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.
Recommended Citation
Khatri, Gaurav, "Ambient temperature modelling with ECOSTRESS and private weather stations" (2024). Theses. 669.
https://louis.uah.edu/uah-theses/669