Digital twin entity refers to the information model that exists in the computer virtual space that is completely equivalent to the physical entity, which is a multidimensional, multiscale description and portrayal of the physical entity, and can achieve the real mapping and simulation analysis of the physical entity. The field of ecological environment has many types of soil-groundwater pollution sources and pollutants in production enterprises, complex source-sink relationship, pollution early warning, and traceability difficulties. The use of digital twinning technology must be studied to establish a real-life 3D model of the plant area of the production enterprise and a digital twin model within the plant, incorporate real-time monitoring data into the simulation system of soil and groundwater twinning, carry out rapid data fusion and simulation derivation, and eventually form a complete digital twin system of a multigranularity polluting enterprise plant. When facing the above problems, the current construction method of digital twin model focuses on the construction of a 3D model, ignoring the complete expression and description of the enterprise entity’s geometrical parameters, attributes, relationships, and other characteristic data, so it is unable to meet the requirements of comprehensively and multidimensionally dynamic portrayal of the enterprise entity. To achieve the accurate construction of the twin entity model of the pollution enterprise, a more efficient way needs to be adopted to organize and manage the characteristic data of the enterprise entity, and select a suitable data model to model the enterprise scene. The traditional GIS data model uses conventional map data as a template for indirect spatial modeling of entities, which limits the application of spatial data and hinders adapting to new expression needs such as real-time dynamic correlation in multimodal situations. To address this problem, Hua Yixin proposed a multigranularity spatiotemporal object data model from the perspective of data model. The model provides an all-round description of multigranularity spatiotemporal entities from spatiotemporal reference, spatial location, attribute characteristics, spatial morphology, and compositional structure, with multidimensional and all-attribute characteristics. The model also increases the description of characteristic information such as behavioral ability and association relationship, and the expression content is more comprehensive and more in line with the actual entity expression. Therefore, this paper proposes a multigranularity spatiotemporal entity modeling method for constructing a digital twin of a polluting enterprise, which achieves the comprehensive multidimensional information description and portrayal of the site entity of a polluting enterprise in the form of a data model by modeling, and analyzing the relevant features and relations of the spatiotemporal entity of the polluting enterprise. A rubber factory in Guangzhou City is taken as a case study for instance validation of the data model.Results show the multigranularity spatiotemporal entity modeling can efficiently organize and express the multidimensional features of the entity, achieve the accurate construction of the digital twin body model of the pollution enterprise, and provide an effective method and data model basis for the application service of the digital twin of the pollution enterprise.

remote sensing;polluting companies;digital twins;entity feature data;multi-granularity spatio-temporal entity modelling;data models