Machine learning-based simulation framework to forecast the environmental impact of urban morphology
No Thumbnail Available
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Thesis
Subject
Abstract
[EMBARGOED UNTIL 12/01/2025] Urban morphology plays a crucial role in shaping the environmental performance of buildings, influencing energy consumption and sustainability outcomes. However, modeling these impacts within Urban Building Energy Simulations (UBES) faces challenges related to predictive accuracy, scalability, and computational demands. This dissertation introduces Morph-ES, a framework integrating Machine Learning (ML) with UBES, to address these limitations. The study explores whether integrating ML into UBES can improve the ability to predict and scale energy performance analyses for various urban morphological scenarios. Two hypotheses guide the research: first, that the framework can accurately predict how urban morphological attributes affect environmental performance; and second, that it is suitable for detailed analysis across different scales of urban development. The research demonstrates that Morph-ES can effectively simulate and predict energy performance for single-block and multi-block urban configurations. By combining archetype calibration, advanced ML techniques, and iterative simulations, the framework provides consistent and reliable predictions. It also accommodates diverse urban contexts and morphological variations, maintaining its applicability across a range of scenarios. The results validate the framework's capacity to support detailed analyses of urban development, offering insights into energy use dynamics and their environmental implications. This dissertation contributes to the theoretical understanding of urban morphology's relationship with environmental performance and holds the potential to serve as a practical tool for urban planners and policymakers. By integrating computational techniques with urban planning workflows, the framework provides a pathway for more informed and sustainable urban design strategies.
Table of Contents
DOI
PubMed ID
Degree
Ph. D.