ABSTRACT
Urban heat islands (UHIs) result due to the replacement of land area with buildings and pavements. UHIs can have a direct impact on the health and well-being of city dwellers. Apart from pollution, the substantially warmer temperature in cities compared to suburbs may provide possible health risks owing to heat waves. Heat waves are common in cities, affecting human and animal health by causing heat cramps, sleep loss, and higher mortality rates. This study examines several publications in the existing literature on the subject, with a particular focus on machine learning (ML) and deep learning (DL) approaches used in climate change mitigation and adaptation. ML and DL methodologies have grown in prominence as technology has advanced in many domains, including climate change. This study is about the investigation of the most widely used ML/DL algorithms such as random forest (RF), artificial neural network (ANN), deep neural network (DNN), and multiple linear regression (MLR) in the prediction of UHI. The study concludes by reviewing significant aspects in the field of UHI as well as underlining the necessity of discovering deep learning algorithms for UHI prediction.
