Urban Data Science & Methods

Urban Road Crash Severity Prediction Using Explainable Machine Learning and Spatial Hotspot Analysis: Evidence from Loja, Ecuador

Regional Innovation Disparities in Kazakhstan: Input–Output Misalignment in an Official Panel, 2014–2025

Adapting large language models for urban trip purpose inference: A domain-informed textual representation and fine-tuning framework

Nonlinear and heterogeneous effects of 2D/3D factors on global urban heat island using explainable spatial machine learning

Urban Flood Risk Prediction Based on the Hybrid Sampling of Imbalanced Data and Deep Learning Model

Global patterns of urban heat shaped by climate and morphology

Separates the heat-island contribution of background climate from that of surrounding urban form across 2,213 cities and projects how each will change.

Large-scale measurement of street interface transparency based on street view data and deep learning: A study of first-tier cities in China (Beijing, Shanghai, and Guangzhou)

Proposes a method to measure how transparent street-level building frontages are, at scale, using open street view images and deep learning in three Chinese megacities.

Street View Imagery Analysis in a Computational Notebook

A hands-on methods chapter showing how to download street view images and apply deep convolutional networks to detect and measure features of the built environment, in a reproducible notebook.

Learning street view representations based on a spatiotemporal contrastive learning framework

Benchmarks representation-learning strategies for street view imagery and introduces a spatiotemporal contrastive framework to learn features useful for perception and socioeconomic prediction tasks.