Embedded Files
Below, you'll find my peer-reviewed academic articles and working papers. For questions on any specific publication, feel free to contact me.
Published papers
The Feminization U in Egypt: Economic Development, Structural Change, and Female Labour Force Decline
Suleiman, H. (2025). The Feminization U in Egypt: Economic Development, Structural Change, and Female Labour Force Decline. The Journal of Development Studies, 1-28. https://doi.org/10.1080/00220388.2025.2563854
Abstract: Female labour force participation (FLFP) has declined in Egypt over the past three decades, despite rapid progress in female education, a phenomenon often referred to as the ‘MENA paradox’. This paper investigates whether this decline is part of a U-shaped trajectory that is associated with economic development and structural change, consistent with the Feminization U hypothesis. The paper leverages a novel provincial dataset spanning 1992–2022, and employs static, dynamic, and spatial regression methods alongside a decomposition analysis. The results reveal four key findings. First, FLFP follows a U-shaped pattern in relation to economic development, marked by a sharp decline followed by a modest recovery. Second, structural change—particularly shifts in agriculture, manufacturing, and white-collar services—is positively associated with FLFP growth. Third, only manufacturing growth exhibits spatial spillover effects on neighbouring provinces’ FLFP. Fourth, up to 2017, most of the change in female employment stemmed from labour movement out of agriculture and into services, and increased concentration of women in services. These findings underscore the potential of targeted sectoral policies to support FLFP growth. Moreover, results of disaggregated age cohorts highlight the importance of maternity and childcare support in boosting women’s labour market participation in Egypt.
Predicting Subnational GDP in Vietnam with Remote Sensing Data: a machine learning approach (2025)
Suleiman, H. & Nguyen, M. T. T. & Mendez, C. (2025). Predicting Subnational GDP in Vietnam with Remote Sensing Data: a machine learning approach. Letters in Spatial and Resource Sciences, 18-5. https://doi.org/10.1007/s12076-025-00397-z
Abstract: Official subnational Gross Domestic Product (GDP) data in Vietnam has been available only since 2010, hindering the analysis of long-term dynamics of local development. Based on remote sensing data and machine learning methods, we construct a subnational GDP indicator for the 63 Vietnamese provinces from 1992 to 2009. Specifically, we rely on nighttime lights, agricultural land, and climate datasets and employ six machine learning algorithms to construct the GDP dataset. We compare the accuracy of several machine learning algorithms and compare the predicted subnational GDP of the best-performing algorithm using two nighttime lights datasets. We show consistent predictions using both datasets, and construct the subnational GDP dataset using the NTL data with the longer temporal coverage. This new dataset allows researchers and policymakers to analyze long-term economic trends at the subnational level in Vietnam, filling a critical gap in historical economic data.
Explore an interactive map of nighttime lights in Vietnam on Google Earth Engine here.
Illuminating the Nile: estimating subnational GDP in Egypt using nighttime lights and machine learning (2024)
Suleiman, H. (2024). Illuminating the Nile: estimating subnational GDP in Egypt using nighttime lights and machine learning. GeoJournal, 89(3), 1-19. https://doi.org/10.1007/s10708-024-11106-6
Abstract: Egypt has been reporting several subnational socioeconomic indicators for more than three decades. However, utilizing these valuable datasets for monitoring long temporal trends in local development and inequalities has been hindered by the lack of a key indicator, the Gross Domestic Product (GDP), which was only reported subnationally starting 2013. This paper aims to address this data gap, by employing satellite-generated nighttime lights (NTL) and machine learning, to estimate subnational GDP in Egypt from 1992 to 2012. The paper relies on the harmonized global nighttime lights dataset that extends from 1992 to 2021, to carry out a twofold process. First, it validates NTL as a useful proxy for subnational economic activity in Egypt using econometric methods; then it estimates missing GDP using machine learning algorithms. Results show that the concentration of nearly the entire Egyptian population densely around the Nile River is challenging to nighttime lights accuracy; however, upon accounting for population density and agricultural activity, NTL could serve as a valuable proxy for subnational GDP in Egypt, and consequently a coherent GDP dataset is constructed since 1992.
Explore an interactive map of nighttime lights in Egypt on Google Earth Engine here.
