Using satellite imagery to understand and promote sustainable development
BACKGROUND Accurate and comprehensive measurements of a range of sustainable
development outcomes are fundamental inputs into both research and policy. For instance …
development outcomes are fundamental inputs into both research and policy. For instance …
A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
Recent advances in artificial intelligence and deep machine learning have created a step
change in how to measure human development indicators, in particular asset-based …
change in how to measure human development indicators, in particular asset-based …
Wilds: A benchmark of in-the-wild distribution shifts
Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …
[HTML][HTML] Energy poverty prediction in the United Kingdom: A machine learning approach
Energy poverty affects billions worldwide, including people in developed and developing
countries. Identifying those living in energy poverty and implementing successful solutions …
countries. Identifying those living in energy poverty and implementing successful solutions …
A review of machine learning and satellite imagery for poverty prediction: Implications for development research and applications
The field of artificial intelligence is seeing the increased application of satellite imagery to
analyse poverty in its various manifestations. This nascent but rapidly growing intersection of …
analyse poverty in its various manifestations. This nascent but rapidly growing intersection of …
A comparison of machine learning approaches for identifying high-poverty counties: Robust features of DMSP/OLS night-time light imagery
G Li, Z Cai, X Liu, J Liu, S Su - International journal of remote …, 2019 - Taylor & Francis
The goal of the present study is to demonstrate that high-poverty counties and robust
classification features can be identified by machine learning approaches using only …
classification features can be identified by machine learning approaches using only …
Satellite image and machine learning based knowledge extraction in the poverty and welfare domain
Recent advances in artificial intelligence and machine learning have created a step change
in how to measure human development indicators, in particular asset based poverty. The …
in how to measure human development indicators, in particular asset based poverty. The …
What matters in the new field of machine learning and satellite imagery-based poverty predictions? A review with relevance for potential downstream applications and …
This paper reviews the state of the art in satellite and machine learning based poverty
estimates and finds some interesting results. The most important factors correlated to the …
estimates and finds some interesting results. The most important factors correlated to the …
[PDF][PDF] Wilds: A benchmark of in-the-wild distribution shifts
Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …
Seeing What We Can't: Evaluating implicit biases in deep learning satellite imagery models trained for poverty prediction
J O'Brien - 2023 - scholarworks.wm.edu
Previous studies have sought to use Convolutional Neural Networks for regional estimation
of poverty levels. However, there is limited research into possible implicit biases in deep …
of poverty levels. However, there is limited research into possible implicit biases in deep …