Benchmark Radar
AI BENCHMARK PROFILE

UHI-Bench

General AIKnowledge & ReasoningUHI-Bench Team

UHI-Bench is a benchmark for dual-source urban heat island (UHI) modeling that integrates dynamic meteorological drivers and static urban morphology. It evaluates over 20 baselines from four model families across five tasks on 20 cities in nine Köppen climate classes, covering land surface temperature UHI and near-surface air temperature UHI.

Released
2026-08-24
Readiness
Paper only
Primary field
General AI

Why it matters

The benchmark addresses the lack of standardized evaluation for dual-source UHI modeling, which is crucial for understanding urban heat exposure and climate adaptation. It provides a unified framework to facilitate cross-city transfer and climate data equity, guiding practical urban heat mitigation strategies.

Motivation

Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks.

Primary resources

Benchmark Radar records only publicly supported details and links back to primary sources for verification.