Connecting the Smart-City Paradigm with a Sustainable Urban Infrastructure Systems Framework to Advance Equity in Communities
This project will investigate a smart urban infrastructure systems framework for advancing access and wellbeing in cities. With transformative new infrastructures (e.g., smart electricity grid, urban farms) on the horizon, this research will provide new perspectives on how the future spatial deployment of these new infrastructures in cities will shape wellbeing, health, and the environmental sustainability of outcomes in the different areas of cities. The project advances basic research in multiple disciplines including environmental and civil engineering, computer science, urban planning and public policy. It will create a unique public database, establish citizen science protocols, and advance the science of smart sustainable urban systems through knowledge co-production with cities engaged in infrastructure planning. The project will engage in educational activities through interdisciplinary training for graduate students and professionals in urban planning, policy and sustainability. Furthermore, a strong component of citizen science engagement is involved through K-12 teachers and students, particularly in schools with underrepresented populations.
Environmental sustainability, human health and wellbeing outcomes in cities are significantly shaped by key physical infrastructure provisions of water, energy, food, shelter, transportation-communications, sanitation waste management and public spaces, as well as their interactions with the social, environmental and urban form parameters. The investigators will conduct an interdisciplinary, community-engaged research project in the cities of Minneapolis, St Paul, and Tallahassee. The research will engage four themes: (a) Develop the first comprehensive fine-scale intra-urban database of over 100 social-ecological-health and well-being parameters via novel citizen science/crowdsourcing campaigns using low cost sensors; (b) Develop advanced computational algorithms to uncover hotspots and spatial correlations in the data and evaluate data-driven as well as discipline-inspired access and wellbeing hypotheses; (c) Using outcomes from (a) and (b) develop connected multi-infrastructure futures scenario models with new infrastructures through shared scenario visioning exercises, and evaluate policy learning and value of information; (d) Focus on education and workforce development for middle-high schoolers, graduate students and sustainability professionals. Outcomes from this research will be useful for informing citizens and policymakers about smart infrastructure transition being planned in cities.
-
Performance PeriodSeptember 2017 - August 2022
-
University of Minnesota-Twin Cities
-
Award Number1737633
-
Lead PIShashi Shekhar -
Co-PIVenkatesh Merwade
-
Co-PITian Tang
-
Co-PIRichard Feiock
-
Co-PIJulian Marshall
-
Co-PIAnu Ramaswami
Project Material
- Statistically-Robust Clustering Techniques for Mapping Spatial Hotspots: A Survey
- SAMCNet: Towards a Spatially Explainable AI Approach for Classifying MxIF Oncology Data
- Examining motivations for owning autonomous vehicles: Implications for land use and transportation
- Encouraging voluntary government action via a solar-friendly designation program to promote solar energy in the United States
- Autonomous vehicle policies with equity implications: Patterns and gaps
- A data framework for assessing social inequality and equity in multi‐sector social, ecological, infrastructural urban systems: Focus on fine‐spatial scales
- Understanding COVID-19 Effects on Mobility: A Community-Engaged Approach
- Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach
- An Alternative Approach for Improving Prediction of Integrated Hydrologic‐Hydraulic Models by Assessing the Impact of Intrinsic Spatial Scales
- The impacts of vehicle automation on transport-disadvantaged people
- Spatial Dimensions of Algorithmic Transparency: A Summary
- SRNet: A spatial-relationship aware point-set classification method for multiplexed pathology images.
- Measuring social equity in urban energy use and interventions using fine-scale data
- Perceptions, motivators and barriers of using city management applications among citizens: a focus group approach
- Discovering regions of anomalous spatial co-locations
- Exploring the interaction effect of poverty concentration and transit service on highway traffic during the COVID-19 lockdown
- Discovering Spatial Mixture Patterns of Interest
- Closing the Gap or Widening the Divide: The Impacts of <scp>Technology‐Enabled</scp> Coproduction on Equity in Public Service Delivery
- Technical perspective: Progress in spatial computing for flood prediction
- Developing a Low-Cost Passive Method for Long-Term Average Levels of Light-Absorbing Carbon Air Pollution in Polluted Indoor Environments
- Data Science for Earth: An Earth Day Report
- Discovering Interesting Subpaths with Statistical Significance from Spatiotemporal Datasets
- A Computationally Efficient and Physically Based Approach for Urban Flood Modeling Using a Flexible Spatiotemporal Structure
- Preparing Transit in the Advent of Automated Vehicles: A Focus-group Study in the Twin Cities
- A Unified Framework for Robust and Efficient Hotspot Detection in Smart Cities
- Linear Hotspot Discovery on All Simple Paths: A Summary of Results
- Revolutionizing Tree Management via Intelligent Spatial Techniques
- Significant DBSCAN towards Statistically Robust Clustering
- Flood inundation modeling and mapping by integrating surface and subsurface hydrology with river hydrodynamics
- A locally-constrained YOLO framework for detecting small and densely-distributed building footprints
- A Nondeterministic Normalization based Scan Statistic (NN-scan) towards Robust Hotspot Detection: A Summary of Results
- Big Spatiotemporal Data Analytics: a research and innovation frontier
- Analyzing Domain Knowledge for Big Data Analysis: A Case Study with Urban Tree Type Classification.
- Intelligent systems for geosciences: an essential research agenda
- An unsupervised augmentation framework for deep learning based geospatial object detection: a summary of results
- A TIMBER Framework for Mining Urban Tree Inventories Using Remote Sensing Datasets
- Transforming Smart Cities with Spatial Computing
- The Science, Policy and Governance of Smart and Sustainable Cities: Policy Design and Voluntary Compliance in Energy Programs
- Avoidance Region Discovery: A Summary of Results
- Transdisciplinary Foundations of Geospatial Data Science
- Spatial Ensemble Learning for Heterogeneous Geographic Data with Class Ambiguity: A Summary of Results
- Significant Linear Hotspot Discovery
Shashi Shekhar joined the Department of Computer Science & Engineering as an assistant professor in 1989 and was later promoted to a professor. He was named a McKnight Distinguished University Professor in 2005 and a Distinguished University Teaching Professor in 2015. Shekhar was also named a fellow of the IEEE Computer Society and the American Association for Advancement of Science. Prior to his time at the University, he was a software engineer at Taj Services Ltd. in 1984 and a post-graduate researcher at the University of California, Berkeley from 1985-99. He is currently serving as an Associate Director of the College of Science and Engineering Data Science Initiative and an ADC/DSI chair (9/2022 - 8/2025). He is also serving as the Director of a National AI Research Institute, namely, AI-CLIMATE (AI Institute for Climate-Land Interactions, Mitigation, Adaptation, Tradeoffs and Economy) starting June 2023.