English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A fundamental problem of interest to policy makers, urban planners, and otherstakeholders involved in urban development projects is assessing the impact ofplanning and construction activities on mobility flows. This is a challengingtask due to the different spatial, temporal, social, and economic factorsinfluencing urban mobility flows. These flows, along with the influencingfactors, can be modelled as attributed graphs with both node and edge featurescharacterising locations in a city and the various types of relationshipsbetween them. In this paper, we address the problem of assessingorigin-destination (OD) car flows between a location of interest and everyother location in a city, given their features and the structuralcharacteristics of the graph. We propose three neural network architectures,including graph neural networks (GNN), and conduct a systematic comparisonbetween the proposed methods and state-of-the-art spatial interaction models,their modifications, and machine learning approaches. The objective of thepaper is to address the practical problem of estimating potential flow betweenan urban development project location and other locations in the city, wherethe features of the project location are known in advance. We evaluate theperformance of the models on a regression task using a custom data set ofattributed car OD flows in London. We also visualise the model performance byshowing the spatial distribution of flow residuals across London.

Learning Mobility Flows from Urban Features with Spatial Interaction Models and Neural Networks