Time-series urban heat island effect analysis and prediction based on urban sensors and remote sensing data

Authors: Fangzheng Lyu*, University Of Illinois, Shaohua Wang, University of Illinois at Urbana Champaign, Shaowen Wang, University of Illinois at Urbana Champaign
Topics: Remote Sensing, Urban and Regional Planning, Climatology and Meteorology
Keywords: CyberGIS, remote sensing, Urban heat island, Machine Learning
Session Type: Paper
Day: 4/8/2020
Start / End Time: 3:20 PM / 4:35 PM
Room: Plaza Court 5, Sheraton, Concourse Level
Presentation File: No File Uploaded


As urbanization proceeds, climate study of the urban area is becoming crucial in understanding human exposure to air quality and other environmental factors in the city. And the climate study can become a guide for future urban planning. Chicago city, which is the third biggest city in the US in terms of population, is the study area of this research. In this study, we combined the traditional urban sensing data over the last several years and the remote sensing data to study and predict the future climate evolving, especially the urban heat island (UHI) effect of the city. UHI is an urban area that is warmer than its surrounding rural area due to human activities and city structure. And studying and predicting UHI can help us better understand the different factors that contribute to UHI and better deal with UHI in the future. We are using the time-series environment data from Array of Things (AOT), which is a network of urban sensors, combining with the remote sensing data and census tract data over the time period of the urban Chicago area to investigate into the heat island effect in the city. Besides, we are employing the machine learning algorithm to help us predict and analyze the heat island effect of the city in the coming future.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login