Combining satellite imagery and machine learning to predict poverty
Neal jean, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, Stefano Ermon
Poverty is the #1 UN Sustainable development goal
The elimination of poverty worldwide is the first of 17 UN Sustainable Development Goals for the year 2030. To track progress towards this goal, we require more frequent and more reliable data on the distribution of poverty than traditional data collection methods can provide.
In this project, we propose an approach that combines machine learning with high-resolution satellite imagery to provide new data on socioeconomic indicators of poverty and wealth. Check out the short video below for a quick overview and then read the paper for a more detailed explanation of how it all works.
Fine-grained maps of poverty
Using the final model that has been trained on survey data, we can estimate per capita consumption expenditure for any location where we have daytime satellite imagery. This allows us to create fine-grained maps of poverty—here are some that we put together for Nigeria, Uganda, Tanzania, and Malawi.
Links to the research paper in Science, an accompanying perspective, and a short article describing the project:
- Combining satellite imagery and machine learning to predict poverty
- Fighting poverty with data
- Satellite images can map poverty
- Supplemental information
Recent media coverage about the project:
- The Washington Post: How satellite images are helping find the world's hidden poor
- Mashable: High-resolution satellite photos may help predict poverty
- Reuters: Artificial intelligence can find, map poverty, researchers say
- BBC News: Satellite images used to predict poverty | Radio
- IEEE Spectrum: Fighting poverty with satellite images and machine learning wizardry
- The Verge: Satellite images of Earth help us predict poverty better than ever
- Motherboard, Vice Media: Artificial intelligence is predicting human poverty from space
- The Christian Science Monitor: How satellite images and deep learning can fight global poverty
- New York Times: Satellite images can pinpoint poverty where surveys can't
- Stanford news: Stanford scientists combine satellite data, machine learning to map poverty
- Stanford news: Stanford researchers use dark of night and machine learning to shed light on global poverty
If you're interested in extending our work, here are some links that can get you started:
We gratefully acknowledge support from NVIDIA Corporation through an NVIDIA Academic Hardware Grant, from Stanford’s Global Development and Poverty Initiative, and from the AidData Project at the College of William & Mary. N.J. is supported by the National Defense Science and Engineering Graduate Fellowship Program and S.E. is partially supported by the National Science Foundation.