A high-resolution monitoring approach of canopy urban heat island using a random forest model and multi-platform observations

Chen, Shihan; Yang, Yuanjian; Deng, Fei; Zhang, Yanhao; Liu, Duanyang; Liu, Chao; Gao, Zhiqiu

doi:https://doi.org/10.5194/amt-15-735-2022

Articles | Volume 15, issue 3

https://doi.org/10.5194/amt-15-735-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-15-735-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 3

Research article

|

09 Feb 2022

Research article |

| 09 Feb 2022

A high-resolution monitoring approach of canopy urban heat island using a random forest model and multi-platform observations

Shihan Chen, Yuanjian Yang, Fei Deng, Yanhao Zhang, Duanyang Liu, Chao Liu, and Zhiqiu Gao

Supplement

https://doi.org/10.5194/amt-15-735-2022-supplement

Data sets

Landsat 8 OLI and TIRS Digital Products Computer Network Information Center http://www.gscloud.cn/sources/index?pid=263&rootid=1&label=Landsat8&sort=priority&page=1

Version 4 DMSP-OLS Nighttime Lights Time Series National Centers for Environmental Information http://ngdc.noaa.gov/eog/dmsp/downloadV4composites.html

ASTER GDEM Computer Network Information Center http://www.gscloud.cn/sources/accessdata/310?pid=302

Short summary

This paper proposes a method for evaluating canopy UHI intensity (CUHII) at high resolution by using remote sensing data and machine learning with a random forest (RF) model. The spatial distribution of CUHII was evaluated at 30 m resolution based on the output of the RF model. The present RF model framework for real-time monitoring and assessment of high-resolution CUHII provides scientific support for studying the changes and causes of CUHII.