In this paper, we introduce a web GIS platform created expressly for exploring and researching a set of 63,467 historical maps and illustrations extracted from 4,000 titles of Chinese local gazetteers. We layer these images with a published, geo-referenced collection of Land Survey Maps of China (1903–1948), which includes the earliest large-scale maps of major cities and regions in China that are produced with modern cartographic techniques. By bringing together historical illustrations depicting spatial configurations of localities and the earliest modern cartographic maps, researchers of Chinese history can study the different spatial epistemologies represented in both collections. We report our workflow for creating this web GIS platform, starting from identifying and extracting visual materials from local gazetteers, tagging them with keywords and categories to facilitate content search, to georeferencing them based on their source locations. We also experimented with neural networks to train a tagger with positive results. Finally, we display them in the web GIS platform with two modes, Images in Map (IIM) and Maps in Map (MIM), and with content- and location-based filtering. These features together enable researchers easy and quick exploration and comparison of these two large sets of geospatial and visual materials of China.

In this paper, we introduce a web GIS platform created expressly for exploring and researching a set of 63,497 historical maps and illustrations extracted from 4,000 titles of Chinese local gazetteers. We layer these images with a published, geo-referenced collection of Land Survey Maps of China (1903China ( -1948, which includes the earliest largescaled maps of major cities and regions in China that are produced with modern cartographic techniques. By bringing together historical illustrations depicting spatial configurations of localities and the earliest modern cartographic maps, researchers of Chinese history can study the different spatial epistemologies represented in both collections. We report our workflow for creating this web GIS platform, starting from identifying and extracting visual materials from local gazetteers, tagging them with keywords and categories to facilitate content search, to georeferencing them based on their source locations. We also experimented with neural networks to train a tagger with positive results. Finally, we display them in the web GIS platform with two modes, Images in Map (IIM) and Maps in Map (MIM), and with content-and location-based filtering. These features together enable researchers easy and quick exploration and comparison of these two large sets of geospatial and visual materials of China.