosis suffer from poor generalization and limited cross-species transferability. To address this, we introduce FloraSyntropy—a large-scale benchmark dataset covering 35 plant species and 97 disease classes—and propose FloraSyntropy-Net, a privacy-preserving federated learning framework. Our contributions include: (1) a client cloning strategy to mitigate data heterogeneity across decentralized nodes; (2) a dynamic optimal model selection mechanism inspired by memetic algorithms; and (3) a hybrid architecture integrating DenseNet201 with a deep feature enhancement module to improve discriminative representation learning. Evaluated on FloraSyntropy, FloraSyntropy-Net achieves 96.38% classification accuracy; on a cross-domain pest dataset, it attains 99.84% accuracy. The framework significantly enhances cross-species robustness and scalability in real-world agricultural applications while ensuring data privacy through decentralized training.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Large Vision Models
• Multiagent Systems: Distributed Problem Solving

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Early diagnosis of plant diseases is critical for global food safety, yet most AI solutions lack the generalization required for real-world agricultural diversity. These models are typically constrained to specific species, failing to perform accurately across the broad spectrum of cultivated plants. To address this gap, we first introduce the FloraSyntropy Archive, a large-scale dataset of 178,922 images across 35 plant species, annotated with 97 distinct disease classes. We establish a benchmark by evaluating numerous existing models on this archive, revealing a significant performance gap. We then propose FloraSyntropy-Net, a novel federated learning framework (FL) that integrates a Memetic Algorithm (MAO) for optimal base model selection (DenseNet201), a novel Deep Block for enhanced feature representation, and a client-cloning strategy for scalable, privacy-preserving training. FloraSyntropy-Net achieves a state-of-the-art accuracy of 96.38% on the FloraSyntropy benchmark. Crucially, to validate its generalization capability, we test the model on the unrelated multiclass Pest dataset, where it demonstrates exceptional adaptability, achieving 99.84% accuracy. This work provides not only a valuable new resource but also a robust and highly generalizable framework that advances the field towards practical, large-scale agricultural AI applications.

Problem

• Addresses lack of generalization in AI for plant disease diagnosis across diverse species
• Introduces a large-scale dataset and benchmark for scalable deep learning in agriculture
• Proposes a federated learning framework for privacy-preserving and adaptable disease classification

Innovation

• Federated learning framework with memetic algorithm
• Deep Block for enhanced feature representation
• Client-cloning strategy for scalable privacy-preserving training