Low-and middle-income countries experience 77% of the world's premature deaths caused by non-communicable diseases, and their underlying health determinant data are often scarce and inaccurate. Improving satellite imagery data literacy worldwide is an integral step toward using the vast amount of publicly available data collected via satellites, such as air pollution, green space and light at night-all determinants of non-communicable diseases. Existing machine learning-based algorithms enable automated analysis of satellite imagery data, but health officials and scientists must know where to find and how to apply these algorithms to measure risk and target interventions.
Keywords: artificial intelligence; data literacy; developing countries; machine learning; non-communicable diseases; satellite imagery.
© The Author(s) 2025. Published by Oxford University Press on behalf of Royal Society of Tropical Medicine and Hygiene.