Satellite-Based Human Settlement Datasets Inadequately Detect Refugee Settlements: A Critical Assessment at Thirty Refugee Settlements in Uganda

Abstract

Satellite-based broad-scale (i.e., global and continental) human settlement data are essential for diverse applications spanning climate hazard mitigation, sustainable development monitoring, spatial epidemiology and demographic modeling. Many human settlement products report exceptional detection accuracies above 85%, but there is a substantial blind spot in that product validation typically focuses on large urban areas and excludes rural, small-scale settlements that are home to 3.4 billion people around the world. In this study, we make use of a data-rich sample of 30 refugee settlements in Uganda to assess the small-scale settlement detection by four human settlement products, namely, Geo-Referenced Infrastructure and Demographic Data for Development settlement extent data (GRID3-SE), Global Human Settlements Built-Up Sentinel-2 (GHS-BUILT-S2), High Resolution Settlement Layer (HRSL) and World Settlement Footprint (WSF). We measured each product’s areal coverage within refugee settlement boundaries, assessed detection of 317,416 building footprints and examined spatial agreement among products. For settlements established before 2016, products had low median probability of detection and F1-score of 0.26 and 0.24, respectively, a high median false alarm rate of 0.59 and tended to only agree in regions with the highest building density. Individually, GRID3-SE offered more than five-fold the coverage of other products, GHS-BUILT-S2 underestimated the building footprint area by a median 50% and HRSL slightly underestimated the footprint area by a median 7%, while WSF entirely overlooked 8 of the 30 study refugee settlements. The variable rates of coverage and detection partly result from GRID3-SE and HRSL being based on much higher resolution imagery, compared to GHS-BUILT-S2 and WSF. Earlier established settlements were generally better detected than recently established settlements, showing that the timing of satellite image acquisition with respect to refugee settlement establishment also influenced detection results. Nonetheless, settlements established in the 1960s and 1980s were inconsistently detected by settlement products. These findings show that human settlement products have far to go in capturing small-scale refugee settlements and would benefit from incorporating refugee settlements in training and validating human settlement detection approaches.

The politics of pixels: A review and agenda for critical remote sensing

“…Remote sensing research often uses satellite data to examine socioeconomic and environmental issues relevant to critical scholarship. Across the social and environmental sciences, studies by economists, political scientists, geographers, and others have used satellite imagery to expose the presence and/or effects of corruption (Hodler and Raschky, 2014), inequality (Ivan et al, 2020; Zhou et al, 2015), poverty (Briggs, 2018), unequal distribution of public services like electricity (Min et al, 2013; Min and Gaba, 2014), natural disasters (Gillespie et al, 2014), conflict (Agnew et al, 2008; Cederman et al, 2015; Coscieme et al, 2017), refugee movements, settlements, and forced migrations (Ahmed et al, 2019; Van Den Hoek and Friedrich, 2021; Witmer and O’Loughlin, 2011), and mass atrocities and genocide (Marx et al, 2019). Remote sensing has also been used to expose deforestation driven by refugee camps (Ahmed et al, 2019; Hassan et al, 2018), illegal mining (Kyba et al, 2019), gas flaring (Elvidge et al, 2013), and illegal fishing (Hsu et al, 2019; Lumban-Gaol et al, 2020).…”

Unknown risk: assessing refugee camp flood risk in Ethiopia

“…However, there is still significant disagreement between these global datasets in rural areas [13,14], where most refugee camps are located. Previous studies have shown that GP maps underrepresent populations in refugee camps in Uganda [15] and informal settlements in Kenya [16]. However, the utility of global data in the context of refugee flood risk has not yet been examined.…”

Indexing climatic and environmental exposure of refugee camps with a case study in East Africa

“…The need for tailored, systematic vulnerability assessments is arguably the most acute for refugee camp settings, which are broadly characterized by data scarcity or outright absence 13 , 14 . In planning refugee camps or evaluating potential hazards, refugee camp managers and humanitarian organizations make prioritization and logistic decisions on local to regional scales, often with a lack of high quality, high spatial resolution data.…”