抄録
The structure of soil aggregates is a crucial factor influencing crop growth, nutrient uptake, and water retention capacity, while roots acquire essential nutrients like nitrogen through dynamic interactions with soil structure. Optimizing soil physical properties has been proven an effective approach to improving nitrogen use efficiency; however, the complexity of soil-root interactions, involving multiple variables and nonlinear dynamics, poses challenges for traditional research methods to fully uncover the underlying mechanisms. To address this, this study employs artificial intelligence (AI) technology to develop a three-dimensional dynamic model of soil aggregate structure and root interaction, simulating root growth and nitrogen uptake characteristics under various soil physical conditions. The results demonstrate that different soil aggregate structures, such as soil looseness and organic matter content, significantly affect nitrogen uptake efficiency in roots, revealing the intricate relationships between soil physical properties and nitrogen cycling. The model further provides theoretical insights and practical guidance for optimizing organic fertilizer application strategies, enhancing soil water retention and aeration, and promoting efficient nitrogen uptake. By integrating AI-driven dynamic modeling techniques, this study offers innovative approaches to understanding the coupling mechanisms between soil physical properties and crop nitrogen uptake, contributing to precision agriculture and sustainable soil management.
