Lecture 13
Sustanaibility /
Inequality

Esteban Moro

Network Science Institute | Northeastern University

NETS 7983 Computational Urban Science

2025-04-01

Welcome!

This week:

Sustainability and Inequality in urban areas from the perspective of Computational Urban Science

Distribution of emissions by car and street, from [1]

You are here

Data -> Methods -> Models -> Applications.

Aims

• Understand main Sustainability and Inequality problems in Urban Areas.
• Show how Computational Urban Science can help to understand and alleviate those problems.
• Showcase some research about it

Contents

• Introduction
• What is sustainability
• Sustainability and CUS
• Research/Application Examples
• Conclusions
• Further reading
• References

Introduction

What is sustainability?

Sustainability is one of the most pressing challenges in urban areas. In its broadest senses, sustainability is about the capacity of a city to maintain its functions, diversity, and resilience over time.

Sustainability is typically framed around the concept of the “triple bottom line” (TBL) which includes economic, social, and environmental dimensions.

• Economic sustainability: promoting sustainable economic growth and development that benefits society without harming the environment.
• Social sustainability: ensuring social equity, justice, and well-being for all people.
• Environmental sustainability: protecting and preserving the natural environment and resources for future generations.

What is sustainability?

UN Sustainable Development Goals (SDGs) are a set of 17 global goals designed to be a “blueprint to achieve a better and more sustainable future for all”.

Sustainability in urban areas.

Key Research Questions [2]:

• Environmental degradation:
  • Pollution (air, water, noise): understanding and mitigation sources and impacts of pollution on human and environment
  • Loss of Green Spaces and Biodiversity
  • Unsustainable Consumption Patterns: understand how our consumptions patterns affect our city, its resources, and make the more sustainable.
  • Waste generation and management

Sustainability in urban areas.

Key Research Questions [2]:

• Social Inequities:
  • Environmental Justice: addressing the disproportionate impact of environmental hazards on some populations
  • Access to Resources and Services: equitable access to essential services, jobs, education, etc.
  • Health and well-being: study the socio-economic determinants of health in urban areas and developing interventions to mitigate them.

Sustainability in urban areas.

Key Research Questions [2]:

• Urban Planning and Governance:
  • Sustainable urban growth: how to promote compact, mixed-used development patterns that minimize urban sprawl and promote walkable, transit-oriented communities
  • Reallocation of road spaces to promote active (walking and cycling) and public transport in our cities.
  • Integrate natural spaces in our communities to mitigate urban heat island effect, improve air quality
  • Community engage and participation: new ways to involve residents in urban decision-making
  • Effective policies and regulations: evaluate the impact of policies

Sustanaibility and CUS

Sustanaibility and CUS

Computational Urban Science is the key tool to address those problems by providing new ways to collect, analyze and understand complex urban dynamics:

• Environmental degradation:
  • Pollution: real-time pollution data from sensors at street level to identify sources of pollution and
  • Urban green space: satellite imagery and remote sensing data to monitor changes in vegetation
  • Consumption patterns: use of credit card data, mobility data to understand residents lifestyles and promote sustainable consumption patterns.
  • Waste management: sensors across the city to provide real-time data to optimize routes, reduce operational cost, etc.

Sustanaibility and CUS

• Social Inequities::

  • Environmental justice analysis: mobility data, social media, credit card data can reveal patterns of environmental exposure, helping policymakers address those disproportionate impacts.

  • Access to resources and services: mobility data and public service usage can inform the strategic allocation of resources and ensure equitable access to transportation, healthcare, etc.

  • Understanding social behaviors and interactions: mobility data, social media can provide insights into community preferences, access to opportunity, exposure to other groups, etc.

Sustanaibility and CUS

• Urban planning and governance
  • Optimizing Transportation and Mobility: large-scale data helps optimize traffic flow, public transport routes, alternative active modes of transportation, etc.
  • Data-driven urban development: housing data, mobility data to help urban planners to make more informed decisions about sustainable development patterns.
  • Evaluation of public policies: using machine learning and causal methods to better evaluate the impact and the design of public policies.

