Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data

Nighttime light (NTL) data have provided invaluable support for estimating gross domestic product (GDP). However, commonly used global-scale NTL data acquired by the visible infrared imaging radiometer suite (VIIRS) aboard the Suomi National Polar-orbiting Partnership (NPP) satellite suffer from rel...

Full description

Saved in:
Bibliographic Details
Main Authors: Weihua Lin, Weixing Xu, Zhaocong Wu, Jiaheng Cao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11059305/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714418919669760
author Weihua Lin
Weixing Xu
Zhaocong Wu
Jiaheng Cao
author_facet Weihua Lin
Weixing Xu
Zhaocong Wu
Jiaheng Cao
author_sort Weihua Lin
collection DOAJ
description Nighttime light (NTL) data have provided invaluable support for estimating gross domestic product (GDP). However, commonly used global-scale NTL data acquired by the visible infrared imaging radiometer suite (VIIRS) aboard the Suomi National Polar-orbiting Partnership (NPP) satellite suffer from relatively coarse spatial resolution (15 arcsec), limiting their potential for fine-scale applications. In this article, we employed a deep-learning-based NTL conditional multiscale downscaling model (NTL-CMDM), incorporating multisource scale factors as conditional constraints, to downscale NPP-VIIRS NTL data (500 m) to a finer spatial scale of 130 m. Furthermore, the effectiveness of downscaled NTL data for county-level GDP estimation was evaluated through comparison with NPP-VIIRS and Luojia1-01 NTL data in 205 Chinese county-level cities with varying economic development levels in the Beijing, Shanghai, and Guangzhou regions. The results show that regressions between GDP and both Total Nighttime Light (TNL) and Nighttime Light Area (NLA) using the downscaled NTL data (<italic>R</italic> &gt; 0.782 and <italic>R</italic> &gt; 0.634) achieve higher fitting accuracy than those using NPP-VIIRS NTL data (<italic>R</italic> &gt; 0.716 and <italic>R</italic> &gt; 0.110), and approach the performance of Luojia1-01 NTL data (<italic>R</italic> &gt; 0.796 and <italic>R</italic> &gt; 0.267). Additionally, the downscaled NTL data improve the accuracy of GDP estimates by reducing the relative error between estimated and statistical GDP compared to NPP-VIIRS NTL data. More importantly, the spatial distribution of GDP estimates derived from the downscaled NTL data more closely aligns with statistical GDP data, reflecting a more realistic geographic pattern. This article demonstrates that the downscaled NTL data generated by NTL-CMDM offer a promising data source for more accurate and fine-scale socioeconomic analysis.
format Article
id doaj-art-a6874fa55f02437183f73ec23de72de9
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-a6874fa55f02437183f73ec23de72de92025-08-20T03:13:42ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118175521756410.1109/JSTARS.2025.358418811059305Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light DataWeihua Lin0https://orcid.org/0009-0002-8999-9983Weixing Xu1https://orcid.org/0009-0001-9209-9516Zhaocong Wu2https://orcid.org/0000-0003-2435-5538Jiaheng Cao3https://orcid.org/0009-0003-3778-3977School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaNighttime light (NTL) data have provided invaluable support for estimating gross domestic product (GDP). However, commonly used global-scale NTL data acquired by the visible infrared imaging radiometer suite (VIIRS) aboard the Suomi National Polar-orbiting Partnership (NPP) satellite suffer from relatively coarse spatial resolution (15 arcsec), limiting their potential for fine-scale applications. In this article, we employed a deep-learning-based NTL conditional multiscale downscaling model (NTL-CMDM), incorporating multisource scale factors as conditional constraints, to downscale NPP-VIIRS NTL data (500 m) to a finer spatial scale of 130 m. Furthermore, the effectiveness of downscaled NTL data for county-level GDP estimation was evaluated through comparison with NPP-VIIRS and Luojia1-01 NTL data in 205 Chinese county-level cities with varying economic development levels in the Beijing, Shanghai, and Guangzhou regions. The results show that regressions between GDP and both Total Nighttime Light (TNL) and Nighttime Light Area (NLA) using the downscaled NTL data (<italic>R</italic> &gt; 0.782 and <italic>R</italic> &gt; 0.634) achieve higher fitting accuracy than those using NPP-VIIRS NTL data (<italic>R</italic> &gt; 0.716 and <italic>R</italic> &gt; 0.110), and approach the performance of Luojia1-01 NTL data (<italic>R</italic> &gt; 0.796 and <italic>R</italic> &gt; 0.267). Additionally, the downscaled NTL data improve the accuracy of GDP estimates by reducing the relative error between estimated and statistical GDP compared to NPP-VIIRS NTL data. More importantly, the spatial distribution of GDP estimates derived from the downscaled NTL data more closely aligns with statistical GDP data, reflecting a more realistic geographic pattern. This article demonstrates that the downscaled NTL data generated by NTL-CMDM offer a promising data source for more accurate and fine-scale socioeconomic analysis.https://ieeexplore.ieee.org/document/11059305/County-level scaledeep learning (DL)downscalinggross domestic product (GDP)nighttime light (NTL) data
spellingShingle Weihua Lin
Weixing Xu
Zhaocong Wu
Jiaheng Cao
Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
County-level scale
deep learning (DL)
downscaling
gross domestic product (GDP)
nighttime light (NTL) data
title Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
title_full Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
title_fullStr Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
title_full_unstemmed Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
title_short Enhancing County-Level GDP Estimation Accuracy With Downscaled NPP-VIIRS Nighttime Light Data
title_sort enhancing county level gdp estimation accuracy with downscaled npp viirs nighttime light data
topic County-level scale
deep learning (DL)
downscaling
gross domestic product (GDP)
nighttime light (NTL) data
url https://ieeexplore.ieee.org/document/11059305/
work_keys_str_mv AT weihualin enhancingcountylevelgdpestimationaccuracywithdownscalednppviirsnighttimelightdata
AT weixingxu enhancingcountylevelgdpestimationaccuracywithdownscalednppviirsnighttimelightdata
AT zhaocongwu enhancingcountylevelgdpestimationaccuracywithdownscalednppviirsnighttimelightdata
AT jiahengcao enhancingcountylevelgdpestimationaccuracywithdownscalednppviirsnighttimelightdata