top of page
Big Data & Aid Targeting in Myanmar
MAPPING COMMUNITY DEVELOPMENT AID:
SPATIAL ANALYSIS IN MYANMAR
In Myanmar, “Using Artificial Intelligence/machine learning to evaluate the distribution of community development aid across Myanmar (2025)” examines how community development projects are distributed spatially across local communities. Specifically, this research seeks to understand which communities are more likely to receive large amounts of development aid based on their poverty levels and other development characteristics. Toward this aim, “Mapping community development aid: Spatial analysis in Myanmar (2023)” develops granular poverty measures drawn from satellite imagery that are consistently available in the country. The paper creates aid density measures and visualizes aid hotspots. The concept of community-centered development was introduced in her paper “Two models of community-centered development in Myanmar (2020)”. These studies were among the earliest to compare the predictive power of nightlights with geospatially interpolated wealth in predicting aid amount per village.
..................................................................................................................................................................................
EXTRACTED FROM:
Mapping Community Development Aid: Spatial Analysis in Myanmar (2023)
Using Computer Vision & Deep Learning to Predict Poverty and Aid in Data-Sparse Contexts (2020)
DISTRUBUTION OF AID
Findings in this study suggest that nuances captured in nightlight luminosity can predict CLD aid density in Myanmar. Brighter nightlights are strongly correlated with higher aid density in that community. The model fit of this variable is better than other poverty-related variables.
​
Nightlight shows promise in capturing the variability of economic development in target villages and improving prediction of aid allocation.
Dr. Jung conducted analysis at the smallest geographical unit at the village level, or, at the administrative level 5. One of the measurements of this study, aid hotspots, does not depend on administrative boundaries.
​
..................................................................................................................................................................................
​
This study promotes evidence-based targeting for area-based interventions, lacking location specific and timely data. It addresses the disconnect between communities wanting to mobilize resources and development agencies identifying populations to serve. Exploring new data sources and synthesizing them with administrative and survey data at a fine-grained level extends their utility as a policy design and evaluation tool.
​
bottom of page