LAUSR

ABSTRACT Poverty continues to pose significant global challenges. Analyzing poverty distribution is pivotal for identifying spatial and demographic disparities, informing targeted policy interventions, and fostering inclusive and equitable development. The absence of a worldwide pixel-scale time-series poverty dataset has hampered effective policy formulation. To address this gap, we employ the international wealth index (IWI) derived from household survey data to represent poverty levels. Subsequently, a random forest regression model was constructed, with IWI serving as the dependent variable and representative features extracted from nighttime lights, land cover, digital elevation model, and World Bank statistical data serving as independent variables. This yielded a global map of the IWI for low- and middle-income nations at a 10-km resolution spanning 2005 to 2020. The model demonstrated robust performance with an R2 value of 0.74. Over the studied period, areas and populations with IWI ≤ 50 decreased by 8.85% and 16.17%, indicating a steady decrease in global poverty regions. Changes in the IWI at the pixel scale indicate that areas closer to cities have faster growth rates. Furthermore, our poverty estimation models present a novel method for real-time pixel-scale poverty assessments. This study provides valuable insights into the dynamics of poverty, both globally and nationally.