AI RESEARCH
Graph Convolutional Support Vector Regression for Robust Spatiotemporal Forecasting of Urban Air Pollution
arXiv CS.LG
•
ArXi:2605.03795v1 Announce Type: new Urban air quality forecasting is challenging because pollutant concentrations are nonlinear, nonstationary, spatiotemporally dependent, and often affected by anomalous observations caused by traffic congestion, industrial emissions, and seasonal meteorological variability. This study proposes a Graph Convolutional Vector Regression (GCSVR) framework for robust spatiotemporal forecasting of urban air pollution.