Geospatial knowledge is the result of spatial thinking and reasoning about natural and human phenomena (Golledge 2002), playing an important role in urban planning, land management, and environmental protection. Digital vector maps are important sources of geospatial knowledge such as topographic maps, land cover maps, traffic maps, city maps, etc. Maps, distinguished by spatial cognition expression symbols, are regarded as the second language of geoscience research. Maps are not only a means for humans to explain geographical phenomena, but they are also a significant instrument for gaining spatial information. Humans get spatial knowledge about geographic objects' location, shape, size, spatial pattern, etc. from maps via intuitive visual perception, computational geometry, spatial statistics, and other spatial operation methods. Driven by data collection technologies, artificial intelligence, and network technology, map audiences are shifting from human-oriented services to intelligent machine-oriented services. Map service has encountered new challenges in intelligent machine application fields (e.g., spatial scene perception for autonomous driving, semantic navigation of indoor robots, etc.)-heterogeneous spatial semantics, insufficient representation of spatial knowledge, and inadequate knowledge reasoning ability (Zhang et al. 2022). Traditional spatial representation with geometric symbols benefits human visual perception, geometric operations, and statistical analysis, but it is unsuitable for machine-oriented services. To expand geospatial knowledge services and promote the development of knowledge-driven research, a geographic knowledge representation model that can be interpreted and calculated by machines is required.

The consistency of geospatial data is of great significance for the application and updating of geographic information in web maps. Due to the multiple data sources and different temporal versions, the tile web maps usually meet the inconsistency question across different layers. This study tries to develop a method to detect this kind of inconsistency utilizing a raster-based scaling approach. Compared with vector-based handling, this method can be directly available for multi-level tile images in a pixel representation form. The proposed cross-layer raster tile map rendering method (CRTMRM) consists of four primary aspects: geographic object separation, consistency rendering rules, data scaling and derivation with super-pixel segmentation, and inconsistency detection. The scale transformation strategy with the super-pixel attempts to obtain a simplified representation. Taking the scale lifespan variation and geometric consistency rules into account, the inconsistency detection of tile maps is conducted between temporal versions, multi-sources, and different scales through actual and derived data overlay analysis. The experiment focuses on features of cross-layer water or vegetation areas with Level 9 to Level 14 in Baidu Maps, Amap, and Google Maps. This method is able to serve as a basis for massive unstructured web map data inconsistency detection and support intelligent web map rendering.