Google Research has created a Heat Resilience tool that applies AI to satellite and aerial imagery, with the goal of helping cities to mitigate urban heat. This online mapping tool is being piloted in 14 U.S. cities: Austin, TX; Baltimore, MD; Boston, MA; Boulder and Colorado Springs, CO; Los Angeles, CA; Miami-Dade County, FL; Nashville, TN; New York City; Phoenix, AZ; San Antonio, TX; Stockton, CA; Tempe, AZ; and Washington, D.C. It’s expected that the mapping tool will help urban planners and local governments see the impact of cooling interventions – right down to the neighborhood level.
“Quantifiable data is crucial for cities to identify their hottest, most vulnerable communities and prioritize where to implement cooling strategies,” the company said in a statement.
The mapping tool uses AI-powered object detection and machine-learning algorithms to account for local characteristics, including how much green space a city has or how well the roofs on buildings reflect sunlight, to determine how much heat a portion of land absorbs. It also incorporates indicators of social vulnerability, such as income statistics, to identify the areas most in need of heat relief.
Quantifying how to reduce surface temperatures with cooling interventions, such as planting trees and installing highly reflective surfaces like cool roofs, should help focus efforts and funds for heat mitigation. For example, Miami-Dade county plans to use the tool to develop policies that incentivize developers to take heat mitigation measures. The city of Stockton has used an earlier version of Google’s Heat Resilience tool to gather data for potential projects and opportunities to reduce urban heat islands.