Urban areas worldwide are expanding and becoming denser. Along with this growth comes amplified local warming, known as the urban heat island effect. A recent study, partially funded by the Climate Program Office’s Climate Observations and Monitoring (COM) program, uses machine learning to contribute accurate and user-friendly resources for urban planners to mitigate urban heat and carbon emissions. This research is part of a COM initiative to develop improved surface-atmosphere interaction representation in models. The incorporation of machine learning in research and modeling to advance mitigation strategies for anthropogenic change is a main goal in the NOAA Artificial Intelligence Strategy. This study contributes to the growing pool of research aligned to CPO’s extreme heat climate risk area.
Researchers from Arizona State University used machine learning techniques to emulate the heat and carbon processes in the urban environment. The results, published in Computers, Environment and Urban Systems, demonstrate the advantage of machine learning to create an accurate and high resolution model product that can be easily understood and used by urban planners. It is imperative to use fast, accurate, and economical techniques to address the rapid rate of localized warming in cities. This study provides a case study where machine learning can be used as a tool to inform urban heat island mitigation strategies.
For more information, contact Clara Deck.