LightNews
jyangtum.bsky.social
@jyangtum.bsky.social
1 followers 1 following 1 posts
Posts Media Videos Starter Packs
jyangtum.bsky.social @jyangtum.bsky.social · 1d
MapLayNet can learn a concept hierarchy of map layout via an unsupervised data similarity measure. The resulting layout embedding can be further explored for more cartographic tasks.
carto-giscience.bsky.social
The Cartography and Geographic Information Society @carto-giscience.bsky.social · Aug 26
New paper from Jian Yang and colleagues, presenting MapLayNet, a way of understanding maps as a graph and classifying how they are laid out, with the aim of better map layout retrieval and design recommendation #GISchat #OpenAccess doi.org/10.1080/1523...
Figure 1 Research diagram illustrating map layout graph construction. Part a) shows a world map of seismic activity with 6 colored markers representing different elements on the map. Part b) transforms these into a graph theory representation where elements become vertices (v1-v6) connected by edges showing relationships. Figure 10 Machine learning visualization showing how AI clusters similar map elements together. Each dot represents a different map and are grouped together in 2D space according to their layout. The algorithm successfully identifies layout patterns across different map types! #MachineLearning #Cartography
2 4