Harnessing artificial intelligence for sustainable rice leaf disease classification

Area of Science:

• Agricultural Science
• Computer Science
• Biotechnology

Background:

• Agriculture is crucial for global food security, with rice being a vital staple crop.
• Rice production faces significant threats from diseases like Hispa, leaf blast, and brown spots, impacting yield and quality.
• Sustainable Development Goal 2 (SDG 2) necessitates innovative solutions for crop protection and enhanced food security.

Purpose of the Study:

• To develop and evaluate an Artificial Intelligence (AI) model for the early detection and classification of rice leaf diseases.
• To enhance the model's accuracy by incorporating spatial and channel attention mechanisms within a convolutional neural network (CNN).
• To design a lightweight, modular system for real-time implementation on edge devices in agricultural settings.

Main Methods:

• A convolutional neural network (CNN) was developed using a dataset of 3,355 labeled rice leaf images.
• Spatial and channel attention mechanisms were integrated into the CNN to improve focus on critical disease indicators.
• The model was trained and evaluated for its performance in classifying four categories: Brown Spot, Leaf Blast, Hispa, and Healthy leaves.

Main Results:

• The enhanced CNN model demonstrated high accuracy and robust performance across all tested rice leaf disease categories.
• Attention mechanisms significantly improved the model's precision in identifying subtle and complex disease patterns.
• The lightweight architecture facilitated efficient real-time operation on edge devices, proving its practical applicability.

Conclusions:

• The AI-driven system offers a reliable and scalable solution for detecting rice leaf diseases, enabling timely interventions to minimize crop losses.
• This technology supports SDG 2 by enhancing rice production, promoting sustainable agricultural practices, and bolstering global food security.
• The research underscores the transformative potential of AI in modernizing agriculture, improving efficiency, and building resilient food systems.