Combining satellite imagery and machine learning to predict poverty
Combining satellite imagery and machine learning to predict poverty
复制标题
DOI：
10.1126/science.aaf7894
复制
发表时间：
2016-08-19
期刊：
影响因子：
56.9
通讯作者：
Ermon, Stefano
中科院分区：
文献类型：
--
作者：
Jean, Neal;Burke, Marshall;Ermon, Stefano
在发展中国家，关于经济生计的可靠数据仍然很少，这阻碍了研究这些结果和制定改善这些结果的政策的努力。在这里，我们展示了一种准确、廉价、可扩展的方法，用于从高分辨率卫星图像中估计消费支出和资产财富。利用来自五个非洲国家（尼日利亚、坦桑尼亚、乌干达、马拉维和卢旺达）的调查和卫星数据，我们展示了如何训练卷积神经网络来识别图像特征，这些特征可以解释高达75%的地方经济结果差异。我们的方法只需要公开可用的数据，可以改变追踪和瞄准发展中国家贫困的努力。它还展示了强大的机器学习技术如何在训练数据有限的情况下应用，表明在许多科学领域有广泛的潜在应用。
Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries-Nigeria, Tanzania, Uganda, Malawi, and Rwanda-we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.