A Unified Spatio-Temporal Data Processing Framework for Multi-Source Air Quality Forecasting

Accurate air quality forecasting requires the effective integration of heterogeneous data sources that vary in spatial coverage, temporal resolution, and sensing reliability. This paper presents a unified spatio-temporal data processing framework designed to support multi-source air quality forecasting by jointly leveraging regulatory monitoring stations of the Central Pollution Control Board (CPCB) as reference-grade anchors and community-driven Internet of Things (IoT) sensing platforms for spatial densification. The proposed end-to-end workflow addresses key challenges associated with heterogeneity, data quality, and interoperability through systematic schema harmonization, multi-stage data cleaning, and robust missing data imputation using a Robocentric Iterated Extended Kalman Filter (RIEKF). The processed data are temporally aligned to a uniform sampling grid and enriched with spatial descriptors, including geospatial coordinates, administrative boundaries, and proximity-based emission features. These enriched observations are subsequently fused into a unified spatio-temporal representation that captures both spatial dependencies and temporal dynamics across the sensor network. Dynamic graphs constructed from this representation are processed using a Mobility-Aware Peripheral-Enhanced Graph Neural Network to forecast pollutant concentrations and generate categorical air quality indices. The framework is evaluated using regression metrics reported as RMSE/MAE in µg/m3 and MAPE in %, together with standard AQI classification metrics, demonstrating its effectiveness in improving predictive accuracy and robustness for real-world air quality forecasting applications.