Where risk concentrates: the hotspots
Geunhye Kim & Aashni Tanna
Team Best Ting worked as a pair on two pieces, both submitted on the day and judged together as one entry. Repos: Geunhye · Aashni.A demonstration of more accessible urban climate modelling. Participants drove the SUEWS urban climate model through an AI agent, in plain language, to re-imagine how we read urban heat in a future city.
The SUEWS Community Hackathon brought participants together for a focused afternoon of urban climate exploration during the 16th UCL RDR Annual Conference. Everyone worked from the same synthetic city, UDA-city, so the emphasis was on interpretation, communication, and judgement rather than on comparing incompatible inputs.
Participants used an AI agent, via the SUEWS agent layer, to drive SUEWS in plain language, turning model outputs into public pages about heat exposure, vulnerability, and possible neighbourhood-scale responses. The result is a compact gallery of different readings of the same future-city problem.
Every entry analysed the same synthetic city, UDA-city, and bridged a SUEWS heat-hazard layer to a socio-economic heat-risk indicator. Explore the pages and the repositories below.
Geunhye Kim & Aashni Tanna
Team Best Ting worked as a pair on two pieces, both submitted on the day and judged together as one entry. Repos: Geunhye · Aashni.Neil Meyer
Divya Thakur
Marina Fitzner
Sam Owens
Watcharaporn (Pam) Moonsap
Farrah Jasmine Dingal
Julie Futcher
The public-facing assessment is based on the pages linked above. Readers should judge how well each page turns SUEWS heat-hazard output into an honest, understandable story about people, places, and possible responses.
Technical evidence from repositories, SUEWS configurations, transcripts, and AI collaboration is reviewed separately by the SUEWS expert panel.
Open the judging form →