Optimisation Model for Spatialisation of Population Based on Human Footprint Index Correction DOI Creative Commons

Dongfeng Ren,

Xin Qiu,

Chun Dong

и другие.

ISPRS International Journal of Geo-Information, Год журнала: 2024, Номер 13(12), С. 429 - 429

Опубликована: Ноя. 29, 2024

The availability of high-precision population distribution data is crucial for urban planning and the optimal allocation resources. To address limitations random forest model in addressing spatial heterogeneity during spatialisation potential features to be lost or distorted between scale changes, which can result excessive error, this study proposes an optimised based on modification Human Footprint Index (HFI). A hierarchical feature coding method used reduce cross-scale errors. (HFI) was then constructed by selecting a total seven characteristic factors five areas, namely, electricity, land use intensity, built environment, transport accessibility, level economic development, corrects predictions. resulting dataset Suzhou demonstrates following: (1) R2 HFI-corrected reaches 92.8%, with accuracy 92.3% medium-density significantly outperforming single (81.6%) WorldPop (69.3%) overall accuracy; (2) Pearson correlation coefficient 0.96, higher than that (0.94) RFPop (0.91), further validating model’s (3) reduces errors, improving percentage points.

Язык: Английский

Supply and demand analysis of urban thermal environments regulation services from an accessibility perspective: A coupled thermal risk and green space cooling assessment model DOI
Zeqi Wang, Yikai Liu, Tianyu Wang

и другие.

Urban Climate, Год журнала: 2025, Номер 60, С. 102356 - 102356

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0

How to Consider Human Footprints to Assess Human Disturbance: Evidence from Urban Agglomeration in the Yellow River Basin DOI Creative Commons
Shun Luo, Xiangxue Li, Jie Yang

и другие.

Land, Год журнала: 2024, Номер 13(12), С. 2163 - 2163

Опубликована: Дек. 12, 2024

Natural processes are substantially impacted by human activity, and assessing activity has significant ramifications for regional ecological conservation. The study developed an extended footprint (HF) assessment model based on the theory of effects pressures to evaluate disturbances in urban agglomerations Yellow River Basin using data from 2005 2020, revealing spatiotemporal pattern region. conclusions show that HF value agglomeration steadily increased primarily driven mining intensity road construction. High areas concentrated south-central region, with a tendency spread outward. Medium mainly distributed eastern part area, spatial distribution increases year year, extending outward center area. moderately low mostly found mountainous northwest. Among Basin, Central Plains UA Shandong Peninsula most heavily affected disturbance. instructive high-quality development Basin.

Язык: Английский

Процитировано

1

Optimisation Model for Spatialisation of Population Based on Human Footprint Index Correction DOI Creative Commons

Dongfeng Ren,

Xin Qiu,

Chun Dong

и другие.

ISPRS International Journal of Geo-Information, Год журнала: 2024, Номер 13(12), С. 429 - 429

Опубликована: Ноя. 29, 2024

The availability of high-precision population distribution data is crucial for urban planning and the optimal allocation resources. To address limitations random forest model in addressing spatial heterogeneity during spatialisation potential features to be lost or distorted between scale changes, which can result excessive error, this study proposes an optimised based on modification Human Footprint Index (HFI). A hierarchical feature coding method used reduce cross-scale errors. (HFI) was then constructed by selecting a total seven characteristic factors five areas, namely, electricity, land use intensity, built environment, transport accessibility, level economic development, corrects predictions. resulting dataset Suzhou demonstrates following: (1) R2 HFI-corrected reaches 92.8%, with accuracy 92.3% medium-density significantly outperforming single (81.6%) WorldPop (69.3%) overall accuracy; (2) Pearson correlation coefficient 0.96, higher than that (0.94) RFPop (0.91), further validating model’s (3) reduces errors, improving percentage points.

Язык: Английский

Процитировано

0