Research/Application Examples

Example: Sustainable mobility patterns

Gross polluters and vehicle emissions reduction [1]

Traditional emission estimation methods use remote sensing stations, missing the full driving cycle of vehicles, or focus on a few vehicles. Use of massive GPS traces and a vehicle emissions model to understand who pollutes more.

From [1]

Example: Sustainable mobility patterns

Gross polluters and vehicle emissions reduction [1]

They found that emissions across vehicles and roads is heavy-tailed distributed. Thus there are gross polluters that are responsible for the greatest quantity of emissions.

Distribution of emissions by car and street, from [1]

Example: Sustainable mobility patterns

Gross polluters and vehicle emissions reduction [1]

More efficient emission reduction policies must target those polluters first.

Simulation of vehicle electrification, from [1]

Example: Environmental justice

Environmental inequality in the neighborhood networks of urban mobility in US cities [3]

Use mobility data (Advan/Safegraph) to understand what is the difference/similarity between exposure to air pollution residents get in their neighborhoods or when they move around.

Number of trips from neighborhoods (in blue), from [3]

Example: Environmental justice

Environmental inequality in the neighborhood networks of urban mobility in US cities [3]

Minority and poor neighborhoods have more exposure to pollution in their neighborhoods. However, is that mitigated or exacerbated because individuals spend much of their time outside their residential neighborhood? No: the same.

PM2.5 exposure in residential neighborhoods, adjacent neighborhoods, and nonadjacent neighborhoods that residents visit (network)

Example: Unequal access to Resources and Services

Banks, alternative institutions and the spatial–temporal ecology of racial inequality in US cities [4]

How does living in minority neighbourhoods affect access to conventional banks versus alternative (predatory) financial institutions (AFIs) such as check cashers and payday lenders?. Use of Google Places API and routes to get those POIs and routes to them

Accessibility to financial institutions from a given block, from [4]

Example: Unequal access to Resources and Services

Banks, alternative institutions and the spatial–temporal ecology of racial inequality in US cities [4]

Predatory institutions are easier to get in neighborhoods with more minorities

Probability AFI access is faster by foot as a function of proportion of residents of white (left), black (center), and hispanic (right) populations, from [4]

Example: Impact of food environments in consumption of fast food

Effect of mobile food environments on fast food visits [5]

Use mobility data (Cuebiq) to see where people consume fast-food and what is the impact of the environments there. Traditionally this has been studied only around home. However, we found most fast-food consumption happens away from home.

Median distance to different type of places in the top 11 metro areas in the US, from [5]

Example: Impact of food environments in consumption of fast food

Effect of mobile food environments on fast food visits [5]

The impact of food environments we are exposed when we move around is huge: being in an area with 10% more fast-food increments the possibility of having fast-food by 20%

Impact (log-odds) of being exposed to fast-food environments in eating there, from [5]

Example: Impact of food environments in consumption of fast food

Effect of mobile food environments on fast food visits [5]

Efficient policies to increase consumption of healthy food should concentrate on behavioral spaces where people consume food and not only residential neighborhoods.

Impact of different interventions on food environments in visits to fast food places, from [5]

Example: Experienced segregation

Mobility patterns are associated with experienced income segregation in large US cities [6]

Economic segregation isn’t just limited to neighborhoods, it is part of the places we visit every day. How is people segregated when they move around?

Use Cuebiq GPS data to calculate places’ segregation and individual experienced segregation in the city

Place and individual income segregation, from [6]

Example: Experienced segregation

Mobility patterns are associated with experienced income segregation in large US cities [6]

Places are segregated differently. Even across the street places can be very different in terms of segregation.

Places have different income segregation, from [6]

Example: Experienced segregation

Mobility patterns are associated with experienced income segregation in large US cities [6]

Individuals are exposed to different segregation patterns as the move and visit places in the city. Most of experienced segregation is encoded in our lifestyles, not where we live.

What explains individual segregation [6]

Conclusions

• Sustainability and Inequality in urban areas are critical, pressing problems.

• The use of large-scale data and powerful descriptive, predictive, and causal methods can help understanding and alleviating those problems.

• Most of research in Computational Urban Science in those problems has to do with

  • Have more individual/temporal/spatial data about those problems
  • Have better understanding of residents’ decision-making to understand the drivers of those problems.
  • Have better tools to model and evaluate the impact of policies.

