Entity Association Network-Guided Method for Three-Dimensional Stratigraphic Modeling

Objectives: Wide-area three-dimensional stratigraphic models play a crucial supporting role in the survey and design of major infrastructure projects such as railways and highways, the development of underground space resources, and disaster risk assessment. However, wide-area stratigraphic data, including regional geological reports and geological maps, are characterized by varying granularity of stratigraphic information, a lack of structured descriptions of stratigraphic adjacency and spatial distribution relationships, and scattered and poorly associated spatiotemporal and attribute characteristic information. The relational entity organization model commonly used in existing three-dimensional stratigraphic modeling methods to organize wide-area stratigraphic data struggles to accurately express multi-dimensional relationships and multi-attributes, thereby affecting the efficiency of wide-area stratigraphic modeling. Methods: To address this issue, we propose a three-dimensional stratigraphic modeling method guided by an entity association network. First, a stratigraphic entity heterogeneous graph association network is constructed. The stratigraphic characteristic information extracted from geological reports and the inherent stratigraphic characteristic information in geological maps, using ChatGPT, are utilized to achieve an integrated expression of association relationships under the joint constraints of the time-space-attribute characteristics and multi-domain characteristics of the stratigraphic entities. Based on the stratigraphic entity heterogeneous graph association network, virtual boreholes are rapidly constructed to guide regional three-dimensional stratigraphic modeling. Results: By selecting typical areas and integrating stratigraphic characteristics and relationship information from DEM, regional geological reports, geological maps, and other data, the stratigraphic entity association network is constructed to guide the generation of a three-dimensional stratigraphic model. Conclusions: The effectiveness of this research method was verified through these applications.