Deep learning-based investigation of the impact of urban form on the particulate matter concentration on a neighborhood scale

Abstract

Despite the importance of urban forms to the dispersion of particulate matter (PM), only a few studies exist on the relationship between them due to the limitations of the data and methodology. Thus, this study used a deep learning-based investigation of the impact of urban form on PM2.5 concentration. Autoencoder, long short-term memory (LSTM), and the random forest model were used to analyze their relationship. The random forest model showed that urban form variables predict PM2.5 concentration with a 95.66% accuracy, confirming that urban form characteristics significantly impact PM2.5 concentrations. Among the urban form variables, floor area ratio turned out to be the most important, suggesting the need for more detailed efforts to reduce PM2.5 in locations with high floor areas. The effect on PM2.5 prediction accuracy was evaluated with root mean square error. It was difficult to accurately predict PM2.5 in areas with large building coverage areas and low-rise residential areas. This study improved the accuracy of results on the influence of urban form by using PM2.5 non-aggregated data measured hourly over 4 years, which expanded the applicability of deep learning-based urban analysis.

A Comparative Analysis of Museum Accessibility in High-Density Asian Cities: Case Studies from Seoul and Tokyo

“…Referring to the United Nation s SDGs [68], several studies have begun including walking accessibility by focusing on travel modes that yield the lowest carbon emissions; these studies have also addressed limiting the travel range in terms of the duration and distance while examining the diversity of travel patterns within this range [33,[69][70][71]. In addition, most previous studies conducted on Tokyo and Seoul focused on analyzing urban accessibility in terms of the urban form, urban development sustainability, and urban services [33,[72][73][74][75][76][77]. Only a few have considered the spatial accessibility of cultural facilities in cities, and studies on museums are rare.…”