Predicting Poverty Level from Satellite Imagery
Keywords:
Poverty prediction, satellite imagery, deep learning, remote sensing, convolutional neural networks (CNN), socioeconomic indicatorsAbstract
Accurate poverty estimation is essential for effective policy-making and resource allocation in underdeveloped regions.
Traditional poverty assessment methods rely on census surveys, which are often expensive, time-consuming, and infrequent. Recent advances in machine learning and remote sensing have enabled the use of satellite imagery to predict economic conditions in data-scarce areas. This study proposes a deep learning-based approach to predict poverty levels using high-resolution satellite images and socioeconomic indicators.
References
J. Blumenstock, G. Cadamuro, and R. On, "Predicting poverty and wealth from mobile phone metadata," Science, vol. 350, no. 6264,
pp. 1073–1076, 2015. [2] N. Jean, M. Burke, M. Xie, W. M. Davis, D. B. Lobell, and S. Ermon, "Combining satellite imagery and machine learning to
predict poverty," Science, vol. 353, no. 6301, pp. 790–794, 2016.
