Data-driven modeling of the impact of Asphalt surfaces on the UHI phenomenon

the physics-based modeling of the impact of road pavement characteristics on UHI can be complex and inaccurate. On the other hand, advances in data science and machine learning along with the ever-increasing computational power offer data-driven modeling opportunities that are relatively easy to setup. In recent years, with the rise of the Internet of things (IoT) and embedded sensors, a large amount of road pavement construction data can be generated and collected. This represents an opportunity to develop accurate data-driven models relating various design/construction/operation parameters referring to asphalt construction and maintenance with UHI.
The general objective of this research is to enhance an understanding of the data capturing, analysis and processing techniques currently conducted at the Concordia University, in particular by the Concordia Institute for Information Systems Engineering. With this in mind, by participating in this programme I seek to answer the following questions, as part of my PhD researcher project:

(1) Based on previous research projects conducted by the researchers Nassim Masoudifar and Amir Sharif, what are the best approaches to treat real-time streams of data? And,
(2) What is the best statistical approach to extract suitable features to represent the climatic characteristics of urban areas.

Faculty Supervisor:

Amin Hammad

Student:

Partner:

University of Twente

Discipline:

Engineering

Sector:

Education

University:

Concordia University

Program: