Characterizing the drivers of heat intensity in Worcester (MA) using Random Forests

Keywords: Urban Heat Island Effect, Worcester, Random Forest.
Session Type: Virtual Poster
Day: Wednesday
Session Start / End Time: 4/7/2021 01:30 PM (Pacific Time (US & Canada)) - 4/7/2021 02:45 PM (Pacific Time (US & Canada))
Room: Virtual 52

Abstract

The Urban Heat Island phenomenon (UHI) has been increasingly affecting vulnerable urban communities in the context of regional climate change. The UHI has numerous negative impacts on vulnerable residents such as influencing summertime utility bills for poor communities who lack air conditioning, and exposure to air pollutants such as ozone - therefore increasing the risk of vulnerable communities to respiratory related illnesses. While the impact of the UHI on environmental justice communities has been recognized by municipal policymakers, few studies have tracked the spatial variability and the drivers of the UHI phenomenon over the course of a day. The objective of this study is to identify those neighborhoods in the city of Worcester, Massachusetts that are most affected by the UHI phenomenon. Air temperature maps were created for morning, afternoon, and evening on August 20th of 2019 using in-situ air temperature data collected by the City of Worcester through mounted car sensors. The heat maps are used to identify the locations that experience the highest air temperature when comparing three times in a day. The maps of heat intensity are them used in a random forest model to identify how factors such as building height, urban canopy density and land-use contribute to the UHI. This study seeks to provide the City of Worcester with a better understanding of the most affected areas by UHI. This work can assist local governments to think on better forms to developing policies to decrease the effects of UHI in environmental justice communities.