Benchmark RadarAI BENCHMARK PROFILE
HeatCast
HeatCast is a benchmark for monthly Land Surface Temperature forecasting at 30m resolution across 124 U.S. cities. It provides Landsat-based tiles, fixed temporal split, LCZ-stratified metrics, and a reference evaluation harness.
- Released
- 2026-08-07
- Readiness
- Inspectable
- Primary field
- General AI
Why it matters
The benchmark addresses a gap in neighborhood-scale LST forecasting, offering a large-scale dataset with standardized metrics to compare forecasting models across diverse urban environments, supporting practical applications in urban heat monitoring.
Motivation
Land Surface Temperature (LST) is a widely used satellite-derived measure of urban surface heat, but there is no shared benchmark for forecasting it at 30 m.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.