The 1992–2024 Global NPP-VIIRS-like Nighttime Light Annual Data from Deep Learning Super-Resolution Reconstruction
Journal of Remote Sensing · 01.01.2026 · 6
DOI: 10.34133/remotesensing.0874 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Remote Sensing, online erschienen am 31.03.2026. Verfasst von Zuoqi Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province.
Abstract (Originalsprache)
Nighttime light (NTL) data have emerged as a valuable tool for urbanization monitoring and socioeconomic evaluation. However, due to the Defense Meteorological Satellite Program Operational Line Scanning System NTL data having worse spatial resolution, shorter temporal coverage, and less radiometric sensitivity than the Suomi National Polar-orbiting Partnership’s Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) NTL data, calibrating these two widely used NTL datasets into one reference becomes crucial for long-term NTL applications. Totally, an Attention U-Net with Skip connection for Super Resolution model was developed to reconstruct longer NPP-VIIRS-like NTL data (Version 2) from 1992 to 2024 than the Version 1 NTL data, which is from 2000 to 2024. Meanwhile, the Version 2 NTL data also have good accuracy of 0.66, 0.91, and 0.93 at the pixel, city, and provincial levels, respectively, as well as a consistent spatial distribution, which is better than other calibrated long-term NTL datasets. By using a triple check of temporal consistency, the Version 2 NTL data can detect global, regional, and national economic growth and shocks and are helpful for estimating economic levels and census data. In general, our product is very consistent with the NPP-VIIRS NTL data and is better than other relative NTL datasets, especially within the Defense Meteorological Satellite Program Operational Line Scanning System saturation regions. In addition, it provides more opportunity to monitor the time series of urbanization process and socioeconomic development with a higher accuracy.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Fujian Province
Zitieren
APA
Chen, Z., Liao, L., Wang, C., Shi, K., & Yu, B. (2026). The 1992–2024 Global NPP-VIIRS-like Nighttime Light Annual Data from Deep Learning Super-Resolution Reconstruction. Journal of Remote Sensing, 6. https://doi.org/10.34133/remotesensing.0874
Vancouver
Chen Z, Liao L, Wang C, Shi K, Yu B. The 1992–2024 Global NPP-VIIRS-like Nighttime Light Annual Data from Deep Learning Super-Resolution Reconstruction. Journal of Remote Sensing. 2026;6. doi:10.34133/remotesensing.0874
BibTeX
@article{Chen2026,
author = {Chen, Zuoqi and Liao, Lingxing and Wang, Congxiao and Shi, Kaifang and Yu, Bailang},
title = {The 1992–2024 Global NPP-VIIRS-like Nighttime Light Annual Data from Deep Learning Super-Resolution Reconstruction},
journal = {Journal of Remote Sensing},
year = {2026},
volume = {6},
doi = {10.34133/remotesensing.0874}
}
EUVIMED