Problem
Research questions and friction points this paper is trying to address.
informal environmental-health hazards
used lead-acid battery recycling
satellite-invisible operations
geospatial detection
low- and middle-income countries
Contextual Geospatial Features for Identifying Informal Environmental-Health Hazards Undetectable from Satellites: A ULAB Case Study
🤖 AI Summary
This study addresses the challenge of identifying small-scale informal environmental health hazards—such as informal lead-acid battery recycling—that evade detection by satellite observations and official registries. To overcome reliance on conventional remote sensing and registration data, the authors propose a contextualized geospatial feature construction method integrating domain knowledge. Leveraging geographic information systems and machine learning, the approach is rigorously evaluated through five-fold cross-validation, matched controls, and an independent dataset across India and Bangladesh. The model significantly outperforms random urban controls in detecting 172 previously unseen informal recycling sites and maintains high specificity by distinguishing informal activity patterns even among 131 formal facilities. This work represents the first scalable, highly specific method for identifying informal environmental risk sources.
📝 Abstract
Reliable, scalable detection of informal, small-scale environmental-health hazards (used lead-acid battery (ULAB) recycling, household-scale e-waste burning, indoor mercury amalgamation, brick kilns, small tanneries) remains an unsolved problem. These operations are invisible to satellites and absent from formal registries, yet disproportionately harm low-income populations in low- and middle-income countries. This paper articulates the problem class and explores a possible response: contextual geospatial features, with case-specific feature design informed by domain expertise. We use ULAB recycling as a demonstration case, drawing on 164 verified sites in Bangladesh and India from Pure Earth's Toxic Sites Identification Programme. At this sample size, five-fold cross-validation on the training set cannot statistically distinguish the engineered contextual features from a simple two-feature socio-demographic baseline. The added value only becomes visible when we evaluate outside the training set. On 172 held-out informal-recycling sites in non-NCR India and Bangladesh, the model assigns scores several times higher than to matched random urban controls; and on an independent set of 131 regulatory-confirmed formal recyclers, informal sites score materially higher than formal ones in non-NCR India, indicating that the model is picking up informal-recycler-specific structure rather than generic industrial signal. We frame these results as exploratory rather than confirmatory: label sparsity, gaps in point-of-interest coverage, and untested transfer beyond South Asia all remain open. We close with seven open problems and invite the environmental-health and geospatial machine-learning communities to engage with informal-hazard detection as a class of problems worth solving.
Innovation
Methods, ideas, or system contributions that make the work stand out.
contextual geospatial features
informal environmental hazards
used lead-acid battery (ULAB) recycling
geospatial machine learning
satellite-invisible detection
🔎 Similar Papers
No similar papers found.
