Construction of Remote Sensing Knowledge Graph for Spatiotemporal Analysis

Currently, a significant portion of knowledge in the field of remote sensing (RS) is stored in unstructured formats, leading to inefficient data analysis and the formation of information silos due to fragmented data accumulation. Consequently, there is an urgent need for an effective knowl edge representation and modeling framework tailored to the characteristics of RS data. Knowledge graph (KG), owing to their highly structured nature and strong interoperability, offers a promising solution by enabling rapid integration of multi-source data and revealing complex interrelationships among heterogeneous datasets. This study proposes a novel approach that integrates temporal sequences with spatial information to construct a spatio-temporally evolving remote sensing KG (RSKG), thereby advancing the intelligent analysis capabilities of remote sensing imagery. Specifically, we innovatively incorporate multi-temporal, high-resolution RS image data into a unified KG framework endowed with spatio-temporal evolution properties. By representing image features within a KG structure, this approach not only improves the efficiency of spatio-temporal data management but also enhances the applicability of large language model (LLM) in the domain-specific context of RS. Experimental results demonstrate that integrating RS imagery, geographic information, and domain expertise into a structured and evolvable knowledge system significantly strengthens the semantic expressiveness of RS data. Furthermore, it enables LLMs to better interpret spatial semantics, accurately analyze surface change dynamics.