Global mapping of GDP at 1 km2 using VIIRS nighttime satellite imagery

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 past decades, scientists have proposed many methods for estimating human activity on the Earth’s surface at various spatiotemporal scales using nighttime lights (NTL) data. NTL data and the associated processing methods have been limited their reliability and applicability for systematic measuring and mapping of socioeconomic development. This study utilizes Visible Infrared Imaging Radiometer Suite (VIIRS) NTL and the Isolation Forest machine learning algorithm for more intelligent data processing to capture human activities. We use machine learning and NTL data to map gross domestic product (GDP) at 1 km2. We then use these data products to derive inequality indexes (e.g. Gini coefficients) at nationally aggregate levels. This flexible approach processes the data in an unsupervised manner at various spatial scales. Our assessments show that this method produces accurate sub-national GDP data products for mapping and monitoring human development uniformly across the globe. This repository hosts one zipped geotiff file for the global global GDP (constant 2011 US$) at 1km output of the analysis and the one tabular file (csv) produced by the aggregated results of inequality analysis - NTL-based Gini index and 20:20 ratios.

频繁且快速的空间显性社会经济发展评估，对于在国家与全球层面落实可持续发展目标（Sustainable Development Goals, SDGs）具有关键意义。过去数十年来，学界已提出诸多方法，可借助夜间灯光（Nighttime Lights, NTL）数据在不同时空尺度上估算地球表面的人类活动。然而，夜间灯光数据及其配套处理方法在系统性测量与绘制社会经济发展图景时，其可靠性与适用性仍存在显著局限。本研究采用可见红外成像辐射计套件（Visible Infrared Imaging Radiometer Suite, VIIRS）夜间灯光数据与孤立森林（Isolation Forest）机器学习算法，通过更智能化的数据处理流程捕捉人类活动信号。我们依托机器学习方法与夜间灯光数据，生成了1平方公里分辨率的国内生产总值（Gross Domestic Product, GDP）空间分布图；继而基于该数据产品，在国家聚合尺度上推导得到各类不平等指数（如基尼系数（Gini Coefficient））。该灵活方法以无监督方式在多空间尺度下开展数据处理。经评估验证，本方法可生成精准的次国家层面GDP数据产品，能够支撑全球范围内统一的人类发展状况制图与监测工作。本数据集仓库包含一份压缩格式的地理光栅（GeoTIFF）文件，即本次分析产出的全球1平方公里分辨率GDP数据（以2011年不变价美元计价）；同时包含一份由不平等分析聚合结果生成的逗号分隔值（Comma-Separated Values, CSV）格式表格文件，其中涵盖基于夜间灯光数据计算得到的基尼系数与20:20收入占比。