Interrelationships in Urban Infrastructure Use: Transport, Electricity, Water, and Gas

As cities keep growing worldwide, so does the demand for key resources such as electricity, gas, water, and transportation. Meeting the demand for these resources can be challenging and it requires an understanding of their usage patterns. The analysis of available infrastructure use data in relation to other components of the infrastructure can help better understand demand patterns of infrastructure to eventually enhance their sustainability and resilience. The main goal of the dissertation is to better understand the interrelations and interdependencies between urban infrastructure systems, both in terms of supply and demand. In chapter 2, I apply extreme gradient boosting to develop three models: electricity, gas, and water consumption in large-scale buildings in New York City, and I use SHapley Additive exPlanation to interpret the results. I find seven major findings that are summarized at the end of the chapter. Overall, I find that electricity, gas, and water consumptions are highly interrelated, but the interrelationships are complex and not universal. In chapter 3, I apply self-organizing map (SOM) to cluster daily electricity consumption patterns in Chicago before and during the COVID-19 pandemic to gain a deeper understanding of electricity consumption patterns and to study how electricity consumption patterns have changed during the pandemic. In chapter 4, I study the relationships between travel demand and electricity consumption using Long Short Term Memory (LSTM) networks. Specifically, I predict electricity consumption in zip codes around Chicago using traffic volume as the only independent variable. In total, I developed and analyzed the results of over 250 models and identify complex temporal and spatial relationships. Overall, the dissertation contributes to the urban metabolism literature that ultimately aims to gain a fundamental understanding of how energy and resources are consumed and interrelated in cities.