Detecting Brick Kiln Infrastructure at Scale: Graph, Foundation, and Remote Sensing Models for Satellite Imagery Data

TL;DR

This paper presents a comprehensive approach to large-scale brick kiln detection in South Asia using high-resolution satellite imagery, combining graph-based models, remote sensing pipelines, and foundation models to improve monitoring capabilities.

Contribution

It introduces ClimateGraph, a novel region-adaptive graph model, and benchmarks multiple detection methods, advancing scalable brick kiln monitoring from satellite data.

Findings

ClimateGraph effectively captures spatial kiln layouts.

Remote sensing pipeline performs competitively with foundation models.

Combining methods offers improved detection accuracy.

Abstract

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major source of air pollution and forced labor in South Asia, yet large-scale monitoring remains limited by sparse and outdated ground data.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.