Date of Award
Africa, Development, GDP, Nighttime light, VIIRS
Frequent and rapid spatially explicit assessment of socioeconomic development is critical for achieving the Sustainable Development Goals (SDGs) at both national and global levels. In the past decades, scientists have proposed many methods for monitoring human activities on the Earth’s surface on various spatiotemporal scales using Defense Meteorological Satellite Program Operational Line System (DMSP-OLS) nighttime lights (NTL) data. However, the DMSP-OLS NTL data and the associated processing methods have limited their reliability and applicability for systematic measuring and mapping of socioeconomic development. This research utilizes Visible Infrared Imaging Radiometer Suite (VIIRS) NTL and the Isolation Forest (iForest) machine learning algorithm for more intelligent data processing to capture human activities. I use machine learning and NTL data to map gross domestic product (GDP) at 1 km2. I then use these data products to derive inequality indexes like GINI coefficients and 20:20 ratios at nationally aggregate levels. I have also conducted a case study based on agricultural production information to estimate subnational GDP in Uganda. This flexible approach processes the data in an unsupervised manner on various spatial scales. Assessments show that this method produces accurate sub-national GDP data for mapping and monitoring human development uniformly in Uganda and across the globe.
Copyright is held by the author. User is responsible for all copyright compliance.
Wang, Xuantong, "Using Multi-Source Data to Assess the Dynamics of Socioeconomic Development in Africa" (2020). Electronic Theses and Dissertations. 1862.
Received from ProQuest