As climate change exacerbates environmental challenges associated with urban growth, green stormwater infrastructure (GSI) is a prevalent stormwater mitigation strategy to provide resilience and mitigate the impacts of development on flooding. In parallel, fully sustainable GSI systems must confront the challenges of historically unequitable distribution of infrastructure. The current data revolution has reached municipal stormwater programs; however, these programs are limited by a lack of knowledge of GSI life-cycle dynamics, high performance and emerging computational tools, and how to integrate new science into design and planning decisions. There is a scientific gap in the space formed among GSI design, performance function, and planning decisions that requires bridging hydrologic science, urban planning, and data analytics. This project leverages innovations in artificial intelligence (AI), advancements in the empirical and theoretical understanding of urban hydrologic science, and social data to produce a new model of GSI dynamics that considers social and environmental equity issues. This model will flip the paradigm of infrastructure planning and put the impact on society and the environment on par with engineering solutions to flooding. The model will be made available for use by public and private practitioners to plan, develop, and manage more sustainable and equitable GSI, and by researchers to deepen convergent knowledge of the complex social issues associated with urban flooding. 

The current state of GSI research is ripe for the application of AI techniques to advance GSI knowledge to discern key parameters, optimize GSI design and development, and enable future performance forecasts in a changing environment. For this project, civil engineers, computer scientists, and geographers are joining together to produce a new platform that uses AI in a dynamic environment with multiple data modalities, ranging from their spatial and temporal characteristics to data types. The research framework acknowledges the wider implications of GSI and its high interdependency and connection to the surrounding community and aims to improve social justice of GSI design through an equity-aware AI model. This project will use a large GSI monitoring relational database (housed at Villanova University) by combining GSI performance data and city-wide open data and applying machine learning methods to develop predictive models applicable across the US. This work targets advancing understanding of GSI dynamics by forecasting the performance of GSIs for a given array of conditions and constraints in urban settings to equitably maximize GSI community benefits. The project will support a diverse faculty team and engage students, urban communities, and industry and academic colleagues by: (1) creating state-of- the-art research and mentoring opportunities for graduate and undergraduate students from underrepresented backgrounds, (2) developing and delivering GSI learning modules for practitioners, and (3) integrating and promoting issues of equity and sustainability within urban stormwater management.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

One in 36 individuals in the US has autism spectrum disorder (ASD). Each year in the US, approximately 70,000 autistic children become autistic adults and face a litany of disheartening statistics regarding independent living, community participation, and employment. The estimated cost of supporting Americans with autism having limited employment prospects will grow to $461 billion per year by 2025. One key to addressing this civic challenge is employment; some 85 percent of autistic adults are un/under-employed, and adults with autism rate employment as their top concern for improved quality of life. However, a major impediment for autistic individuals to access work opportunities and a life of independence, is lack of independence with transportation; fewer than 30 percent of driving-age autistic individuals are licensed to drive. The CIVIC Stage 2 award to Vanderbilt University will support the rapid pilot deployment of the team’s AI-based Vehicle Technology Simulator with Behavioral Strategies (AI-VTSBS) system, specifically designed for the ASD population – comprising a virtual-reality driving simulator with artificial intelligence-based analysis and feedback, together with a curriculum built on a cognitive behavioral intervention for driving – to address this critical civic need. The project will perform community-based participatory research including multiple stakeholders to make the AI-VTSBS system adaptable to use within multiple employment contexts and multiple employment outcomes of relevance to stakeholder communities. 

The team led by Vanderbilt University and partner San Diego State University will build on its work on Stage 1 and will conduct a full Stage 2 pilot deployment with multiple types of civic partners and support providers – including community-based vocational training centers, behavioral health clinics, and secondary schools – toward an effective, low-cost, commercializable, integrated driving-instruction platform and curriculum, with a value proposition that offers increased independence and expanded career options for autistic people. The Stage 2 research pilot project will use an implementation science framework involving Exploration, Preparation, Implementation and Sustainment (EPIS) to specifically assess and pilot-test deployment factors with both qualitative and quantitative methods. Additionally, the AI-VTSBS technology may also be generalizable beyond adults with autism; some 1 in 6 people have a related neurodevelopmental disability (e.g., ADHD) or temporary cognitive impairment (e.g., traumatic brain injury) that manifest similar challenges for transportation independence. The CIVIC Stage 2 work will be integrated with the NSF NRT program in Neurodiversity Inspired Science & Engineering (NISE) through Vanderbilt University’s Frist Center for Autism & Innovation, thus providing advanced training for students in interdisciplinary research and translation.