Working papers
Regional Economic Inequality in Egypt: A Kuznets curve, convergence, or shock-driven decline?
Suleiman, H. & Chen, Y. (202X). Regional Economic Inequality in Egypt: A Kuznets curve, convergence, or shock-driven decline?
Abstract: This article studies regional (inter-provincial) economic inequality in Egypt to revisit the ’Arab inequality puzzle', which refers to the popular perception of rising inequality that contradicts official data. The article leverages provincial output per capita data to carry out four objectives. First, Gini and Theil indices are measured from 1992 to 2022; second, the presence of a Kuznets curve is investigated; third, sigma, beta, and club convergence among provinces are tested; and fourth, the causal effects of shocks from a recent structural adjustment programme and COVID-19 on regional inequality are examined. The findings show that regional inequality in Egypt has been high and has consistently risen from the mid-1990s to the mid-2010s. It declined in recent years, exhibiting an inverted U-shaped relationship with economic development, consistent with the Williamson-Kuznets hypothesis. However, there is no evidence of overall inter-provincial beta convergence, but only convergence within multiple clubs. Instead, the recent decline in inequality was caused by the shocks, and was temporary in levels, after which inequality resumed its growing trend, with an even faster pace.
The Unequal Effect of Structural Adjustment on Female Labour Force Participation in Egypt: provincial evidence from levels of education and urban-rural divide
Abstract: Using a novel provincial-level panel dataset spanning 1997-2022, this paper measures the effect of the recent 2016 structural adjustment program on female labor force participation (FLFP) in Egypt. The analysis reveals that the program has had an overall negative effect on FLFP, with unequal magnitude across educational levels and urban-rural divides. In particular, women with less than intermediate (secondary) education and those in rural areas experienced the most pronounced declines in labour force participation following the program's implementation.
Higher-Quality Nighttime Lights, Economic Activity, and Spatial Inequality: evidence from developed and developing countries
Mendez, C. & Chen, Y. & Suleiman, H. Higher-Quality Nighttime Lights, Economic Activity, and Spatial Inequality: evidence from developed and developing countries.
Abstract: Satellite nighttime lights (NTL) are becoming a popular resource for assessing economic performance across countries and subnational regions. However, most economic studies use outdated and imprecise data from the Defense Meteorological Satellite Program (DMSP). This study compares the predictive economic content of nightlight luminosity from the new Visible Infrared Imaging Radiometer Suite (VIIRS) and other newly processed images from the Defense Meteorological Satellite Program (DMSP). Specifically, we analyze the predictive performance of NTL luminosity across 139 countries and 1,557 subnational regions during the 2013-2019 period. The main findings of our multi-country and multi-region analyses are threefold. First, consistent with the findings of the single-country analysis, NTL luminosity predicts economic differences between economies better than economic changes within a single economy over time. Second, while both VIIRS and DMSP luminosity indicators perform similarly at the national level, VIIRS excels in subnational analyses, especially in developing countries. Third, in subnational regions of developing countries, VIIRS luminosity data more accurately characterizes economic inequality than the new DMSP nightlight indicators. Overall, these results illustrate how recent geospatial technologies can advance our understanding of economic activity.
Improving Nighttime Lights Prediction of Economic Activity over-time: evidence using global data and machine learning
Suleiman, H. & Chen, Y. & Mendez, C. Improving Nighttime Lights Prediction of Economic Activity over-time: evidence using global data and machine learning.
Abstract: Nighttime lights (NTL) are evidently a poorer predictor of temporal changes in economic activity, compared to cross-sectional changes. Using NTL data on their own as a proxy for economic output time-series could thus prove problematic. In this study, we build a model with higher predictive power of economic output time-series by augmenting NTL with additional datasets, mainly on population and agriculture, and leveraging machine learning algorithms to improve predictive accuracy. The study uses national-level gross domestic product (GDP) for 149 countries during the 2013-2019 period, as a benchmark to validate the temporal performance of the Visible Infrared Imaging Radiometer 4 Suite (VIIRS) nighttime lights, and the control variables. We find that adding control variables improves the predictive accuracy of the model, and that using machine learning algorithms instead of conventional regression further improves the accuracy as well, hence enabling efficient prediction of economic activity time-series using nighttime lights.
Page updated
Google Sites
Report abuse