Integrated framework for geological modeling: integration of data, knowledge, and methods

Three-dimensional (3D) geological modeling from limited and scattered information is essential for engineering geological investigation and design. Previous studies have encountered limitations when using a single modeling approach in complex tasks involving diverse geological structures, due to difficulties in accommodating the heterogeneity of geological structures and data imbalances. In response to this situation, this work presented an integrated geological modeling framework enabling the fusion of multi-source data, the integration of data and knowledge, and the combination of multiple modeling methods. Initially, multi-source data were merged into a unified format and integrated with knowledge extracted from geological texts to create a geological knowledge graph and a geospatial database for modeling. The complexity of the geological setting was then quantified by constructing a joint influence function, which informed the division of the modeling area into several subregions with geological significance. According to the geological characteristics and data conditions, the appropriate method for each subregion was automatically matched for independent modeling and finally integrated into a complete 3D geological model. The results indicated that the proposed integrated framework provided a flexible solution for complex modeling tasks, simplifying the process by addressing simpler subtasks while retaining the ability to capture structural information in geological domains with diverse characteristics. Moreover, the integration of geological data and knowledge promoted the structured representation and utilization of geological knowledge, promising to provide richer information for model construction and validation. This is crucial for the developed model to be able to effectively support engineering geological exploration.