Graph Convolutional Support Vector Regression for Robust Spatiotemporal Forecasting of Urban Air Pollution

TL;DR

This paper introduces GCSVR, a novel graph convolutional support vector regression framework that improves urban air pollution forecasting by capturing spatiotemporal dependencies and reducing outlier sensitivity.

Contribution

It combines graph convolutional learning with support vector regression to enhance robustness and accuracy in spatiotemporal air quality prediction, including uncertainty quantification.

Findings

GCSVR outperforms existing benchmarks in predictive accuracy.

The model maintains stable performance across different seasons and pollution episodes.

Conformal prediction provides reliable uncertainty estimates.

Abstract

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 Support Vector Regression (GCSVR) framework for robust spatiotemporal forecasting of urban air pollution. The model combines graph convolutional learning to capture inter-station spatial dependence with support vector regression to model nonlinear temporal dynamics while reducing sensitivity to outlier observations. The proposed framework is evaluated using air quality records from 37 monitoring stations in Delhi and 18 stations in Mumbai, representing inland and coastal metropolitan environments in India. Forecasting performance is assessed across multiple horizons and compared with established temporal and spatiotemporal benchmarks. The results show that GCSVR consistently improves predictive accuracy and maintains stable performance across seasons and outlier-prone pollution episodes. Statistical test further confirms the reliability of the proposed approach across the two cities. Finally, conformal prediction is integrated with GCSVR to generate calibrated prediction intervals, enhancing its practical value for uncertainty-aware air quality monitoring and public health decision-making.