-
- GC21A-05: Development of an hourly machine learning model for spatially disaggregating urban moist heat stress
-
NOLA CC
Author(s):Generic 'disconnected' Message
Sarah Berk, University of North Carolina at Chapel Hill (First Author, Presenting Author)
TC Chakraborty, Pacific Northwest National Laboratory
Xuewei Wang, University of North Carolina at Chapel Hill
Angel Hsu, University of North Carolina at Chapel Hill
Heat doesn’t affect all parts of a city equally. To understand these differences, we built a machine learning model using measurements of air temperature and humidity collected across a variety of places, from green spaces like parks to more developed areas, such as paved streets. We found that models based only on one type of area, i.e., pavement only or grass only, make different predictions to models that include a mix of land types. Using this mixed land type model, we make comparisons of heat across the city for each hour of the day and night. This research shows how important it is to collect data from diverse urban environments, and can help cities make better decisions to protect public health, support equity, and prepare for climate change.
Scientific DisciplineNeighborhoodType
Enter Note
Go to previous page in this tab
Session
