Abstract
Enhancing rice’s salt-alkali tolerance is important to agricultural production on globally salinized and alkaline soils. In recent years, the critical role of rhizosphere microorganisms in helping plants adapt to adverse conditions has drawn increasing attention, making the screening of core strains that enhance rice’s salt-alkali tolerance a research hotspot. This study integrates big data analysis and pattern recognition technologies with metagenomics and 16S rRNA sequencing to comprehensively uncover the diversity and functional profiles of rice rhizosphere microorganisms. Key microbial groups associated with salt-alkali tolerance were rapidly identified using machine learning and deep learning algorithms. AI-driven functional prediction and optimization methods, combined with genomic information, were applied to evaluate the salt-alkali tolerance potential of candidate strains. Furthermore, a high-throughput screening platform was established, and field trials validated the growth-promoting effects of the selected strains on rice. Leveraging AI’s adaptive learning capabilities, application conditions were optimized, and the strains’ adaptability to various salt-alkali environments was predicted. This study aims to explore the potential of big data and AI technologies in rhizosphere microbial screening, building an efficient and intelligent system for strain selection and optimization, and providing innovative strategies and solutions to enhance rice’s salt-alkali tolerance.
