The proliferation of geospatial data in urban and territorial environments has significantly facilitated the development of geospatial artificial intelligence (GeoAI) across various Urban Applications. Given the vast yet inherently sparse labeled nature of geospatial data, there is a c
Spatial representation learning (SRL) is addressed with the proposed TorchSpatial framework, which includes a unified location encoding framework, benchmark tasks, and evaluation metrics, aiming to support SRL model development, reproducibility, and spatial fairness in GeoAI research.