Introduction to the Special Issue on Deep Learning for Spatio-Temporal Data: Part 2

Abstract

framework that explicitly models the topological skeleton of a terrain surface with a contour tree from com-putational topology, which is guided by the physical constraint. Their framework consists of two neural networks: a convolutional neural network (CNN) to learn spatial contextual features on a 2D image grid and a graph neural network (GNN) to learn the statistical distribution of physics-guided spatial topological dependency on the contour tree. The two models are co-trained via variational EM. Evaluations on the real-world flood mapping datasets show that the proposed models outperform baseline methods in classification accuracy, especially when training labels are limited.Inthe article titled “Make More Connections: Urban Traffic Flow Forecasting with Spatiotemporal Adaptive Gated Graph Convolution Network,” Lu et al. consider constructing the road network as a dynamic weighted graph through the attention mechanism to describe and capture the dynamic spatio-temporal correlation, and they aim to seek both spatial neighbors and semantic neighbors to make more connections between road nodes. They propose a novel Spatio-temporal Adaptive Gated Graph Convolution Network (STAG-GCN) to predict traffic conditions for several time steps ahead. STAG-GCN mainly consists of two major components: (1) multivari-ate self-attention Temporal Convolution Network (TCN) is utilized to capture local and long-range temporal dependencies across recent, daily periodic and weekly periodic observations, and (2) mix-hop AG-GCN extracts selective spatial and semantic dependencies within multi-layer stack-ing through an adaptive graph gating mechanism and mix-hop propagation mechanism. The out-puts of different components are weighted fused to generate the final prediction results. Extensive experiments on two real-world large-scale urban traffic datasets have verified the effectiveness of their proposed approach.