Further reading

General

• Big Data for Urban Sustainability A Human-Centered Perspective by Wang and Moriarty.
• Social Media Data for Urban Sustainability [7]
• Grand Challenges in Sustainable Cities and Health, by Vardoulakis et al. [2].

Experienced segregation

• Estimating experienced racial segregation in US cities using large-scale GPS data [8]
• Using human mobility data to quantify experienced urban inequalities [9]
• The great equalizer? Mixed effects of social infrastructure on diverse encounters in cities, [10]

Further reading

Environmental justice

• Environmental inequality in the neighborhood networks of urban mobility in US cities [3]
• PM2.5 polluters disproportionately and systemically affect people of color in the United States [11]

Energy and pollution patterns

• Gross polluters and vehicle emissions reduction [1]
• Planning for electric vehicle needs by coupling charging profiles with urban mobility [12]

References

[1]

M. Böhm, M. Nanni, and L. Pappalardo, “Gross polluters and vehicle emissions reduction,” Nature Sustainability, vol. 5, no. 8, pp. 699–707, Aug. 2022, doi: 10.1038/s41893-022-00903-x.

[2]

S. Vardoulakis and P. Kinney, “Grand Challenges in Sustainable Cities and Health,” Frontiers in Sustainable Cities, vol. 1, Dec. 2019, doi: 10.3389/frsc.2019.00007.

[3]

N. Brazil, “Environmental inequality in the neighborhood networks of urban mobility in US cities,” Proceedings of the National Academy of Sciences, vol. 119, no. 17, p. e2117776119, Apr. 2022, doi: 10.1073/pnas.2117776119.

[4]

M. L. Small, A. Akhavan, M. Torres, and Q. Wang, “Banks, alternative institutions and the spatial–temporal ecology of racial inequality in US cities,” Nature Human Behaviour, vol. 5, no. 12, pp. 1622–1628, Jul. 2021, doi: 10.1038/s41562-021-01153-1.

[5]

B. García Bulle Bueno et al., “Effect of mobile food environments on fast food visits,” Nature Communications, vol. 15, no. 1, p. 2291, Mar. 2024, doi: 10.1038/s41467-024-46425-2.

[6]

E. Moro, D. Calacci, X. Dong, and A. Pentland, “Mobility patterns are associated with experienced income segregation in large US cities,” Nature Communications, vol. 12, no. 1, pp. 1–10, Jul. 2021, doi: 10.1038/s41467-021-24899-8.

[7]

R. T. Ilieva and T. McPhearson, “Social-media data for urban sustainability,” Nature Sustainability, vol. 1, no. 10, pp. 553–565, Oct. 2018, doi: 10.1038/s41893-018-0153-6.

[8]

S. Athey, B. Ferguson, M. Gentzkow, and T. Schmidt, “Estimating experienced racial segregation in US cities using large-scale GPS data,” Proceedings of the National Academy of Sciences, vol. 118, no. 46, p. e2026160118, Nov. 2021, doi: 10.1073/pnas.2026160118.

[9]

F. Xu et al., “Using human mobility data to quantify experienced urban inequalities,” Nature Human Behaviour, pp. 1–11, Feb. 2025, doi: 10.1038/s41562-024-02079-0.

[10]

T. Fraser, T. Yabe, D. P. Aldrich, and E. Moro, “The great equalizer? Mixed effects of social infrastructure on diverse encounters in cities,” Computers, Environment and Urban Systems, vol. 113, p. 102173, Oct. 2024, doi: 10.1016/j.compenvurbsys.2024.102173.

[11]

C. W. Tessum, D. A. Paolella, S. E. Chambliss, J. S. Apte, J. D. Hill, and J. D. Marshall, “PM2.5 polluters disproportionately and systemically affect people of color in the United States,” Science Advances, vol. 7, no. 18, p. eabf4491, Apr. 2021, doi: 10.1126/sciadv.abf4491.

[12]

Y. Xu, S. Çolak, E. C. Kara, S. J. Moura, and M. C. González, “Planning for electric vehicle needs by coupling charging profiles with urban mobility,” Nature Energy, vol. 3, no. 6, pp. 484–493, Jun. 2018, doi: 10.1038/s41560-018-0136-x.