CIVIC is a joint collaboration with Department of Energy, Department of Homeland Security, and the National Science Foundation

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

This Smart and Connected Communities award supports research that will develop systematic deployment tools that smart and connected communities can use to achieve their sustainable travel goals in a quantifiable manner by leveraging advances in information, communication and sensor technologies. While the deployment of advanced technological solutions offers great promise for communities to improve residents' quality of life and prosperity, they are faced with significant challenges in realizing these aspirations due to the diversity in technological and travel needs and barriers faced by the residents. Solutions to achieve sustainability objectives related to enhancing travel mobility, safety, equity, and access will be developed using the City of Peachtree Corners (GA) as an immersive living lab. They include building novel partnerships involving emerging micromobility services in the private sector and the well-established public transit modes. Further, they will involve personalized behavioral interventions to nudge and incentivize personal auto users to consider sustainable alternatives through seamless information provision. At the community level, public policy interventions will seek to enable flexible and novel travel alternatives while ensuring that all residents have access to timely travel-related information. For underserved and underrepresented residents, the solutions will include strategies to overcome information deserts in lower-income neighborhoods, age-related technology savviness issues for senior residents, and reduced access to smartphones and transportation options. These solutions will be developed using data collected from community residents and other sources, and deployed using an information design system that provides targeted information delivery to the various stakeholders in the community using multiple delivery mechanisms, including a community app.

This project will advance theory and deployment paradigms associated with holistic, community-level decision-making to achieve travel sustainability goals characterized by multiple, disparate objectives while meeting the needs and constraints of different stakeholders. In particular, it will address the challenges of how to integrate disparate, multi-source data from various stakeholders and use it to systematically generate multidimensional solution options (partnerships, behavioral interventions, policy interventions) to meet multiple sustainability objectives at the community level in a systematic, quantifiable manner over time. It will draw on methods from multi-objective and multi-agent optimization, machine learning, behavioral economics, and data and policy analytics, to generate the multidimensional solutions. Further, it will lead to novel paradigms and algorithms for the solution options themselves, and for the development of generalizable principles related to practical deployment frameworks in the inherently complex, multidimensional smart and connected communities. The project will also develop formal methods for information design and delivery that translate the multidimensional solutions into actionable information that is seamless for the various stakeholders.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

The broader impact/commercial potential of this Partnerships for Innovation - Technology Translation (PFI-TT) project lies in its potential to revolutionize surveillance systems and promote public safety while protecting privacy. By leveraging recent advances in Artificial Intelligence (AI), the project aims to detect real-time public safety threats by only focusing on behaviors and utilizing the existing surveillance cameras. This innovation addresses the pressing challenges of rising criminal activities and public safety threats in public spaces and private businesses. By focusing on behavioral abnormalities rather than individual identification, this project helps to remove biases and promote social equity. The proposed technology has a significant potential for commercialization, with applications in various sectors, including public agencies, private businesses, and critical infrastructure, enhancing security and improving public well-being. The project will foster training and leadership development in innovation and entrepreneurship by involving students and post-docs in meetings with stakeholders, attending industry events, and collaborating closely with the industries involved.

The proposed project aims to address the problem of inefficient and costly security measures by developing an innovative deep learning-based surveillance system. The project's successful implementation will foster the scientific and technological understanding of computer vision and deep learning, advancing the capabilities of surveillance systems and promoting innovation in the security industry. The project seeks to create a deep learning system capable of detecting behavioral anomalies in real-time by utilizing transformer-based architectures and identity-neutral visual feature embedding. The research objectives include analyzing complex human behavior without relying on personally identifiable information, developing a scalable technology, and conducting real-world pilots. The project aims to establish realistic metrics for evaluating detection reliability and resilience in real-world settings by integrating state-of-the-art AI advancements. Anticipated technical results include a novel anomaly detection dataset, a semi-supervised transformer-based video sequence learning approach and anomaly detection algorithm, and identity-neutral visual feature embedding advancements. The project's outcomes build upon previous NSF-funded research and will contribute to the scientific understanding of AI in surveillance applications.

Urban Air Mobility (UAM) envisions integrating the skyscape into the transportation network and encompasses services such as delivery drones, on-demand shared mobility by Vertical-Take Off and Landing (VTOL) aircraft for intra-city passenger trips, and, in the longer run, electric and autonomous VTOLs. This possible modal alternative provides a safe, reliable, and environmentally sound option to reduce surface-level congestion. Nevertheless, the history of transportation infrastructure development shows that it is imperative to design transportation infrastructures with the community to find the best balance between these sociotechnical requirements. Much research shows that the design of transportation systems has a long-lasting, often discriminatory effect that reinforces existing socio-economic inequality. As UAM is being developed as a new transportation mode, we are at an opportune moment to design its infrastructure to provide effective and equitable air mobility for all, avoiding our past mistakes. This project will focus on understanding the preferences, attitudes, and concerns of all stakeholders of UAM, including the potential users of UAM, the general public in different communities who may be positively and/or adversely affected by UAM, policymakers, and city planners. The knowledge elicited from the stakeholders will guide the design of an open-source Computer Aided Planning tool that policy-makers and urban planners can use to design UAM infrastructure that accommodates communities’ priorities and enables transportation equity. While the timeline for UAM may be in the future, its deployment may entail significant future investment in infrastructure which makes inclusion of equity considerations and early community engagement critical.

