Using Machine Learning to Greener Zoning in Philadelphia

Category Engineering

tldr #

Researchers from Drexel University's College of Engineering have developed a process using two machine learning programs to predict how changes in zoning configurations could affect building energy use and subsequent greenhouse gas emissions. Their team believes cities such as Philadelphia can conserve energy, save money, and create a more sustainable environment through the use of machine learning and energy-aware zoning.

content #

As Philadelphia strives to meet greenhouse gas emissions goals established in its 2050 Plan, a better understanding of how zoning can play a role in managing building energy use could set the city up for success. Researchers in Drexel University's College of Engineering are hoping a machine learning model they've developed can support these efforts by helping to predict how energy consumption will change as neighborhoods evolve.

Philadelphia is one of the oldest cities in the United States

In 2017, the city set a goal of becoming carbon neutral by 2050, led in large part by a reduction in greenhouse gas emissions from building energy use—which accounted for nearly three-quarters of Philadelphia's carbon footprint at the time. But the key to meeting this mark lies not just in establishing sustainable energy use practices for current buildings, but also incorporating energy use projections into zoning decisions that will direct future development.

Philadelphia aims to become carbon neutral by 2050

And the challenge for Philadelphia, one of the oldest cities in the country, is that building types vary widely—as does their energy use. So planning for more efficient energy use at the City level is not a problem with a one-size-fits-all solution.

"For Philadelphia in particular, neighborhoods vary so much from place to place in prevalence of certain housing features and zoning types that it's important to customize energy programs for each neighborhood, rather than trying to enact blanket policies for carbon reduction across the entire city or county," said Simi Hoque, Ph.D., a professor in the College of Engineering who led research into using machine learning for granular energy-use modeling recently published in the journal Energy and Buildings.

In 2015, nearly three-quarters of Philadelphia's carbon footprint was from building energy use

Hoque's team believes existing machine learning programs, properly deployed, can provide some clarity on how zoning decisions could affect future greenhouse gas emissions from buildings.

"Right now there is a huge volume of energy use data, but it's often just too inconsistent and messy to be reasonably put to use. For example, one dataset corresponding to certain housing characteristics may have usable energy estimates, but another dataset corresponding to socioeconomic features is missing too many values to be usable," she said.

Machine Learning is equipped to handle data limitations due to its ability to iteratively learn and improve

"Machine learning is well equipped to handle this challenge because they can iteratively learn and improve through the training process to reduce bias and variance despite these data limitations." .

To glean information from the disjointed data, the team developed a process using two machine learning programs—one that can tease out patterns from massive tranches of data and use them to make projections about future energy and a second that can pinpoint the details in the model that likely had the greatest effect on changing the projections.

Extreme Gradient Boosting (XGBoost) is a deep-learning program used by researchers in the project

First they trained a deep-learning program, called Extreme Gradient Boosting (XGBoost), with volumes of commercial and residential energy-use data for Philadelphia from the U.S. Energy Information's Residential Energy Consumption Survey and Commercial Buildings Energy Consumption Survey for 2015, as well as the city's demographic and socioeconomic data from the U.S. Census Bureau's American Communities Survey for that time period.

Machine Learning can provide clarity on how zoning decisions could affect future greenhouse gas emissions from buildings

The program learned enough from the data that it could draw correlations between a laundry list of variables, such as density of buildings, population size, number of occupant households, and land use—to the building energy use associated with that particular zone.

Using the machine learning model, the team could simulate different projected energy scenarios based on changes in zoning configurations and anticipate the potential greenhouse gas emissions that could result. For example, a larger number of multi-family housing units or development of several commercial buildings in one area could result in a certain amount of energy use and subsequent emissions. But clamping zoning rules to limit such development could adjust emissions accordingly.

By having the ability to make energy predictions from zoning plans, the team believes cities like Philadelphia can conserve energy, save money, and create a more sustainable environment for its citizens.

"Historically, zoning was viewed in a vacuum when it came to energy and environment," Hoque said. "This research demonstrates that through the use of machine learning, cities and counties can become more energy-aware when it comes to planning and zonning, consciously choosing strategies that protect the planet and pocketbooks." .

hashtags #
worddensity #