Spatial regression graph convolutional neural networks (SRGCNNs) as a deep learning paradigm that is capable of handling a wide range of geographical tasks where multivariate geographic data needs spatial regression modeling and prediction.

Spatial regression analysis conducted in the manner of graph convolutional neural network. Two versions of SRGCNN model are provided in the initial post: a) global regression model (SRGCNN) and b) geographically weighted regression model (SRGCNN-GW)

Details can be found in the original paper: Zhu, D., Liu, Y., Yao, X., & Fischer, M. M. (2021). Spatial regression graph convolutional neural networks: A deep learning paradigm for spatial multivariate distributions. GeoInformatica, 1-32..