<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Urban Health | Cai Wu</title><link>https://wucai.me/tag/urban-health/</link><atom:link href="https://wucai.me/tag/urban-health/index.xml" rel="self" type="application/rss+xml"/><description>Urban Health</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 24 Jun 2026 00:00:00 +0000</lastBuildDate><image><url>https://wucai.me/media/icon_hu85d1edb00a0a31beb9b4c5ffd37a6d0d_2581_512x512_fill_lanczos_center_3.png</url><title>Urban Health</title><link>https://wucai.me/tag/urban-health/</link></image><item><title>06-2026 | UST-GNN for urban health analytics</title><link>https://wucai.me/post/20260624-ust-gnn/</link><pubDate>Wed, 24 Jun 2026 00:00:00 +0000</pubDate><guid>https://wucai.me/post/20260624-ust-gnn/</guid><description>&lt;p>Our &lt;a href="https://wucai.me/publication/zhao-2026-ceus/">UST-GNN paper&lt;/a> became available online in &lt;em>Computers, Environment and Urban Systems&lt;/em> on &lt;strong>24 June 2026&lt;/strong>, ahead of its October 2026 issue.&lt;/p>
&lt;p>UST-GNN combines spatial context and neighborhood connectivity within a graph neural network. A case study in Greater London examines how these relationships contribute to urban health prediction, with spatial cross-validation used to evaluate performance beyond the neighborhoods used for training.&lt;/p>
&lt;p>Read the &lt;a href="https://wucai.me/publication/zhao-2026-ceus/">publication details&lt;/a> and &lt;a href="https://doi.org/10.1016/j.compenvurbsys.2026.102466" target="_blank" rel="noopener">publisher&amp;rsquo;s version&lt;/a>.&lt;/p></description></item></channel></rss>