A review of machine learning and satellite imagery for poverty prediction: Implications for development research and applications

Abstract

The field of artificial intelligence is seeing the increased application of satellite imagery to analyse poverty in its various manifestations. This nascent but rapidly growing intersection of scholarship holds the potential to help us better understand poverty by leveraging big data and recent advances in machine vision. In this study, we statistically analyse the literature in the expanding field of welfare and poverty predictions from the combination of machine learning and satellite imagery. Here, we apply an integrative review method to extract key data on factors related to the predictive power of welfare. We found that the most important factors correlated to the predictive power of welfare are the number of pre‐processing steps employed, the number of datasets used, the type of welfare indicator targeted and the choice of AI model. Studies that used stock measure indicators (assets) as targets achieved better performance—17 percentage points higher—in predicting welfare than those that targeted flow measures (income and consumption) ones. Additionally, we found that the combination of machine learning and deep learning significantly increases predictive power—by as much as 15 percentage points—compared to using either alone. Surprisingly, we found that the spatial resolution of the satellite imagery used is important but not critical to the performance as the relationship is positive but not statistically significant. These findings have important implications for future research in this domain and for anyone aspiring to use the methodology.

The multiscale nexus among land use-land cover changes and water quality in the Suquía River Basin, a semi-arid region of Argentina

“…The seasonality could affect the results related to the water quality and, except for sample sites 7, 9, and 10, the cold season had a better WQI than the warm season. These results are in disagreement with different authors who suggest that during the wet season (local summer), rainfall could cause better surface water quality since it naturally dilutes the pollutants, thus decreasing pollutant concentrations and improving water quality 48 , 49 . Particularly, during the Summer, WQI at SS11 drops concerning SS10.…”

“…The thematic maps were generated through machine learning based on a methodological and algorithmic decision tree. This technique is highly effective in satellite data analysis due to its ability to process large amounts of information and detect complex patterns 46 , and LULC time-series mapping has a great potential to analyze satellite data 47 , 48 . The final LULC thematic maps include seven classes: forest, shrubland, grassland, cropland, built-up, bare soil (including sparse vegetation), and permanent water bodies.…”

A Scoping Review of Earth Observation and Machine Learning for Causal Inference: Implications for the Geography of Poverty

“…At the same time, outside of the field of human geography, rapid advancements in AI and machine learning (ML) have augmented research in numerous domains, from physics (Karniadakis et al, 2021), health (Kino et al, 2021), economics (Athey et al, 2018) and beyond. While there has been some progress in combining Earth Observation (EO) data such as satellite imagery with machine learning methods such as convolutional neural networks (CNN) and Vision Transformers (ViTs) in the study of spatial poverty (Hall et al, 2023), social geographers have only relatively recently begun to examine the potentially far-ranging implications of the synergy between ML-EO. These technologies have the potential to contribute to our understanding of the geographies of poverty-but there are also numerous challenges requiring exploration.…”

Grid-Scale Poverty Assessment by Integrating High-Resolution Nighttime Light and Spatial Big Data—A Case Study in the Pearl River Delta

“…Poverty is a global social problem, and poverty eradication is the first of the 17 sustainable development goals proposed by the United Nations [1][2][3][4][5]. The issue of poverty is particularly prominent in China.…”