Global Mapping of GDP at 1 km2 Using VIIRS Nighttime Satellite Imagery

Wang, Xuantong; Sutton, Paul; Qi, Bingxin

doi:10.3390/ijgi8120580

Cited by 33 publications

(28 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [86] estimate GDP based on VIIRS night-time imagery at 1 × 1 km 2 resolution using GHS-SMOD urban clusters as spatial aggregation units. The authors estimate urban GDP based on VIIRS data and rural GDP based on GHS-POP data.…”

Section: Settlement Societal Impactmentioning

confidence: 99%

Open and Consistent Geospatial Data on Population Density, Built-Up and Settlements to Analyse Human Presence, Societal Impact and Sustainability: A Review of GHSL Applications

et al. 2021

View full text Add to dashboard Cite

This review analyses peer-reviewed scientific publications and policy documents that use built-up density, population density and settlement typology spatial grids from the Global Human Settlement Layer (GHSL) project to quantify human presence and processes for sustainability. Such open and free grids provide detailed time series spanning 1975–2015 developed with consistent approaches. Improving our knowledge of cities and settlements by measuring their size extent, as well as the societal processes occurring within settlements, is key to understanding their impact on the local, regional and global environment for addressing global sustainability and the integrity of planet Earth. The reviewed papers are grouped around five main topics: Quantifying human presence; assessing settlement growth over time; estimating societal impact, assessing natural hazard risk and impact, and generating indicators for international framework agreements and policy documents. This review calls for continuing to refine and expand the work on societal variables that, when combined with essential variables including those for climate, biodiversity and ocean, can improve our understanding of the societal impact on the biosphere and help to monitor progress towards local, regional and planetary sustainability.

show abstract

Section: Settlement Societal Impactmentioning

confidence: 99%

Open and Consistent Geospatial Data on Population Density, Built-Up and Settlements to Analyse Human Presence, Societal Impact and Sustainability: A Review of GHSL Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For instance, Doll, et al [13] employed the DMSP/OLS data to produce the global gridded Purchasing Power Parity GDP map at the spatial resolution of 1-degree and Sutton and Costanza [5] used it to generate the global gridded GDP map at a finer spatial resolution of 1-km. Recently, the Visible Infrared Imaging Radiometer Suite (VIIRS) NTL data have been proved its better performance than DMSP/OLS data in GDP downscaling because of its higher spatial resolution (i.e., 500-m) [18,19]. Although NTL data have been widely applied in GDP downscaling, its shortcomings are obvious.…”

Section: Introductionmentioning

confidence: 99%

“…To handle the limitation of the only usage of NTL data, a large number of geospatial big data (e.g., land use/cover, road network, points of interest (POI), footprint of buildings and human distribution data) have been adopted to combine with NTL data for GDP downscaling [15,16,[18][19][20][21][22]. To deal with the absence of agricultural distribution by NTL data [20,21], the land use/cover was integrated with NTL data to delineate the agricultural and non-agricultural distributions for estimating global 1-km GDP grids in 2015 by Wang, et al [19] and national gridded GDP data [15,23].…”

Section: Introductionmentioning

confidence: 99%

Mapping Gridded Gross Domestic Product Distribution of China Using Deep Learning With Multiple Geospatial Big Data

Chen

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Timely gridded gross domestic product (GDP) data is a fundamental indicator in many applications. It is critical to characterize the complex relationship between GDP and its auxiliary information for accurately estimating gridded GDP. However, few knowledge is available about the performance of deep learning approaches for learning this complex relationship. This paper develops a novel convolutional neural network-based GDP downscaling approach (GDPnet) to transform the statistical GDP data into GDP grids by integrating various geospatial big data. An existing autoencoder-based downscaling approach (Resautonet) is employed to compare with GDPnet. The latest county-level GDP data of China and the multiple geospatial big data are adopted to generate the 1-km gridded GDP data in 2019. Due to the different related auxiliary data of each GDP sector, the two downscaling approaches are first separately built for each GDP sector and then the results are merged to the gridded total GDP data. Experimental results show that the two deep learning approaches had a good predictive power with R 2 over 0.8, 0.9 and 0.92 for the three sectors tested by county-level GDP data. Meanwhile, the proposed GDPnet outperformed the existing Resautonet. The average R 2 of GDPnet was 0.034 higher than that of Resautonet in terms of county-level GDP test data. Furthermore, GDPnet had higher accuracy (R 2 =0.739) than Resautonet (R 2 =0.704) assessed by town-level GDP data. In addition, the proposed GDPnet is faster (about 78% running time) than the Resautonet. Hence, the proposed approach provides a valuable option for generating gridded GDP data.

show abstract

“…It is crucial that GDP data can be spatialized into a fine-scale so that data from different disciplines can be easily integrated (Jia et al., 2015). The gridded GDP data offer the flexibility to perform analysis at various spatial units, such as spatially explicit exposure assessment (Dasgupta et al., 2011; Geiger et al., 2018; Paprotny et al., 2018), and may enable policy planning for the reduction of economic inequality (Wang et al., 2019a), in a more convenient way.…”

Section: Introductionmentioning

confidence: 99%

Mapping China’s regional economic activity by integrating points-of-interest and remote sensing data with random forest

Qian

Zhao

et al. 2020

Environment and Planning B: Urban Analytics and City Science

View full text Add to dashboard Cite

Nighttime light imageries are widely used for mapping the gross domestic product (GDP) over large areas. However, nighttime light imagery is inappropriate to disaggregate agricultural GDP and inadequate to differentiate the GDP from the secondary and tertiary sectors. Points-of-interest, a kind of geospatial big data with geographic locations and textual descriptions of the category, can effectively distinguish industrial and commercial areas, and therefore have the potential to improve the precise GDP mapping from secondary and tertiary sectors. In this study, a machine learning method, random forest, was used to disaggregate the 2010 county-level census GDP data of mainland China to 1 km × 1 km grids. Six Random Forest models were constructed for different economic sectors to explore the non-linear relationships between various geographic predictors and GDP from different sectors. By fusing points-of-interest of varying categories, the spatial distribution of economic activities from the secondary and tertiary sectors was effectively distinguished. Compared to previous studies, the strategy of developing specific Random Forest models for different sectors generated a more reasonable distribution of GDP. Our results highlight the feasibility of using point-of-interest data in disaggregating non-agricultural GDP by exploiting the complementary features of the different data sources.

show abstract

Global Mapping of GDP at 1 km2 Using VIIRS Nighttime Satellite Imagery

Cited by 33 publications

References 41 publications

Open and Consistent Geospatial Data on Population Density, Built-Up and Settlements to Analyse Human Presence, Societal Impact and Sustainability: A Review of GHSL Applications

Open and Consistent Geospatial Data on Population Density, Built-Up and Settlements to Analyse Human Presence, Societal Impact and Sustainability: A Review of GHSL Applications

Mapping Gridded Gross Domestic Product Distribution of China Using Deep Learning With Multiple Geospatial Big Data

Mapping China’s regional economic activity by integrating points-of-interest and remote sensing data with random forest

Contact Info

Product

Resources

About