Poverty maps derived from satellite imagery are increasingly used to inform
high-stakes policy decisions, such as the allocation of humanitarian aid and
the distribution of government resources. Such poverty maps are typically
constructed by training machine learning algorithms on a relatively modest
amount of ``ground truth" data from surveys, and then predicting poverty levels
in areas where imagery exists but surveys do not. Using survey and satellite
data from ten countries, this paper investigates disparities in representation,
systematic biases in prediction errors, and fairness concerns in
satellite-based poverty mapping across urban and rural lines, and shows how
these phenomena affect the validity of policies based on predicted maps. Our
findings highlight the importance of careful error and bias analysis before
using satellite-based poverty maps in real-world policy decisions.

本文通过使用十个国家的调查与卫星数据，研究城乡界限上的贫困地图建立中的不平等现象、预测误差中的系统性偏差以及公平性问题，展示了这些现象如何影响基于预测地图的政策的有效性。本文的发现强调了在使用卫星贫困地图做出现实世界政策决策之前进行仔细的误差和偏差分析的重要性。

卫星贫困地图中的公平性和代表性：城乡差异及其对下游政策的影响证据

Fairness and representation in satellite-based poverty maps: Evidence of  urban-rural disparities and their impacts on downstream policy

Poverty maps are essential tools for governments and NGOs to track
socioeconomic changes and adequately allocate infrastructure and services in
places in need. Sensor and online crowd-sourced data combined with machine
learning methods have provided a recent breakthrough in poverty map inference.
However, these methods do not capture local wealth fluctuations, and are not
optimized to produce accountable results that guarantee accurate predictions to
all sub-populations. Here, we propose a pipeline of machine learning models to
infer the mean and standard deviation of wealth across multiple geographically
clustered populated places, and illustrate their performance in Sierra Leone
and Uganda. These models leverage seven independent and freely available
feature sources based on satellite images, and metadata collected via online
crowd-sourcing and social media. Our models show that combined metadata
features are the best predictors of wealth in rural areas, outperforming
image-based models, which are the best for predicting the highest wealth
quintiles. Our results recover the local mean and variation of wealth, and
correctly capture the positive yet non-monotonous correlation between them. We
further demonstrate the capabilities and limitations of model transfer across
countries and the effects of data recency and other biases. Our methodology
provides open tools to build towards more transparent and interpretable models
to help governments and NGOs to make informed decisions based on data
availability, urbanization level, and poverty thresholds.

该研究利用卫星图像和在线群众采集与社交媒体数据，运用机器学习方法，建立了可预测多个具有地理聚集特征的人口聚居地财富平均数和标准差的模型，并在塞拉利昂和乌干达进行了验证和性能比较，揭示元数据对农村区域财富预测有更好的表现。该方法不仅能恢复本地财富的平均数和变异性，还能捕捉它们之间的正相关性，具有一定的可迁移性和可解释性。

利用多模态数据推断贫困地图解释财富分布

Interpreting wealth distribution via poverty map inference using  multimodal data

Up-to-date poverty maps are an important tool for policy makers, but until
now, have been prohibitively expensive to produce. We propose a generalizable
prediction methodology to produce poverty maps at the village level using
geospatial data and machine learning algorithms. We tested the proposed method
for 25 Sub-Saharan African countries and validated them against survey data.
The proposed method can increase the validity of both single country and
cross-country estimations leading to higher precision in poverty maps of 44
Sub-Saharan African countries than previously available. More importantly, our
cross-country estimation enables the creation of poverty maps when it is not
practical or cost-effective to field new national household surveys, as is the
case with many low- and middle-income countries.

通过地理空间数据和机器学习算法，提出了一种在乡村级别上生成贫困地图的通用预测方法，通过在 25 个撒哈拉以南非洲国家的验证，该方法可以提高单个国家和跨国估计的有效性，为 44 个撒哈拉以南非洲国家提供比以前更精确的贫困地图。此方法可用于缩短成本和节省时间，避免重新采集新的全国家庭调查。