Spatial-Temporal Data Intelligence for Urban Carbon Footprint Tracking via Satellite Imagery

Abstract

Rapid urbanization and the imperative to achieve net-zero targets have elevated the need for accurate, high-resolution tracking of urban carbon footprints. This review synthesizes spatial-temporal data intelligence frameworks that leverage satellite imagery for emission estimation, source attribution, and mitigation planning, positioning them as intelligent engineering systems (IES) for sustainable urban governance. Grounded in systems engineering, cyber-physical systems (CPS) theory, and information theory, these frameworks integrate multi-resolution satellite observations (optical, thermal, SAR) with auxiliary socio-economic and IoT data through computer vision, spatio-temporal deep learning, and graph-based models. The analysis examines four AI-driven transformation pathways: from standardized emission inventories to personalized, morphology-aware tracking; from reactive annual reporting to proactive hotspot prediction and optimization; from labor-intensive ground surveys to autonomous intelligent pipelines; and from isolated municipal dashboards to integrated cyber-physical urban ecosystems. Concrete examples include U-Net and DeepLab segmentation of building footprints and land-use change from Sentinel-2 and PlanetScope imagery, combined with ConvLSTM models for temporal emission dynamics, and digital-twin city simulations for scenario optimization. While these approaches deliver substantial gains in spatial resolution and update frequency, critical limitations persist regarding atmospheric interference, ground-truth scarcity, model generalization across heterogeneous cities, and attribution uncertainty. Future prospects emphasize physics-informed multi-modal architectures, edge-deployed inference, and federated learning for privacy-preserving cross-city collaboration. The work provides a rigorous template for developing trustworthy spatial-temporal intelligence systems aligned with broader IES principles in urban sustainability.