Third CITIES Symposium

Bios and Abstracts

• Satish Ukkusuri

  Bio: Satish Ukkusuri is a Hubert and Audrey Kleasen Professor in the Lyles School of Civil and Construction Engineering at Purdue University, Director of the Urban Mobility Networks and Intelligence (UMNI) Lab and Director of the Purdue Transportation Cybersecurity and Resilience Center. His research is in the area of interdisciplinary transportation networks with current interests in data driven mobility solutions, disaster management, resilience of interdependent networks, connected and autonomous traffic systems, shared mobility platforms, and smart logistics. He is a University Faculty Scholar (2017-2022), ASCE Fellow, Fulbright Fellow, a selectee of the National Academy of Engineering (NAE) JAFOE conference (2016), a selectee of the National Academy of Science (NAS) Arab American Frontiers of Science, Engineering and Medicine in 2017 and a CUTC/ARTBA Faculty Award (2011) among other awards. He has published more than 350 peer reviewed papers in journals such as PNAS, Nature Communications, Nature and discipline specific journals. He is the co-Editor in Chief of the Journal Data Science for Transportation (Springer) and co-Editor in Chief of the ACM Journal of Autonomous Transportation.

  Title: AI for Transportation Sustainability Development Goals – Promise and Challenges

  Abstract: Artificial Intelligence based data driven modeling has gained significant attention in the last few years for modeling transportation systems. Using real world use cases from the USA, India and Africa, this presentation will demonstrate the promise and challenges of AI based modeling for travel time estimation, OD estimation, equity assessment, transit planning, COVID-19 impacts and investment analysis. The tradeoffs between model versus data driven modeling will be discussed along with new opportunities and future directions for transportation AI.

• Andres Sevtsuk

  Bio: Andres Sevtsuk is Head of the City Design and Development Group and an Associate Professor of Urban Science and Planning at the Department of Urban Studies and Planning, where he also leads the City Form Lab. His research focuses on the influence of urban form on sustainable travel behavior and on public qualities of built environments--urban ground floors, main streets, and amenity location patterns. His work contributes to making city environments more walkable, sustainable and equitable, bridging the fields of urban design, spatial analytics and mobility research. Andres is the author of the Urban Network Analysis framework and software tools, used by researchers and practitioners around the world to model pedestrian activity in cities and to study coordinated land use and transportation development in ways that reduce transportation carbon emissions.

  He has published a book entitled “Street Commerce: Creating Vibrant Urban Sidewalks” with Penn Press and before that, "Urban Network Analysis: Tools for Modeling Walking and Biking in Cities" with Tianjin University Press. Andres has collaborated with a number of city governments, international organizations, planning practices and developers on urban designs, plans and policies in both developed and rapidly developing urban environments, including those in US, Indonesia, Australia, Lebanon, Estonia and Singapore. He has led various international research projects, published in planning, transportation and urban design journals, and received numerous awards for his work.

  Title: The Green Mobility City: Tools for representing and modeling built environments at the pedestrian scale

  Abstract: The global climate-change crisis, along with public health and economic competitiveness challenges in cities around the world have underscored the need for analytic tools and models to examine the relationship between city design and sustainable mobility. In this presentation i present the Urban Network Analysis framework for modeling land-use and transportation interactions at the pedestrian scale, which enable planners and policy makers to measure pedestrian access to urban destinations and to model the impacts of land use and infrastructure changes on pedestrian mobility. Such analyses can enable planners, designers and policy makers to prioritize projects that increase sustainable mobility outcomes.
  

• Serge Hoogendoorn

  Bio: Professor Serge P. Hoogendoorn is an expert in the field of traffic and transportation engineering. He is a distinguished professor in Smart Urban at Delft University of Technology in the Netherlands. With a strong focus on traffic flow theory, pedestrian and crowd dynamics, and intelligent transportation systems, Professor Hoogendoorn has significantly contributed to advancing knowledge in traffic and transportation domain. His research encompasses the development of mathematical models and simulation tools to understand and improve traffic flow and pedestrian movement in urban environments. He has published extensively in academic journals and has been involved in numerous national and international research projects aimed at enhancing the efficiency and safety of transportation networks.

  Professor Hoogendoorn is also recognized for his work on data-driven approaches and the application of artificial intelligence in transportation systems. His efforts in integrating traditional engineering principles with innovative data science methodologies are testaments of his the pursuit for smarter, more efficient urban transportation solutions.

  Title: The Transformative Role of Data and AI in Smart Urban Mobility

  Abstract: Artificial Intelligence (AI) and data-driven methodologies are revolutionizing the field of urban transportation. In this keynote, Professor Serge Hoogendoorn explores how data and AI are reshaping smart urban mobility while highlighting the unique challenges inherent to the traffic and transportation domain. By debunking some of the unfounded promises, he emphasizes that despite the perception of AI as a panacea for transportation issues, traditional engineering principles remain crucial due to the sector's specific characteristics.

  The presentation will delve into the value of data collection in smart cities, showcasing examples where comprehensive datasets enable innovations like digital twins. Through a selection of projects, Professor Hoogendoorn will illustrate the added value of data and AI in addressing complex problems such as crowd risk management and planning, network traffic flow management, and real-time vehicle dispatching. These case studies will not only demonstrate the value of data and AI applications but also discuss the typical challenges faced when integrating AI into transportation systems.

  A significant focus will be on data-driven decision support for real-time interventions and mobility planning. The talk will emphasize the importance of explainable or interpretable AI, underscoring the need for transparency and trust in AI solutions deployed within urban mobility networks. By bridging data science and traditional transportation engineering, this keynote aims to provide a balanced perspective on leveraging AI to enhance, rather than replace, existing methodologies in the pursuit of smarter, more efficient urban transportation systems.

• Gerard Torrats-Espinosa

  Bio: Gerard Torrats-Espinosa is an Assistant Professor of Sociology at Columbia University and a member of the Columbia University Data Science Institute. He uses causal inference and machine learning methods to study urban inequality, violence, and racial disparities in policing. His work has been published or is forthcoming in the American Journal of Sociology, the American Sociological Review, Demography, the Journal of Urban Economics, PLoS One, the Proceedings of the National Academy of Sciences, and Social Science & Medicine, among other peer-reviewed journals. He received his Ph.D. in Sociology from New York University in 2019, a Master’s in Public Policy from the Harvard Kennedy School of Government in 2014, and a BS in Engineering from the Polytechnic University of Catalonia in 2004.

  Title: The Social Consequences of Militarized Policing in American Cities

  Abstract: In the wake of the War on Drugs and the subsequent expansion of “tough-on-crime” policies, American law enforcement has increasingly adopted militarized policing practices. These practices, once reserved for combat zones, are now frequently used in civilian neighborhoods, particularly during the execution of search warrants and raids. While such militarized policing practices are often defended as necessary for officer safety and operational efficiency, their use raises significant questions about fairness and equity. This talk will assess the spatial concentration of militarized police raids, highlighting how racial minorities are disproportionately exposed to these aggressive forms of policing. It will also discuss the broader implications of these policing tactics on community well-being, focusing on the psychological impacts on residents. Finally, the talk will examine how militarized policing erodes trust in government and law enforcement among residents of affected neighborhoods and the broader implications this has for societal perceptions of justice and fairness.

• Elizabeth Roberto

  Bio: Elizabeth Roberto is an Assistant Professor in the Department of Sociology and the founding co-Director of the Center for Computational Insight on Inequality and Society at Rice University. She has research interests in social and spatial inequality, a substantive focus on residential segregation, and methodological expertise in computational social science and quantitative methods. Her research uses innovative methods to examine the complex relationship between the social and built environment of cities. She received a Ph.D. in sociology from Yale University and a M.P.A. and B.A. from George Washington University, and she was a Postdoctoral Fellow in the Department of Sociology at Princeton University. Her research has been supported by the James S. McDonnell Foundation, American Sociological Association, and the National Academies.

  Title: The Infrastructure of Inequality: Road Network Disconnectivity and Racial Disparities in U.S. Cities

  Abstract: Racism, discriminatory practices, and systematic exclusion can take lasting physical form in the built environment. Prominent examples in the United States include the segregationist mortgage lending policies that contributed to White suburbanization and Black ghettoization, and the highway construction and urban renewal projects that razed neighborhoods, displaced Black residents, and systematized physical divisions between racial groups. This study analyzes a key, yet often overlooked, feature of built environments, road network connectivity, and its relationship to racial residential segregation and disparities in access to local public goods. We apply a novel computational approach for constructing counterfactual road networks by identifying road segments that we would expect to exist, given the surrounding infrastructure, but are nonetheless missing. This allows us to identify sites of unexpected disconnectivity and analyze differences in racial composition, segregation, and access to public goods for nearby areas. We find that unexpected disconnectivity is more likely between areas with different racial compositions, and is associated with higher levels of local- and city-level segregation and racial disparities in access to libraries and emergency services. Rather than focusing only on the observed built environment, this study considers what is missing and seeks to uncover the mechanisms and consequences of racist infrastructure.