We propose a ''Community-in-the-Loop Integrative Framework for Fair and Equitable Urban Air Mobility (UAM) Infrastructure Design''. Our integrative framework will develop methods to engage with key stakeholders to address significant socio-technical challenges, including (a) understanding the community preferences and desiderata in terms of necessary considerations for equitable mobility, (b) developing novel machine learning techniques to generate design options that optimize for community desiderata efficiently and (c) devising community-driven evaluative measures and trade-off decision mechanisms. We address these challenges by drawing from urban and transportation engineering, aerospace, and computer and information sciences. The final product of our framework is an open-source Computer Aided Planning tool called VertiCAP. VertiCAP will be equipped with novel machine learning-based algorithms to navigate complex design space options, including long-term decisions (i.e., allocation of UAM airports, also known as vertiports), medium-term decisions (i.e., design of air space), and short-term decisions (i.e., air-traffic control). We will establish a ''community council'' representing different stakeholders. Through continuous interactions with the community council, we will evaluate and demonstrate the effectiveness of the developed VertiCAP tool in the City of Austin, TX and Southern California.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

When a disaster strikes, communities often become isolated and citizens come together to help each other: people share resources, pass along information, and take on tasks that are outside of their usual domains. These activities have been reported in both academic literature and anecdotal documents. Some examples include: New Yorkers’ sharing private vehicles and boats during the 2005 MTA strike that crippled NYC transit services; and neighbors helping neighbors escape from flooding caused by 2016’s Hurricane Matthew using rafts improvised from inflatable mattresses in Rowland, NC. These peer-to-peer resource sharing activities fill important gaps during times of disaster that cannot be fulfilled by emergency response agencies. This project helps fill this gap by working with urban and rural, higher- and lower-income communities in Washington State to understand and advance more effective local information and resource dissemination during a disaster. The project integrates hardware, robust communication technologies, social capacities, and spatial conditions to leverage and enhance place-based social networks for information-resource sharing; and investigate a little-studied scientific frontier intersecting communications, sharing, and disaster resilience. The results of the project will be scalable and useful on a daily and emergency basis to communities that increasingly face natural disaster risks and are interested in enhancing their resilience through information and resource sharing.

More specifically, the project will co-design with the two communities and conduct research in four thrusts. Thrust 1—robust communications, will develop robust off-grid community-based networks that are owned and operated by the community. Thrust 2—building community social networks for information-resource sharing, will conduct surveys to collect information about people’s sharing behavior and their social ties within a community, and develop novel models to infer community-based social networks. Thrust 3—community-based information-resource sharing, will develop models and strategies that will lead to efficient information-resource sharing. The key hypothesis is that social network structures affect the optimality and stability of information-resource sharing. Thrust 4 (Dynamic Map your Neighborhood) integrates the results of Thrusts 1-3 and uses them to co-design and pilot-test applications with two communities in WA (urban and rural). The diverse team expertise facilitates knowledge and methods across disciplines through the design of robust communication technologies, and novel ways to solicit social ties information and information-resource sharing models that considers both model optimality and human inputs (e.g., leader nominations from the communities).

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Prescribed fires have long been used by ranchers and farmers in the Great Plains as a land management tool. They help farming and grazing by replenishing the soil, increasing forage production, and protecting prairies from invasive overgrowth. They are also used by rural and Wildland Urban Interface (WUI) communities to remove built-up fuels for reducing risks of wildfires. Despite the many benefits of prescribed fires, there are safety and environmental concerns for prescribed burn events. On the safety aspect, an escaped fire or a fire reignited from smoldering fuels can become uncontrolled and result in severe property damages and injuries to people. On the environmental aspect, smoke from prescribed fires causes air pollution for local communities and communities downwind. To manage and minimize these concerns, optimal planning and execution of prescribed fires are crucial. The objective of this project is to develop a community sensing, planning, and learning infrastructure to support smart and safe prescribed burning for communities that use prescribed fires for rangeland and wildfire risk management. The developed infrastructure will be integrated into a cloud-based platform to support landowners to optimally plan and operate prescribed burns, collect and share data about burning, and train fire operators to learn the most effective ways of burning. The project will also promote technology awareness for building smart communities in rural areas, by increasing partnerships among academia, rural communities, and local governments.

The integrated research of this project includes: 1) technical research on multi-scale sensing and data fusion, data-driven burn condition modeling, grassland fuel mapping & hotspot detection, and fire behavior modeling and simulation; 2) social science research that addresses the knowledge gap on how communities engage with and coordinate burn practices through the use of technology; and 3) community engagement that develops tools, data repositories, and activities to support communities’ smart and safe prescribed burning. The multiscale sensing and data fusion integrate data from heterogeneous sources including satellite remote sensing, unmanned aircraft systems, and crowdsourced reports. We will work with two communities in Kansas to evaluate and demonstrate the developed research: 1) The Gyp Hills community represents a rangeland community where an average prescribed fire covers over hundreds of acres for grasslands primarily used for grazing; 2) the Eastern Kansas community represents a suburban WUI community where prescribed fires are employed at a smaller scale.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.