Towards Limiting Semantic Data Loss in 4d Urban Data Semantic Graph Generation

Abstract

Abstract. To enrich urban digital twins and better understand city evolution, the integration of heterogeneous, spatio-temporal data has become a large area of research in the enrichment of 3D and 4D (3D + Time) semantic city models. These models, which can represent the 3D geospatial data of a city and their evolving semantic relations, may require data-driven integration approaches to provide temporal and concurrent views of the urban landscape. However, data integration often requires the transformation or conversion of data into a single shared data format, which can be prone to semantic data loss. To combat this, this paper proposes a model-centric ontology-based data integration approach towards limiting semantic data loss in 4D semantic urban data transformations to semantic graph formats. By integrating the underlying conceptual models of urban data standards, a unified spatio-temporal data model can be created as a network of ontologies. Transformation tools can use this model to map datasets to interoperable semantic graph formats of 4D city models. This paper will firstly illustrate how this approach facilitates the integration of rich 3D geospatial, spatio-temporal urban data and semantic web standards with a focus on limiting semantic data loss. Secondly, this paper will demonstrate how semantic graphs based on these models can be implemented for spatial and temporal queries toward 4D semantic city model enrichment.

Leveraging Standards in Model-Centric Geospatial Knowledge Graph Creation

“…-Geospatial XML Schema [25] extending the mappings based on [24] to take advantage of geospatial standards in the Semantic Web -Geospatial OWL ontologies created from UML models using the ISO 19150-2 standard [26] Thus far, an initial comparison of the resulting ontologies and datasets has been performed using the CityGML 2.0 and 3.0 conceptual models [26] within the context of improving the integration of 3D city model snapshots to model spatio-temporal building evolution. These data models were chosen for their rich vocabularies and widespread use in nD urban data research and industry.…”

“…Q3: How can these transformations be structured to improve scalability when integrating large datasets covering the district and city-sized urban areas? Towards this end, several contributions have been realized [25,26]:…”

“…This work explores a method for model-centric data integration with semantic web technologies based on standards to create interoperable data models and improve data interoperability of nD urban linked-open-data. By using semiautomated mapping transformations, as proposed in UD-Graph [25,26], existing nD urban data standard data models and data can be combined with existing spatio-temporal semantic web standards.…”

“…Currently, using UML models appears to be a favorable approach for creating OWL ontologies [26] due to the similarity in modeling concepts between UML and OWL, but a more formal evaluation of this approach is needed to measure how much semantic data may be lost in the case of urban data standards which present a large divergence between their conceptual and physical data models, and thus more human intervention is required to converge on a complete mapping. Additionally, this approach requires testing with additional data models aside from CityGML, such as IndoorGML 10 , or BIM-IFC and profiling the data volume and query execution time of the datasets generated.…”

UD‐SV: Urban data services and visualization framework for sharing multidisciplinary research

“…We also have to explore more on navigation based on space and time. For example, we are currently working on visualization modes based on graphs (Vinasco‐Alvarez et al, 2021). More integration of other types of data (2D/3D), at different scales, for example, building scale, urban scale, etc) including vector data (road, railway lines etc.)…”