Author

Gaurav Khatri

Date of Award

2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

Committee Chair

Huaming Zhang

Committee Member

Leiqiu Hu

Committee Member

Deepak Acharya

Research Advisor

Huaming Zhang, Leiqiu Hu

Subject(s)

Data integration (Computer science), Machine learning, Meteorological stations, Urban temperature--Mathematical models

Abstract

This thesis explores the development and application of a novel data architecture for predicting ambient temperatures across US cities, focusing on integrating multi-source data i.e. ECOSTRESS land surface temperatures, urban surface properties, and crowdsourced weather data. The methodology is designed for scalability and adaptability across different urban regions, employing rigorous data quality control to enhance prediction accuracy. The validation of this model across diverse urban settings, demonstrated through rigorous RMSE comparisons and spatial mapping, validates its superiority over traditional models. Through experiments in diverse climatic conditions in Madison, Wisconsin, and Las Vegas, Nevada, the study assesses the model’s generalizability and effectiveness in capturing spatio-temporal temperature variations. This study aims to contribute to urban heat island mitigation and sustainable urban planning, setting a benchmark for future research in urban climatology.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.