Poverty Map

Poverty maps use satellite imagery, socioeconomic surveys, and other data sources, combined with machine learning algorithms like convolutional neural networks and regression models, to estimate poverty levels geographically. Current research emphasizes improving model accuracy and interpretability, addressing biases (particularly urban-rural disparities), and validating predictions rigorously across diverse contexts. These maps are crucial for informing policy decisions related to resource allocation and poverty reduction strategies, demanding careful consideration of model limitations and potential inaccuracies to ensure equitable and effective interventions.

Papers

August 3, 2024

A Comparative Analysis of Wealth Index Predictions in Africa between three Multi-Source Inference Models
Márton Karsai, János Kertész, Lisette Espín-Noboa
Comparative Study Market Index Source Model Poverty Reduction Market Prediction Poverty Map

December 1, 2023

Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks
Hamid Sarmadi, Thorsteinn Rögnvaldsson, Nils Roger Carlsson, Mattias Ohlsson, Ibrahim Wahab, Ola Hall
Convolutional Neural Network Deep Convolutional Neural Network Poverty Map

May 2, 2023

Fairness and representation in satellite-based poverty maps: Evidence of urban-rural disparities and their impacts on downstream policy
Emily Aiken, Esther Rolf, Joshua Blumenstock
Procedural Fairness Individual Representation Bias Evaluation Impact Assessment Health Disparity Poverty Map

February 28, 2023

Novel Machine Learning Approach for Predicting Poverty using Temperature and Remote Sensing Data in Ethiopia
Om Shah, Krti Tallam
Machine Learning Remote Sensing Temperature Measurement Poverty Level Poverty Map Poverty Prediction

February 17, 2023

Interpreting wealth distribution via poverty map inference using multimodal data
Lisette Espín-Noboa, János Kertész, Márton Karsai
Multimodal Data Crowd Sourced Data Poverty Level Wealth Distribution Poverty Map

Poverty Map

Papers

A Comparative Analysis of Wealth Index Predictions in Africa between three Multi-Source Inference Models

Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks

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

Novel Machine Learning Approach for Predicting Poverty using Temperature and Remote Sensing Data in Ethiopia

Interpreting wealth distribution via poverty map inference using multimodal data