Abstract
The screening of agricultural microbial strains plays a crucial role in enhancing crop stress resistance, promoting growth, and improving agricultural productivity, particularly in the cultivation of salt- and alkali-tolerant crops. However, traditional screening methods often suffer from limitations, including lengthy processing cycles, low efficiency, and inadequate environmental adaptability. In recent years, the rapid development of artificial intelligence (AI) technologies has brought unprecedented opportunities to the field of agricultural microbiology. This paper provides a comprehensive review of recent advances in AI-based screening and optimization of agricultural microbial strains, with a focus on the integration of genomics, metabolomics, and multi-omics data for strain function prediction and underlying mechanisms. It also examines specific applications of AI in the study of salt-alkali-tolerant crops, such as utilizing soil and crop growth data to optimize strain selection and application conditions, thereby enhancing the plant growth-promoting effects. In addition, the paper discusses technical frameworks for multi-strain combination optimization and highlights the unique advantages of AI in environmental adaptability simulation and functional prediction of microbial strains. This paper aims to clarify the vital role of AI technologies in microbial strain screening and optimization, reveal their application potential in the field of salt-alkali-tolerant crops, and provide references and prospects for future theoretical research and practical applications.
