Detecting Brick Kiln Infrastructure at Scale: Graph, Foundation, and Remote Sensing Models for Satellite Imagery Data
This work addresses the problem of scalable monitoring for brick kilns, which are critical for environmental and social issues in South Asia, by providing practical guidance using satellite imagery, though it is incremental as it builds on existing detection approaches.
The study tackled large-scale brick kiln detection from high-resolution satellite imagery to address air pollution and forced labor monitoring in South Asia, using a curated dataset of over 1.3 million image tiles and evaluating multiple models including a novel graph-based approach, with results showing complementary strengths across different methods.
Brick kilns are a major source of air pollution and forced labor in South Asia, yet large-scale monitoring remains limited by sparse and outdated ground data. We study brick kiln detection at scale using high-resolution satellite imagery and curate a multi city zoom-20 (0.149 meters per pixel) resolution dataset comprising over 1.3 million image tiles across five regions in South and Central Asia. We propose ClimateGraph, a region-adaptive graph-based model that captures spatial and directional structure in kiln layouts, and evaluate it against established graph learning baselines. In parallel, we assess a remote sensing based detection pipeline and benchmark it against recent foundation models for satellite imagery. Our results highlight complementary strengths across graph, foundation, and remote sensing approaches, providing practical guidance for scalable brick kiln monitoring from satellite imagery.