Constructing a Resource Network for Data–Model Associative Retrieval and Recommendation in Geographic Modeling

Geographic modeling and simulation are essential methods for investigating complex geographic processes, such as urban expansion, land use change, and the hydrological cycle. Their implementation relies on diverse data and model resources to support model construction, calibration, and validation. However, these resources' growing volume and dispersion across distributed platforms make piecemeal manual retrieval time‐consuming and labor‐intensive, ultimately hindering their efficient discovery. To address this challenge, this study proposes a method for constructing a resource associative network that links data and models to facilitate data and model discovery. The proposed strategy includes four components: (1) a unified representation model is established for data and models to ensure consistent expression; (2) hierarchical associative relationships between resources are defined and quantified; (3) a resource associative network is constructed through the establishment of resource nodes and edges; (4) based on the resource network, an associative retrieval and recommendation method is proposed to realize the joint retrieval and intelligent recommendation of the data and model resources. To validate the practicality of the proposed method, a prototype system was developed and applied in a case study on flood forecasting. The results show that in the process of data collection and model construction, this method effectively improves the retrieval efficiency of resources, supporting broader adoption in geographic modeling and simulation.