Expanding our Heat Resilience data to 50+ global cities

2026-06-30 · Source: The latest research from Google · Field: Science & Research — Environmental Science & Earth Systems, Research Methodology & Innovation, Engineering & Applied Sciences · Depth: Advanced, short

Summary

Google Research has released an expanded dataset of building-level rooftop reflectivity, now covering over 50 global cities, to assist urban planners in implementing cool-roof solutions. This dataset, accessible via a new high-resolution Heat Resilience Earth Engine App, aims to mitigate extreme urban heat, which contributes to approximately 500,000 deaths annually. The methodology, detailed in "Estimating high-resolution albedo for urban applications" in Nature Communications, fuses 10-meter Sentinel-2 satellite data with 30-cm Airbus Pléiades Neo imagery using machine learning and radiometric calibration. This approach provides granular, building-level insights, validated against airborne hyperspectral measurements over Boulder, Colorado, achieving an RMSE of 0.04. Targeted cool-roof planning using this data could mitigate extreme urban heat by up to 0.5°C (1.8°F) globally, offering a cost-effective path for cities like London, Athens, Rio de Janeiro, and Los Angeles.

Key takeaway

For urban planners and municipal decision-makers addressing extreme heat, the new Heat Resilience Earth Engine App provides critical, high-resolution albedo data. You can now identify specific buildings for cool-roof interventions, moving beyond neighborhood averages to prioritize efforts effectively. Utilize this open-access data to develop targeted adaptation plans and monitor reflectivity changes, potentially reducing urban temperatures by up to 0.5°C.

Key insights

Google Research's new high-resolution albedo dataset and app enable precise, building-level cool-roof planning for urban heat mitigation.

Principles

• Fusing satellite data improves resolution for urban planning.
• Building-level albedo data guides targeted heat interventions.
• Cool roofs offer a cost-effective heat mitigation strategy.

Method

Fuses 10-meter Sentinel-2 satellite data with 30-cm Airbus Pléiades Neo imagery using machine learning and radiometric calibration to create high-resolution albedo maps.

In practice

• Identify low-reflectivity rooftops for cool-roof retrofits.
• Monitor urban reflectivity changes over time.
• Download high-resolution data for local policy development.

Topics

• Urban Heat Island Effect
• Cool Roofs
• Satellite Imagery Analysis
• Geospatial AI
• Google Earth Engine
• Climate Adaptation

Best for: Computer Vision Engineer, Research Scientist, AI Scientist, Policy Maker, Director of AI/ML

Related on AIssential

• Blue, yellow and green: Google invests in its new data center in Sweden. — Google is expanding its infrastructure in Sweden with a sustainable data center and significant community investment.
• LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data — Image-to-image networks globally estimate non-stationary spatial parameters faster and more accurately than local methods.
• We’re creating a new satellite imagery map to help protect Brazil’s forests. — High-resolution satellite imagery provides critical baseline data for environmental monitoring and policy enforcement.
• Spatially-constrained clustering of geospatial features for heat vulnerability assessment of favelas in Rio de Janeiro — Settlement morphology significantly influences heat vulnerability in informal urban areas, with flat-terrain favelas experiencing higher temperatures.
• Scalable Deep Learning Framework for Global High-Resolution Land Use Reconstruction — AI4Land uses U-Net on HPC to reconstruct global 1 km land use from coarse data, improving climate model inputs.
• Building Extraction from Remote Sensing Imagery under Hazy and Low-light Conditions: Benchmark and Baseline — A new benchmark and network address building extraction challenges in hazy and low-light remote sensing imagery.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The latest research from Google.