Instant urban climate modelling with AI: An interactive LEGO®-based workshop for public engagement with urban heat islands

Urban heat island processes are well established in the scientific literature, yet their physical mechanisms can remain abstract for non-expert audiences. To address this gap, we developed an interactive outreach workshop, designed as a serious game, combining hands-on city construction using LEGO® bricks with rapid, artificial intelligence-based temperature simulations. Participants construct miniature urban layouts that are scanned and translated into land-cover representations, which are used to generate spatial temperature patterns for warm, low-wind nighttime conditions. The workshop was held at public science outreach events in Brussels, Belgium, from 2023 to 2025, targeting mainly children aged 7–12. Across four editions from 2024 to 2025, post-workshop questionnaires ( N = 400 ) characterized immediate responses to questions concerning land cover, urban temperature, and climate adaptation, together with self-reported perceived learning and prior awareness of climate change. High proportions of participants selected the correct responses to questions addressing the principal workshop concepts: 86.2% identified built-up areas as warmest, 92.5% identified green areas as coolest, and 90.5% selected a greener urban design under the given warm nighttime conditions. In addition, 77.1% self-reported learning something new. Pearson chi-square tests detected no statistically significant differences in selected response proportions between events, while subgroup analyses by age, gender, living environment, and prior participation are descriptive. The workshop demonstrates how a data-driven urban temperature model can support interactive public engagement with urban climate concepts.

Authors

Institutions

Publication Details

Journal
Urban Climate
Published
2026-11-15
DOI
https://doi.org/10.1016/j.uclim.2026.103206
Primary Topic
Urban Heat Island Mitigation
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Instant urban climate modelling with AI: An interactive LEGO®-based workshop for public engagement with urban heat islands

Sara M. Top, Lesley De Cruz, Andrei Covaci, Geert De Paepe et al.
Urban Climate
Urban Heat Island Mitigation
article

Instant urban climate modelling with AI: An interactive LEGO®-based workshop for public engagement with urban heat islands

Sara M. Top, Lesley De Cruz, Andrei Covaci, Geert De Paepe, Jef Grupping, Jorre Verelst, Hannes Coenen, Firass Kooli, Jonathan Beliën
article en

Abstract

Urban heat island processes are well established in the scientific literature, yet their physical mechanisms can remain abstract for non-expert audiences. To address this gap, we developed an interactive outreach workshop, designed as a serious game, combining hands-on city construction using LEGO® bricks with rapid, artificial intelligence-based temperature simulations. Participants construct miniature urban layouts that are scanned and translated into land-cover representations, which are used to generate spatial temperature patterns for warm, low-wind nighttime conditions. The workshop was held at public science outreach events in Brussels, Belgium, from 2023 to 2025, targeting mainly children aged 7–12. Across four editions from 2024 to 2025, post-workshop questionnaires ( N = 400 ) characterized immediate responses to questions concerning land cover, urban temperature, and climate adaptation, together with self-reported perceived learning and prior awareness of climate change. High proportions of participants selected the correct responses to questions addressing the principal workshop concepts: 86.2% identified built-up areas as warmest, 92.5% identified green areas as coolest, and 90.5% selected a greener urban design under the given warm nighttime conditions. In addition, 77.1% self-reported learning something new. Pearson chi-square tests detected no statistically significant differences in selected response proportions between events, while subgroup analyses by age, gender, living environment, and prior participation are descriptive. The workshop demonstrates how a data-driven urban temperature model can support interactive public engagement with urban climate concepts.

Urban ClimateVol. 70
Royal Meteorological Institute of Belgium (BE), Vrije Universiteit Brussel (BE), Ghent University (BE), Karel de Grote Hogeschool (BE)
Urban Heat Island Mitigation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon