Sustainability

Using machine learning to understand causal relationships between urban form and travel CO2 emissions across continents

Wagner, Felix
Nachtigall, Florian
Franken, Lukas
Milojevic-Dupont, Nikola
Pereira, Rafael H. M.
Koch, Nicolas
Runge, Jakob
Gonzalez, Marta
Creutzig, Felix
2023

Climate change mitigation in urban mobility requires policies reconfiguring urban form to increase accessibility and facilitate low-carbon modes of transport. However, current policy research has insufficiently assessed urban form effects on car travel at three levels: (1) Causality -- Can causality be established beyond theoretical and correlation-based analyses? (2) Generalizability -- Do relationships hold across different cities and world regions? (3) Context specificity -- How do relationships vary across neighborhoods of a city? Here, we address all three gaps via causal graph...

Urban Science: Integrated Theory from the First Cities to Sustainable Metropolises

Lobo, José
Alberti, Marina
Allen-Dumas, Melissa
Arcaute, Elsa
Barthelemy, Marc
Bojorquez Tapia, Luis A.
Brail, Shauna
Bettencourt, Luis
Beukes, Anni
Chen, Wei-Qiang
Florida, Richard
Gonzalez, Marta
Grimm, Nancy
Hamilton, Marcus
Kempes, Chris
Kontokosta, Constantine E.
Mellander, Charlotta
Neal, Zachary P.
Ortman, Scott
Pfeiffer, Deirdre
Price, Michael
Revi, Aromar
Rozenblat, Céline
Rybski, Diego
Siemiatycki, Matthew
Shutters, Shade T.
Smith, Michael E.
Stokes, Eleanor C.
Strumsky, Deborah
West, Geoffrey
White, Devin
Wu, Jingle
Yang, Vicky Chuqiao
York, Abigail
Youn, Hyejin
2020

Urban science seeks to understand the fundamental processes that drive, shape and sustain cities and urbanization. It is a multi/transdisciplinary approach involving concepts, methods and research from the social, natural, engineering and computational sciences, along with the humanities. This report is intended to convey the current “state of the art” in urban science while also clearly indicating how urban science builds upon and complements (but does not replace) prior work on cities and urbanization in many other disciplines. The report does not aim at a fully comprehensive synopsis of...

Sidewalk networks: Review and outlook

Rhoads, Daniel
Rames, Clément
Solé-Ribalta, Albert
González, Marta C.
Szell, Michael
Borge-Holthoefer, Javier
2023

From a transport perspective, increasing active travel –and walking in particular– is crucial for the future of sustainable cities, as reflected in global decarbonisation policies and agendas. Further, walking is much more than a mere mode of transport: it provides a fundamental social function, fostering vibrant cohesive communities. Arguably, walking and its associated infrastructure –sidewalks– should rank among the highest priorities for planning authorities. However, efficiency- and speed-driven urbanisation has gradually reallocated street space to private cars, leading to...

Dimension reduction approach for understanding resource-flow resilience to climate change

Salgado, Ariel
He, Yiyi
Radke, John
Ganguly, Auroop Ratan
Gonzalez, Marta C.
2024

Networked dynamics are essential for assessing the resilience of lifeline infrastructures. The dimension-reduction approach was designed as an efficient way to map the high-dimensional dynamics to a low-dimensional representation capturing system-level behavior while taking into consideration network structure. However, its application to socio-technical systems has not been considered yet. Here, we extend the dimension-reduction approach to resource-flow dynamics in multiplex networks. We apply it to the San Francisco fuel transportation network, considering the flow between refineries,...

DeepAir: deep learning and satellite imagery to estimate high-resolution at scale

Guo, Wenxuan
Hu, Zhaoping
Jin, Ling
Xu, Yanyan
Gonzalez, Marta C
2025

Air pollution, specifically PM
2.5
, has become a significant global concern owing to its detrimental impacts on public health. Even so, the high-resolution monitoring of air pollution is still a challenge on a global scale. To cope with this, machine learning (ML) techniques have been utilized to infer the concentration of air pollutants at a fine scale. In this study, we propose
DeepAir
, a learning framework for estimating PM
2.5
concentrations at a fine scale with sparsely distributed observations.
DeepAir
integrates a pre-trained convolutional neural...

A mesoscopic model of vehicular emissions informed by direct measurements and mobility science

Öztürk, Ayşe Tuğba
Kasliwal, Aparimit
Fitzmaurice, Helen
Kavvada, Olga
Calvez, Philippe
Cohen, Ronald C.
González, Marta C.
2025

Vehicle emissions pose a significant challenge for cities worldwide, yet a comprehensive analysis of the relationship between mobility metrics and vehicle emissions at scale remains elusive. We introduce the Mobile Data Emission System (MODES), a framework that integrates various sources of individual mobility data on an unprecedented scale. Our model is validated with direct measurements from a network of high-density sensors analyzed before and during the COVID-19 pandemic. MODES is used as a laboratory for scaling analysis. Informed by millions of individual trips at a metropolitan...

A cluster-based appliance-level-of-use demand response program design

Wu, Jiaman
Lu, Chenbei
Wu, Chenye
Shi, Jian
Gonzalez, Marta C.
Wang, Dan
Han, Zhu
2024

The ever-intensifying threat of climate change renders the electric power system undergoing a profound transition toward net-zero emissions. Energy efficiency measures, such as demand response, facilitate the transformation to jointly relieve consumers’ financial burden and improve the operability of the electric power grid, in a carbon-free way. In this paper, we design a cluster-based appliance-level-of-use demand response program, based on the massive volume of appliance consumption data, to expand the role demand response can play in the power grid’s low-carbon transition. We...

Optimizing Urban Bus Transit Network Design Can Lead to Greenhouse Gas Emissions Reduction

Griswold, Julia B.
Sztainer, Tal
Lee, Jinwoo
Madanat, Samer
Horvath, Arpad
2017

The high contribution of greenhouse gas (GHG) emissions by the transportation sector calls for the development of emission reduction efforts. In this paper, we examine how efficient bus transit networks can contribute to these reduction measures. Utilizing continuum approximation methods and a case study in Barcelona, we show that efforts to decrease the costs of a transit system can lead to GHG emission reductions as well. We demonstrate GHG emission comparisons between an optimized bus network design in Barcelona and the existing system. The optimization of the system network design...

Vehicle Emissions Estimation Under Oversaturated Conditions Along Signalized Arterials

Skabardonis, Alexander
Geroliminis, Nikolas
Christofa, Eleni
Transportation Research Board
2012

Traditionally, the amount of air pollutant emissions from motor vehicles—hydrocarbons, carbon monoxide, and oxides of nitrogen—is estimated from emission factors based on trip and vehicle miles traveled and aggregate measures of vehicle activity (e.g., average vehicle speed). This method is not reliable for urban networks, as it does not consider the effect of traffic signals and congestion. There is a need to predict vehicle activity by mode of operation, i.e., time spent in cruise, acceleration, deceleration, and idle to obtain improved emission estimates. An analytical model for...

Traffic signal timing as a transportation system management measure : the California experience

Deakin, Elizabeth A
Skabardonis, Alexander
May, Adolf D
1986

Traffic signal retiming has long been suggested as a means of improving traffic operations and reducing fuel consumption and emissions. However, few local agencies have been able to muster the resources to systematically retime their signals. In California, a statewide program--the Fuel Efficient Traffic Signal Management (FETSIM) Program--was established to address this need. The FETSIM Program provides funds, training, and technical assistance to local agencies to retime their signal systems for greater operating efficiency. To date, 62 local jurisdictions have participated in the...