Machine Learning Approach to Examine the Relationship between Residential Energy and Water Consumption with Greenhouse Gas Emissions in NYC

The City of New York has set an ambitious goal to reduce 80% of its greenhouse gas (GHG) emission by 2050, relative to the 2005 baseline. While approaches have been taken on the regulatory level, residential consumption of water and energy needs to be better understood for incentives on reducing house-hold level GHG emissions. This study examines the impact of end-use residential water and energy consumption on greenhouse gas emissions. We model the relationships between demand, end-use consumption, and emissions. We use artificial neural networks to predict the impact of the water-energy nexus on greenhouse gas emissions. We also examine how these relationships change by the income of the area of consumption. We theorize that income impacts residential energy and water consumption and consequently, GHG emissions outcomes.