抄録
Soil carbon storage is a key element of the global carbon cycle and plays a crucial role in mitigating climate change. However, climate warming and land-use changes make the dynamic variation of soil carbon storage more complex. Traditional estimation methods have limitations in both spatial and temporal resolution, while the application of remote sensing technology, big data, and artificial intelligence (AI) models offers new opportunities for more accurate estimation of soil carbon storage. This paper reviews the application of remote sensing technology in monitoring the spatial distribution of soil carbon storage, analyzes the advantages of big data in integrating multi-source soil and climate information, and explores the potential of AI models in predicting spatiotemporal changes in soil carbon storage, with a particular focus on how machine learning and deep learning algorithms optimize dynamic estimation. Furthermore, the paper evaluates the prospects of applying remote sensing, big data, and AI in multi-scale analysis, and proposes data-driven carbon management strategies and policy recommendations. This paper aims to provide more precise methods for estimating soil carbon storage by integrating remote sensing, big data, and AI technologies, thereby offering scientific support for carbon management and soil protection strategies in the context of climate change.
