Using Machine Learning to Inform the Spatial Design of Energy Self-Sufficient Communities

Cities are complex systems that face continuous change of environmental, developmental, and political conditions. This dynamic complexity calls into question traditional urban planning and design principles, and demands new approaches that can be accomplished using new technologies, such as artificial intelligence and machine learning. This need is particularly acute when addressing energy-related issues that are affected by environmental conditions complicated by climate change. Reaching the goal of energy efficient and resilient cities requires moving past building-scale analysis to address the phenomenon at an urban scale. A strategy for reaching energy independency in urban environments has been the development of communities that guarantee the local supply and demand for clean energy, considering both network and building configurations. However, while the spatial development process requires the participation of architects and urban planners, the relationship between urban form and energy performance has not been widely explored in the design of high-performance energy communities. This may be due to the complexity associated with studying how urban form impacts energy performance and the unavailability of tools for designing and assessing energy performance at this scale.

In this study, the use of artificial neural networks is described as a method to unravel the complex, intertwined relationship between urban form and energy demand in communities in the context of San Diego, California.

Files

Metadata

Work Title Using Machine Learning to Inform the Spatial Design of Energy Self-Sufficient Communities
Access
Open Access
Creators
  1. Mina Rahimian
  2. Jose M Pinto Duarte
  3. Lisa Iulo
Keyword
  1. Urban design
  2. Energy independent communities
  3. Machine learning
  4. Artificial neural networks
  5. Energy performance
License CC BY-NC 4.0 (Attribution-NonCommercial)
Work Type Poster
Publication Date September 23, 2021
Source
  1. Fall 2021 Stuckeman Research Open House
Deposited February 24, 2022

Versions

Analytics

Collections

Work History

Version 1
published

  • Created
  • Added Creator Mina Rahimian
  • Added Creator Jose M Pinto Duarte
  • Added Creator Lisa Iulo
  • Added Using Rahimian.pdf
  • Updated License Show Changes
    License
    • https://creativecommons.org/licenses/by-nc/4.0/
  • Published
  • Updated
  • Updated