Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood

This research aimed to develop an alternative method for estimating ambient population density at the neighborhood scale by utilizing a simple and universally available dataset. Physical environment data from GIS & OSM databases, basic statistics, and population density data from Mobile Spatial...

Full description

Saved in:
Bibliographic Details
Main Authors: Pasit Rojradtanasiri, Junko Tamura, Masami Kobayashi
Format: Article
Language:English
Published: Taylor & Francis Group 2024-11-01
Series:Journal of Asian Architecture and Building Engineering
Subjects:
Online Access:http://dx.doi.org/10.1080/13467581.2024.2428262
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124647494451200
author Pasit Rojradtanasiri
Junko Tamura
Masami Kobayashi
author_facet Pasit Rojradtanasiri
Junko Tamura
Masami Kobayashi
author_sort Pasit Rojradtanasiri
collection DOAJ
description This research aimed to develop an alternative method for estimating ambient population density at the neighborhood scale by utilizing a simple and universally available dataset. Physical environment data from GIS & OSM databases, basic statistics, and population density data from Mobile Spatial Statistics were combined to train tree-based Machine Learning models. The experiment resulted in an XGBoost model using 16 features capable of estimating ambient population density across three classes of outcome with 75.9% accuracy. The trained models were analyzed and visualized using SHAP and Partial Dependence Plot techniques to reveal feature importance and their threshold values. The study concludes that physical features can be effectively used as predictors of ambient population density and highlights areas for further investigation.
format Article
id doaj-art-51ebaeba32744b8eb5d13d1e50b9c8f2
institution Kabale University
issn 1347-2852
language English
publishDate 2024-11-01
publisher Taylor & Francis Group
record_format Article
series Journal of Asian Architecture and Building Engineering
spelling doaj-art-51ebaeba32744b8eb5d13d1e50b9c8f22024-12-13T15:19:01ZengTaylor & Francis GroupJournal of Asian Architecture and Building Engineering1347-28522024-11-010011610.1080/13467581.2024.24282622428262Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhoodPasit Rojradtanasiri0Junko Tamura1Masami Kobayashi2Meiji UniversityMeiji UniversityMeiji UniversityThis research aimed to develop an alternative method for estimating ambient population density at the neighborhood scale by utilizing a simple and universally available dataset. Physical environment data from GIS & OSM databases, basic statistics, and population density data from Mobile Spatial Statistics were combined to train tree-based Machine Learning models. The experiment resulted in an XGBoost model using 16 features capable of estimating ambient population density across three classes of outcome with 75.9% accuracy. The trained models were analyzed and visualized using SHAP and Partial Dependence Plot techniques to reveal feature importance and their threshold values. The study concludes that physical features can be effectively used as predictors of ambient population density and highlights areas for further investigation.http://dx.doi.org/10.1080/13467581.2024.2428262neighborhood planningmachine learningcorrelation analysisambient populationgis
spellingShingle Pasit Rojradtanasiri
Junko Tamura
Masami Kobayashi
Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
Journal of Asian Architecture and Building Engineering
neighborhood planning
machine learning
correlation analysis
ambient population
gis
title Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
title_full Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
title_fullStr Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
title_full_unstemmed Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
title_short Estimating ambient population density using physical features from GIS and machine learning: a study based on Japanese neighborhood
title_sort estimating ambient population density using physical features from gis and machine learning a study based on japanese neighborhood
topic neighborhood planning
machine learning
correlation analysis
ambient population
gis
url http://dx.doi.org/10.1080/13467581.2024.2428262
work_keys_str_mv AT pasitrojradtanasiri estimatingambientpopulationdensityusingphysicalfeaturesfromgisandmachinelearningastudybasedonjapaneseneighborhood
AT junkotamura estimatingambientpopulationdensityusingphysicalfeaturesfromgisandmachinelearningastudybasedonjapaneseneighborhood
AT masamikobayashi estimatingambientpopulationdensityusingphysicalfeaturesfromgisandmachinelearningastudybasedonjapaneseneighborhood