Artificial Intelligence-Assisted Breeding for Plant Disease Resistance

Area of Science:

• Plant Science
• Computational Biology
• Genetics and Breeding

Background:

• Improving crop disease resistance is crucial for global food security.
• Traditional breeding methods face challenges in efficiently developing resistant varieties.
• Emerging technologies like artificial intelligence offer new avenues for enhancing plant resilience.

Purpose of the Study:

• To review advancements in AI for plant disease detection and resistance prediction.
• To explore the potential of deep learning, large language models, and multi-modal models in plant science.
• To provide insights into integrating AI into plant breeding programs for disease resistance.

Main Methods:

• Bibliometric analysis of recent research on AI in plant disease detection, focusing on convolutional neural networks.
• Review of large language models and multi-modal models for interpreting complex disease patterns from heterogeneous data.
• Exploration of AI applications in genomic and phenomic selection for resistance-associated traits.

Main Results:

• AI, particularly deep learning, significantly enhances plant disease detection capabilities.
• Large language and multi-modal models show promise in analyzing complex, multi-source plant health data.
• AI accelerates high-throughput analysis for genomic and phenomic selection, aiding in the prediction of disease-resistant phenotypes.

Conclusions:

• AI integration is transformative for developing disease-resistant crops.
• Future directions include addressing data, model, and privacy challenges, potentially through federated learning.
• This review serves as a guide for applying AI to accelerate crop breeding for enhanced disease resistance.