Spatial Analysis of Urban Expansion and Energy Consumption Using Nighttime Light Data: A Comparative Study of Google Earth Engine and Traditional Methods for Improved Living Spaces DOI Creative Commons

Thidapath Anucharn,

Phongsakorn Hongpradit,

Niti Iamchuen

et al.

ISPRS International Journal of Geo-Information, Journal Year: 2025, Volume and Issue: 14(4), P. 178 - 178

Published: April 18, 2025

This study employs a dual methodological approach, integrating Google Earth Engine (GEE) and unsupervised classification (UNSUP) to analyze urban expansion patterns in Chiang Mai province using nighttime light imagery. The research utilizes Visible Infrared Imaging Radiometer Suite (VIIRS) satellite data from 2014 2023 assess growth dynamics. primary objectives are (1) evaluate the performance of GEE UNSUP processing, (2) validate area accuracy multiple assessment metrics, (3) examine relationship between intensity electricity consumption through Pearson’s correlation analysis, thereby establishing patterns. framework incorporates dual-threshold mechanism K-means clustering traditional geospatial software. Accuracy is conducted 256 stratified random sampling points, complemented by land use cover (LULC) for ground truth validation. results indicate that consistently outperforms UNSUP, achieving overall values 0.80 0.82, compared 0.73 0.76 UNSUP. Kappa coefficient ranges 0.60 0.65, whereas demonstrates lower agreement with (0.44–0.52). Furthermore, both approaches reveal significant intensity, R2 = 0.9744 0.9759 confirming efficacy nocturnal illumination monitoring. findings areas have expanded approximately 70% over period. contributes field demonstrating effectiveness integrated methodologies development analysis. offer planners policymakers critical insights sustainable management decision-making.

Language: Английский

Urban land use function prediction method based on RF and cellular automaton model DOI Creative Commons

Wenjun Song,

Min Ling

Computational Urban Science, Journal Year: 2025, Volume and Issue: 5(1)

Published: Feb. 21, 2025

Abstract To accurately grasp the dynamic changes of urban land use and solve difficulties challenges in predicting functions at present, this study integrates interest point data open street map through kernel density estimation technology. Moreover, also random forest algorithm cellular automaton model, finally proposes a new function prediction method based on model. The experiment results show that comprehensive precision Kappa coefficient calculated by research reach 81.88% 0.71, separately, verifying validity way. indicate number squares required for road transportation, industrial land, public services, residential green squares, commercial service Hulunbuir City 2030 is expected to 2000, 3889, 2591, 9280, 2696, 8988, respectively. This provides scientific basis future planning. sum up, raised has high applicability accuracy distribution pattern functional regions, important instructing significance planning, optimal assignment resources, continuous expanding urbanization.

Language: Английский

Citations

0
Spatial Analysis of Urban Expansion and Energy Consumption Using Nighttime Light Data: A Comparative Study of Google Earth Engine and Traditional Methods for Improved Living Spaces DOI Creative Commons

Thidapath Anucharn,

Phongsakorn Hongpradit,

Niti Iamchuen

et al.

ISPRS International Journal of Geo-Information, Journal Year: 2025, Volume and Issue: 14(4), P. 178 - 178

Published: April 18, 2025

This study employs a dual methodological approach, integrating Google Earth Engine (GEE) and unsupervised classification (UNSUP) to analyze urban expansion patterns in Chiang Mai province using nighttime light imagery. The research utilizes Visible Infrared Imaging Radiometer Suite (VIIRS) satellite data from 2014 2023 assess growth dynamics. primary objectives are (1) evaluate the performance of GEE UNSUP processing, (2) validate area accuracy multiple assessment metrics, (3) examine relationship between intensity electricity consumption through Pearson’s correlation analysis, thereby establishing patterns. framework incorporates dual-threshold mechanism K-means clustering traditional geospatial software. Accuracy is conducted 256 stratified random sampling points, complemented by land use cover (LULC) for ground truth validation. results indicate that consistently outperforms UNSUP, achieving overall values 0.80 0.82, compared 0.73 0.76 UNSUP. Kappa coefficient ranges 0.60 0.65, whereas demonstrates lower agreement with (0.44–0.52). Furthermore, both approaches reveal significant intensity, R2 = 0.9744 0.9759 confirming efficacy nocturnal illumination monitoring. findings areas have expanded approximately 70% over period. contributes field demonstrating effectiveness integrated methodologies development analysis. offer planners policymakers critical insights sustainable management decision-making.

Language: Английский

Citations

0