Monitoring compliance with environmental regulations is a global challenge. It is particularly difficult for governments in low-income countries, where informal industry is responsible for a large amount of pollution, because the governments lack the ability to locate and monitor large numbers of dispersed polluters. This study demonstrates an accurate, scalable machine learning approach for identifying brick kilns, a highly polluting informal industry in Bangladesh, in satellite imagery.Our data reveal widespread violations of the national regulations governing brick manufacturing, which has implications for the health and well-being of the country. Our approach offers a low-cost, replicable method for regulatory agencies to generate information on key pollution sources.
We demonstrate how machine-learning methods can inform the efficient use of these limited resources while accounting for real-world concerns, such as gaming the system and institutional constraints. Here, we predict the likelihood of a facility failing a water pollution inspection and propose alternative inspection allocations that would target high-risk facilities. Implementing such a data-driven inspection allocation could detect over seven times the expected number of violations than current practices.