• Eduardo Tapia

  Bio: Eduardo Tapia holds a Ph.D. in Computational Sociology from the Autonomous University of Barcelona. He is an associate professor at the Institute for Analytical Sociology at Linkoping University, Sweden. As a scholar of segregation, he applies statistical methods to analyze residential and school choices and employs large-scale simulation models to evaluate segregation dynamics and the potential effects of policy interventions.

  Title: Neighborhood Media Reputation and Urban Residential Segregation

  Abstract: Residential segregation evolves as households selectively move within the city. Existing literature on segregation has demonstrated the pivotal role of various factors, including household ethnicity, socioeconomic status, proximity to neighborhoods, family connections, and the ethnic-socioeconomic characteristics of neighborhoods, in influencing residential mobility. However, a significant aspect often overlooked in the literature on residential mobility—and consequently in segregation studies—is the influence of neighborhood reputation. This refers to how neighborhoods are perceived in public opinion and how such perceptions impact household residential choices. This paper addresses this oversight by examining the effects of neighborhood reputation on urban residential mobility in Stockholm, Sweden.

• Remco Chang

  Bio: Remco Chang is a Professor in the Computer Science Department at Tufts University. He received his BA in Computer Science and Economics from Johns Hopkins University in 1997, his MSc from Brown University in 2000, and his PhD from the University of North Carolina (UNC) at Charlotte in 2009. Prior to his PhD, he worked at Boeing, developing real-time flight tracking and visualization software, and later served as a research scientist at UNC Charlotte. His research interests include visual analytics, information visualization, human-computer interaction (HCI), and databases. His work has been supported by the NSF, DARPA, Navy, DOD, Walmart Foundation, Merck, DHS, MIT Lincoln Lab, and Draper, and he is a co-founder of two startups, Hopara.io and GraphPolaris. He has received best paper, best poster, and honorable mention awards at InfoVis, VAST, CHI, EuroVis.

  He served as program chair of the IEEE VIS conference in 2018 and 2019 and is currently the general chair of VIS in 2024. Additionally, he is an associate editor for the ACM TiiS and IEEE TVCG journals and received the NSF CAREER Award in 2015. He has mentored 11 PhD students and postdocs who now hold faculty positions at institutions such as Smith College (x2), DePaul University, Washington University in St. Louis, University of Washington, University of San Francisco, University of Colorado Boulder, WPI, San Francisco State, the University of Utrecht, and Brandeis, as well as 7 researchers working in companies and government agencies like Google, Draper, Facebook, MIT Lincoln Lab (x2), the National Renewable Energy Lab, and Idaho National Lab.

  Title: Urban Data Visualization and Exploration Using Neural Network Surrogates

  Abstract: Urban data exploration combines information about physical locations with abstract data on the environment and people. This data is highly heterogeneous, multivariate, and often extremely large and complex, making its visualization and exploration challenging. In this talk, I present early work on visualizing urban data, followed by recent advancements in using neural networks to develop surrogate models that can effectively replace the original datasets. These trained networks are significantly more compact—for instance, a 1MB neural network can substitute a 1.8GB database with minimal loss of information—while still enabling users to uncover hidden spatial and temporal patterns. The talk concludes with reflections on the role of visualization design, its integration with data management, and the challenges and opportunities of visualizing large, complex databases.

• Zachary Ives

  Bio: Zachary Ives is the department chair and Adani President's Distinguished Professor of Computer and Information Science at the University of Pennsylvania. Zack's research interests include data integration and sharing, data provenance and trustworthiness, machine learning systems, and their applications to scientific discovery. He is a Fellow of the Association for Computing Machinery and a recipient of an IEEE Technical Committee on Data Engineering Education Award. He has also received the NSF CAREER award, as well as multiple best-paper or most-influential-paper awards for his research. He is a co-author of the textbook Principles of Data Integration, and has served as program co-chair and general chair for the ACM SIGMOD Conference.

  Title: Enabling Data-Driven Decisions at Scale

  Abstract: The vision of integrating live data streams, data from unstructured sources on the Web, and data from heterogeneous sources — all in support of better decisions, dashboards, and models — seems for the first time to be within reach. Modern AI techniques such as large language models and learning-driven optimizers, combined with appropriate human feedback, hold tremendous promise for realizing this vision. I will describe our ongoing efforts to build systems that provide integrated views over “open-world” data to enable AI applications and AI-driven decision-making.