Combining satellite imagery and machine learning to predict poverty

@article{Jean2016CombiningSI,
  title={Combining satellite imagery and machine learning to predict poverty},
  author={Neal Jean and M. Burke and Sang Michael Xie and W. Matthew Davis and D. Lobell and Stefano Ermon},
  journal={Science},
  year={2016},
  volume={353},
  pages={790 - 794}
}
Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. [...] Key Methodwe show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine…Expand
Predicting City Poverty Using Satellite Imagery
TLDR
This work applies a transfer learning process to the metropolitan areas of five different cities in North and South America, starting from pre-trained convolutional models used for poverty mapping in developing regions, and shows the feasibility of estimating household income from visual satellite features from satellite data. Expand
MAPPING POVERTY IN THE PHILIPPINES USING MACHINE LEARNING, SATELLITE IMAGERY, AND CROWD-SOURCED GEOSPATIAL INFORMATION
Mapping the distribution of poverty in developing countries is essential for humanitarian organizations and policymakers to formulate targeted programs and aid. However, traditional methods forExpand
Poverty from Space: Using High-Resolution Satellite Imagery for Estimating Economic Well-Being
Can features extracted from high spatial resolution satellite imagery accurately estimate poverty and economic well-being? This paper investigates this question by extracting object and textureExpand
Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
TLDR
Deep learning models are shown to be able to explain 70% of the variation in ground-measured village wealth in held-out countries, outperforming previous benchmarks from high-resolution imagery with errors comparable to that of existing ground data. Expand
Employing Night-Time Light Images for Wealth Assessment in India: A Machine Learning Perspective
With the urbanization upsurge and rapid development, India is the country with dense population of urban dwellers. However, disparity among various states in terms of infrastructures, per-capitaExpand
Measuring Changes in Poverty with Deep Learning and Satellite Imagery
Timely and accurate data about local wealth is essential in the global fight against poverty to allocate resources efficiently. In many countries, such data is unavailable or outdated. To close thisExpand
Using Satellite Imagery and Deep Learning to Evaluate the Impactof Anti-Poverty Programs
TLDR
This work infer changes in household wealth based on satellite-derived changes in housing quality and obtain consistent results with the traditional field-survey based approach, providing the first evidence that program evaluations based solely on high-resolution satellite imagery and deep learning methods can be conducted. Expand
Poverty Prediction with Public Landsat 7 Satellite Imagery and Machine Learning
TLDR
This work trains CNN models on free and publicly available multispectral daytime satellite images of the African continent from the Landsat 7 satellite, which has collected imagery with global coverage for almost two decades. Expand
On monitoring development using high resolution satellite images
TLDR
A machine learning based tool for accurate prediction of development and socio-economic indicators from high resolution day-time satellite imagery and shows that the direct regression of asset indicators gives superior R2 scores compared to that of transfer learning through night light data, which is a popular proxy for economic development used world wide. Expand
Lightweight and Robust Representation of Economic Scales from Satellite Imagery
TLDR
This work presents READ, a new approach for obtaining essential spatial representation for any given district from high-resolution satellite imagery based on deep neural networks, which outperforms the state-of-the-art in predicting economic scales, and shows a high potential use for developing countries where district-level economic scales are not known. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping
TLDR
A fully convolutional CNN model is trained to predict nighttime lights from daytime imagery, simultaneously learning features that are useful for poverty prediction, and it is demonstrated that these learned features are highly informative for poverty mapping, even approaching the predictive performance of survey data collected in the field. Expand
Predicting poverty and wealth from mobile phone metadata
TLDR
It is shown that an individual’s past history of mobile phone use can be used to infer his or her socioeconomic status and that the predicted attributes of millions of individuals can accurately reconstruct the distribution of wealth of an entire nation or to infer the asset distribution of microregions composed of just a few households. Expand
Lights, Camera … Income! Illuminating the National Accounts-Household Surveys Debate
GDP per capita and household survey means present conflicting pictures of the rate of economic development in emerging countries. One of the areas in which the national accounts–household surveysExpand
Measuring Economic Growth from Outer Space
TLDR
A statistical framework is developed that uses satellite data on lights growth to augment existing income growth measures, under the assumption that measurement error in using observed light as an indicator of income is uncorrelated with measurementerror in national income accounts. Expand
Using luminosity data as a proxy for economic statistics
  • X. Chen, W. Nordhaus
  • Geography, Medicine
  • Proceedings of the National Academy of Sciences
  • 2011
TLDR
It is found that luminosity has informational value for countries with low-quality statistical systems, particularly for those countries with no recent population or economic censuses. Expand
Deep Learning
TLDR
Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data. Expand
Exploring Alternative Measures of Welfare in the Absence of Expenditure Data
We consider an asset‐based alternative to the standard use of expenditures in defining well‐being and poverty. Our motivation is to see if there exist simpler and less demanding ways to collect dataExpand
Estimating Wealth Effects Without Expenditure Data—Or Tears: An Application To Educational Enrollments In States Of India*
TLDR
This work estimates the relationship between household wealth and children’s school enrollment in India by constructing a linear index from asset ownership indicators, using principal-components analysis to derive weights, and shows that this index is robust to the assets included, and produces internally coherent results. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
A Survey on Transfer Learning
TLDR
The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed. Expand
...
1
2
3
4
...