Precise GDP Spatialization and Analysis in Built-Up Area by Combining the NPP-VIIRS-like Dataset and Sentinel-2...

Spatialization and analysis of the gross domestic product of second and tertiary industries (GDP₂₃) can effectively depict the socioeconomic status of regional development. However, existing studies mainly conduct GDP spatialization using nighttime light data; few studies specifically concentrated on the spatialization and analysis of GDP₂₃ in a built-up area by combining multi-source remote sensing images. In this study, the NPP-VIIRS-like dataset and Sentinel-2 multi-spectral remote sensing images in six years were combined to precisely spatialize and analyze the variation patterns of the GDP₂₃ in the built-up area of Zibo city, China. Sentinel-2 images and the random forest (RF) classification method based on PIE-Engine cloud platform were employed to extract built-up areas, in which the NPP-VIIRS-like dataset and comprehensive nighttime light index were used to indicate the nighttime light magnitudes to construct models to spatialize GDP₂₃ and analyze their change patterns during the study period. The results found that (1) the RF classification method can accurately extract the built-up area with an overall accuracy higher than 0.90; the change patterns of built-up areas varied among districts and counties, with Yiyuan county being the only administrative region with an annual expansion rate of more than 1%. (2) The comprehensive nighttime light index is a viable indicator of GDP₂₃ in the built-up area; the fitted model exhibited an R² value of 0.82, and the overall relative errors of simulated GDP₂₃ and statistical GDP₂₃ were below 1%. (3) The year 2018 marked a significant turning point in the trajectory of GDP₂₃ development in the study area; in 2018, Zhoucun district had the largest decrease in GDP₂₃ at -52.36%. (4) GDP₂₃ gradation results found that Zhangdian district exhibited the highest proportion of high GDP₂₃ (>9%), while the proportions of low GDP₂₃ regions in the remaining seven districts and counties all exceeded 60%. The innovation of this study is that the GDP₂₃ in built-up areas were first precisely spatialized and analyzed using the NPP-VIIRS-like dataset and Sentinel-2 images. The findings of this study can serve as references for formulating improved city planning strategies and sustainable development policies.