DeepGeneralizationZhiyong ZhouLast updated on Jan 22, 2026Go to Project Site CodeAI ICRelatedGeoTextGeoAI for map generalization in multi-scale cartography: foundations, a research agenda, and interdisciplinary perspectivesSpaGAN: A spatially-aware generative adversarial network for building generalization in image mapsReasoning cartographic knowledge in deep learning-based map generalization with explainable AIMove and remove: Multi-task learning for building simplification in vector maps with a graph convolutional neural networkPublicationsGeoAI for map generalization in multi-scale cartography: foundations, a research agenda, and interdisciplinary perspectivesThis research investigates how GeoAI can contribute to the map generalization in multi-scale cartography.Zhiyong Zhou, Cheng Fu, Yu Feng, Guillaume Touya, Monika Sester, Robert WeibelProject DOISpaGAN: A spatially-aware generative adversarial network for building generalization in image mapsThis research proposes a spatially-aware generative adversarial network for building generalization in image maps, SpaGAN. It enhances the capacity to generalize buildings of varying sizes and shapes.Zhiyong Zhou, Cheng Fu, Robert WeibelProject DOIReasoning cartographic knowledge in deep learning-based map generalization with explainable AIThis research investigates what cartographic knowledge have been learned by deep learning models in map generalization.Cheng Fu, Zhiyong Zhou, Robert WeibelProject DOIMove and remove: Multi-task learning for building simplification in vector maps with a graph convolutional neural networkThis research proposes a multi-task learning method with graph convolutional neural networks. The proposed method formulates the building simplification problem as a joint task of node removal classification and node movement regression.Zhiyong Zhou, Cheng Fu, Robert WeibelProject DOI
