From heat maps to cooling actions

AI-driven citywide hourly mapping of thermal stress, drivers, and targeted cooling

Bibliographic Data

ID19487013
AuthorsSiqi Jia (0000-0001-6439-457X, University of Architecture, Civil Engineering and Geodesy, corresponding author), Cheolhee Yoo (0000-0002-3922-2300, Jet Propulsion Laboratory), Yifu Ou (0000-0001-8756-8018), Guangzhao Chen (0000-0001-7537-2288, Sun Yat-sen University), Qunshan Zhao (0000-0002-5549-9457, Urban Big Data Centre)
Year2026
Volume141
Pages107275
Publication date2026-05-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueSustainable Cities and Society (JOURNAL)
Journal identifiersISSN: 2210-6707 • E-ISSN: 2210-6715
PublisherElsevier BV (PUBLISHER)
DOI10.1016/j.scs.2026.107275
OpenAlexW7133132754
LanguageEN
References cited71

MLP-ANN fuses weather and morphology to predict hourly NET across Hong Kong. • Model achieves R2=0.97, resolving diurnal and seasonal thermal stress patterns. • Summer NET peaks at 30.29°C (15:00); winter nights drop to -4.02°C (03:00). • Elevated NET concentrates in highly urbanized zones (e.g., airport, CBD). • Larger green and water patches provide the strongest localized cooling effects. Thermal stress is critical for sustainable, health-oriented urban planning, yet remains difficult to characterize at hourly resolution and citywide in dense cities. Using Hong Kong as a case study, this study develops a regression-based machine learning framework to predict hourly thermal stress, expressed as Net Effective Temperature (NET). Long-term meteorological data was combined with detailed geographic, urban-morphological, and landscape composition–configuration metrics in a multilayer perceptron artificial neural network (MLP-ANN). The model uses 37 input variables, while the target variable is the continuous hourly NET. The model attains high predictive skill (R2 = 0.97, RMSE=1.1°C over the full dataset) and captures pronounced diurnal and seasonal patterns in thermal stress. Performance remains robust under hot (R2 = 0.97, RMSE = 0.5°C) and cold (R2 = 0.94, RMSE = 1.7°C) conditions. In summer, afternoon NET reaches about 30.3°C and remains elevated at night, whereas in winter nocturnal NET can fall below –4°C. Spatially, higher NET concentrates in dense urban and industrial districts, with summer hotspots around the airport, Northwest New Territories, and Kwai Tsing Container Terminals. Daytime NET is dominated by near-surface air temperature, followed by P impervious and NDBI, along with configuration metrics such as SHAPE, CIRCLE, and AREA, while P green and NDWI become especially influential in winter daytime. At night, configuration metrics including FRAC, CONTIG, CORE, and GYRATE gain importance. The framework delivers citywide, hourly NET maps and quantitative driver rankings to guide targeted, nature-based and morphological interventions in subtropical high-density cities

Air temperature · Automatic weather station · Daytime · Diurnal cycle · Impervious surface · Thermal · Urban heat island · Building Energy and Comfort Optimization · Smart Materials for Construction · Urban Heat Island Mitigation

Tools

Open DOIOpen Access