Poverty maps are essential tools for governments and NGOs to track socioeconomic changes and adequately allocate infrastructure and services in places in need.
This interactive map tool is for exploring and comparing the inferred wealth in Sierra Leone, Uganda, and Hungary from multiple machine learning models. These models leverage seven independent and freely available feature sources based on satellite images, and metadata features collected via online crowd-sourcing and social media.
In these maps, we use different proxies of wealth. In the African countries we leverage the International Wealth Index (IWI) which ranges from 0 to 100 indicating households with the lowest and highest socioeconomic class respectively. In Hungary, the socioeconomic indicator is inferred from housing price per square meter as a proxy of wealth. Households with score close to 0 correspond to the lowest socioeconomic class, while households with scores close to 3 are representing the highest socioeconomic class.
On the maps, each location contains multiple households and is colored by the mean wealth. Most features were extracted in 2022 and 2023. In the prediction view, models were trained with ground-truth data from the last two available surveys (2016 and 2018-19) in the African countries, and from a 2018 house listing prices in Hungary. Note that the comparison tab is only available for the African countries. Here, the left panel was trained on 2016 and the right on 2018-19.
Models
Feature-based: the CatBoost model, is trained with metadata features (i.e., Demographics, Mobility, Population, Nightlight intensity, Antennas, and Infrastructure).
Image-based: the Convolutional Neural Network model with daylight satellite images.
Combined: uses all features.
Weighted: “weighted samples” applied during training to correct for wealth imbalance.
Augmented: “offline augmentation” applied to correct for small samples.
Learn more
Citation
Lisette Espín-Noboa, János Kertész, and Márton Karsai. 2023. Interpreting wealth distribution via poverty map inference using multimodal data. In Proceedings of the ACM Web Conference 2023 (WWW ’23), April 30-May 4, 2023, Austin, TX, USA. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/3543507.3583862