Mapping fine-scale anthropogenic heat flux in Shanghai by integrating multi-source geospatial big data using Cubist

Abstract

Anthropogenic heat flux (QF) significantly affects urban surface energy budget. However, refined QF data are lacking for most cities across the world. To address this deficiency, this study firstly estimated the spatial distribution of the annual average QF from different sources of industry (QFI), buildings (QFB), transportation (QFT) and human metabolism (QFM) at district and sub-district level based on multi-source data over Shanghai in 2018. Then, a Cubist machine learning based model was developed to disaggregate QF into 1 km dataset by fusing points-of-interest (POIs) geospatial big data and multi-source remote sensing data. Results showed that the district-level QFB contributes most to the total QF in city center, while QFI dominates in suburbs. High value areas of 1 km gridded QFI are mainly distributed outside the central urban area. QFT presents a divergence pattern from the city center to the outside. The total anthropogenic heat flux is highest in the city center with maximum of 523.03 W m−2. Variable importance analysis revealed that POIs are important for estimations of QF. Compared with previous studies, QF values presented here are within the range of exiting results but reveal a more reasonable spatial distribution. This study provides new aspects for spatially refined quantifications of QF that can supplement future studies on urban heat island and urban climate numerical modeling.