Remote Sensing-based Socioeconomic Analysis using Task-driven Transfer Learning and Regression

The economic status of each country varies; some countries are well developed while some are underdeveloped. A lower economic status in any place in the world can lead to hunger, malnutrition, and low life expectancy, especially for children and the older generation. For instance, in Africa, most people live below the international poverty line of 1.25 US dollars per day, according to the World Bank Group. One way of solving this problem is through collecting data and building intelligent models to automatically detect the low economic regions so the organizations, like The United Nations Development Program (UNDP), can allocate vital support systems to save the people there from the severity and help them lead a better life. Unfortunately, obtaining such data through manual surveys takes too long and requires a lot of resources. Thus, this work aims to provide an efficient solution to this problem. It analyzes the socioeconomic status of the underdeveloped regions, primarily a few selected African countries, by using remote sensing (RS), multimodal data exploitation, machine learning, transfer learning, and computer vision technologies. The proposed framework can make accurate prediction on a particular geographic region's standard of living (wealth index) based on the distribution of nightlight intensity that is observed via satellite remote sensing. Exhaustive experiments are carried out using data from the National Oceanic And Atmospheric Administration (NOAA), Demographic and Health Survey (DHS), and Google Static Maps. The experimental results verify that the proposed framework can be used as an effective alternative to the conventional approaches for socioeconomic analysis.