Adaptive non-negative geographically weighted regression for population density estimation based on nighttime light

Hone-Jay Chu, Chen Han Yang, Chelsea C. Chou

Research output: Contribution to journalArticle

Abstract

Nighttime light imagery provides a perspective for studying urbanization and socioeconomic changes. Traditional global regression models have been applied to explore the nonspatial relationship between nighttime lights and population density. In this study, geographically weighted regression (GWR) identifies the spatially varying relationships between population density and nighttime lights in mainland China. However, the rural population does not have a strong relationship with remote-sensing spectral features. The rural population estimation using nighttime light data alone easily identifies meaningless negative population density in the rural area. This study proposes an adaptive non-negative GWR (ANNGWR) to explore the spatial pattern of population density by using nonnegative constraints with an adaptive bandwidth of kernel. The ANNGWR solves the negative value of population density and serious overestimation of the western boundary. The result shows that the ANNGWR provides the best goodness-of-fit compared with linear regression and original GWR. This study applies Moran's I index to prove that the ANNGWR substantially decreases the spatial autocorrelation of the model residual. The model offers a robust and effective approach for estimating the spatial patterns of regional population density solely on the basis of nighttime light imagery.

Original languageEnglish
Article number26
JournalISPRS International Journal of Geo-Information
Volume8
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

population density
regression
rural population
imagery
population estimation
Autocorrelation
Linear regression
socioeconomic development
Remote sensing
autocorrelation
urbanization
rural area
Bandwidth
remote sensing
China

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Computers in Earth Sciences
  • Earth and Planetary Sciences (miscellaneous)

Cite this

@article{3624156407ad4971baf0159d1cc3c4b3,
title = "Adaptive non-negative geographically weighted regression for population density estimation based on nighttime light",
abstract = "Nighttime light imagery provides a perspective for studying urbanization and socioeconomic changes. Traditional global regression models have been applied to explore the nonspatial relationship between nighttime lights and population density. In this study, geographically weighted regression (GWR) identifies the spatially varying relationships between population density and nighttime lights in mainland China. However, the rural population does not have a strong relationship with remote-sensing spectral features. The rural population estimation using nighttime light data alone easily identifies meaningless negative population density in the rural area. This study proposes an adaptive non-negative GWR (ANNGWR) to explore the spatial pattern of population density by using nonnegative constraints with an adaptive bandwidth of kernel. The ANNGWR solves the negative value of population density and serious overestimation of the western boundary. The result shows that the ANNGWR provides the best goodness-of-fit compared with linear regression and original GWR. This study applies Moran's I index to prove that the ANNGWR substantially decreases the spatial autocorrelation of the model residual. The model offers a robust and effective approach for estimating the spatial patterns of regional population density solely on the basis of nighttime light imagery.",
author = "Hone-Jay Chu and Yang, {Chen Han} and Chou, {Chelsea C.}",
year = "2019",
month = "1",
day = "1",
doi = "10.3390/ijgi8010026",
language = "English",
volume = "8",
journal = "ISPRS International Journal of Geo-Information",
issn = "2220-9964",
publisher = "MDPI AG",
number = "1",

}

Adaptive non-negative geographically weighted regression for population density estimation based on nighttime light. / Chu, Hone-Jay; Yang, Chen Han; Chou, Chelsea C.

In: ISPRS International Journal of Geo-Information, Vol. 8, No. 1, 26, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive non-negative geographically weighted regression for population density estimation based on nighttime light

AU - Chu, Hone-Jay

AU - Yang, Chen Han

AU - Chou, Chelsea C.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Nighttime light imagery provides a perspective for studying urbanization and socioeconomic changes. Traditional global regression models have been applied to explore the nonspatial relationship between nighttime lights and population density. In this study, geographically weighted regression (GWR) identifies the spatially varying relationships between population density and nighttime lights in mainland China. However, the rural population does not have a strong relationship with remote-sensing spectral features. The rural population estimation using nighttime light data alone easily identifies meaningless negative population density in the rural area. This study proposes an adaptive non-negative GWR (ANNGWR) to explore the spatial pattern of population density by using nonnegative constraints with an adaptive bandwidth of kernel. The ANNGWR solves the negative value of population density and serious overestimation of the western boundary. The result shows that the ANNGWR provides the best goodness-of-fit compared with linear regression and original GWR. This study applies Moran's I index to prove that the ANNGWR substantially decreases the spatial autocorrelation of the model residual. The model offers a robust and effective approach for estimating the spatial patterns of regional population density solely on the basis of nighttime light imagery.

AB - Nighttime light imagery provides a perspective for studying urbanization and socioeconomic changes. Traditional global regression models have been applied to explore the nonspatial relationship between nighttime lights and population density. In this study, geographically weighted regression (GWR) identifies the spatially varying relationships between population density and nighttime lights in mainland China. However, the rural population does not have a strong relationship with remote-sensing spectral features. The rural population estimation using nighttime light data alone easily identifies meaningless negative population density in the rural area. This study proposes an adaptive non-negative GWR (ANNGWR) to explore the spatial pattern of population density by using nonnegative constraints with an adaptive bandwidth of kernel. The ANNGWR solves the negative value of population density and serious overestimation of the western boundary. The result shows that the ANNGWR provides the best goodness-of-fit compared with linear regression and original GWR. This study applies Moran's I index to prove that the ANNGWR substantially decreases the spatial autocorrelation of the model residual. The model offers a robust and effective approach for estimating the spatial patterns of regional population density solely on the basis of nighttime light imagery.

UR - http://www.scopus.com/inward/record.url?scp=85061121070&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061121070&partnerID=8YFLogxK

U2 - 10.3390/ijgi8010026

DO - 10.3390/ijgi8010026

M3 - Article

VL - 8

JO - ISPRS International Journal of Geo-Information

JF - ISPRS International Journal of Geo-Information

SN - 2220-9964

IS - 1

M1 - 26

ER -