Skip to main content
Data Science and AI Academy

Seed Grant Awardees

Every year the Data Science and AI Academy awards seed grants to help support interdisciplinary data science research efforts. Below is a list of all awardees and the projects funded.

2024 Awardees

  • PI: Yang Cheng, College of Humanities and Social Sciences
  • Co-PIs:
    • William Rand, Poole College of Management
    • Florence Martin, College of Education
  • Awarded: $35,000
  • Abstract: The rise of deepfake technology poses significant challenges in distinguishing between genuine and manipulated content, leading to widespread mis/disinformation that undermines trust in public discourse. This project aims to address these challenges by developing a comprehensive framework for analyzing the impact of misinformation, particularly deepfakes, on public perceptions and behaviors. Utilizing a mixed-methods approach, we will conduct surveys, focus groups, and educational workshops to enhance media literacy and critical evaluation skills among students and community members. Our objectives include understanding the characteristics of mis and disinformation, examining user psychological factors, and fostering a culture of informed decision-making. The anticipated outcomes include improved detection skills, heightened awareness of misinformation risks, and enhanced media literacy in the face of AI-generated content.
  • PI: Sarah Rhea, College of Veterinary Medicine
  • Co-PIs:
    • Brian Reich, College of Sciences
    • William Rand, Poole College of Management
    • Cristina Lanzas, College of Veterinary Medicine
  • Awarded: $40,000
  • Abstract: Today, the US population is older than ever. The cohort of people 85 years of age, who have the highest need for nursing home (NH) and other long-term care services, is predicted to triple by 2050. Currently, >3M Americans receive NH care annually. Each year, >1.5 M healthcare-associated infections (HAIs) occur in NHs. Staff working in NHs often struggle to effectively prevent HAIs in their facilities, a challenge magnified during the COVID-19 pandemic. Clinical risk prediction tools can support healthcare providers in decision-making while caring for NH patients. However, no validated or broadly used clinical HAI risk prediction tools exist for the NH setting. Our proposed project lays the groundwork to address this resource gap by establishing a collaborative of interdisciplinary researchers from three Colleges to tackle the application of artificial intelligence (AI) and machine learning (ML) for improved patient safety. We propose to link individual-level Medicare data to aggregate facility- and community-level data; build a random forest model to predict HAIs in NH patients; and employ double machine learning to facilitate model explainability and examine hypothetical risk under an intervention. Our project will culminate in a NCSU networking event to foster collaboration for interdisciplinary AI/ML research for patient safety. The project will move us closer to increasing accessibility of AI technology to healthcare providers in NHs, ultimately enhancing patient safety and improving health outcomes. Additionally, this project will support our pursuit of R01 funding through the Agency for Healthcare Research & Quality to continue working on this important issue.
  • PI: Mikhail Gilman, College of Sciences
  • Co-PIs:
    • Justin Matthew, University College
    • Anatoly Larkin, University College 
  • Awarded: $27,000
  • Abstract: The rapid growth of Artificial Intelligence (AI) has led to a wealth of new AI-based applications, such as ChatGPT (Large Language Models), Alexa (speech recognition and natural language processors), and facial recognition (computer vision models). This has been enabled by the vast amount of collected text, audio, and video data and researchers who found novel ways to use the data for these use cases. In the context of human performance instruction, many AI models rely on similar datasets to measure success of the task. Even though skeletal tracking from video is possible, there can be errors due to camera viewpoint and its missing the micro muscular gestures, which could provide more insight on the user’s technique. For example, musical instructors can use video and audio data to evaluate a player’s note and tempo accuracy, but they would only have a rough estimate of body position to provide guidance for Improvement. We will address these deficiencies by augmenting the dataset with high-resolution motion data. For example, a pianist’s body can be tracked using LiDAR cameras (for depth and motion capture) and Electromyography (EMG) sensors (for micro gesture analysis during executions of musical gestures) to provide the data for more insightful analysis of body dynamics. Using AI-based approaches, we will establish the mapping between the musical features (notes, their duration and dynamics) and body motion and micro-gestures of the performer. Similar augmented datasets can be collected for various use cases of human performance, such as dance, sports, and speaker presentation.
  • PI: Stephen Wiley, College of Humanities and Social Sciences
  • Co-PIs:
    • Fernanda Duarte, College of Humanities and Social Sciences
    • Benjamin Watson, College of Engineering
    • Tania Allen, College of Design
    • Madhusudan Katti, College of Natural Resources
    • Nii Nikoi, College of Humanities and Social Sciences
    • Hannah Rainey, NC State University Libraries 
  • Awarded: $28,400
  • Abstract: Data science and academic research more broadly have been dominated by Western concepts, methods, and data infrastructures. The Western perspective became hegemonic during the colonial expansion of European powers into Asia, Africa, and the Americas over the last 600 years, erasing or delegitimizing Indigenous, Black, Islamic, South Asian, and other forms of pre-colonial knowledge. Today, the continuing coloniality of knowledge production is evident in the centrality of Anglo-American theorists, English-language journals, and Eurocentric biases in data infrastructures, including the emergent technologies of platformization, machine learning, and generative AI, thus replicating centuries-old inequalities of power and the resulting epistemological limitations. Our initiative will develop a decolonizing data-science framework and test its operational principles through a series of design studies around the construction of the Listening Machine, a public-facing, accessible data infrastructure focused on listening to subaltern voices and perspectives. We will build on a pilot project, the Decolonial Media Studies Database, a collection of nearly 200 under-represented sources in critical data studies and media studies. Our interdisciplinary team, with researchers from four Colleges and the NCSU Libraries, will develop and test new approaches to data collection, data architecture, and data visualization. We will do so in dialogue with scholars, research centers, and public science initiatives from the Global South as well as local and international community-knowledge experts, whom we will invite to our design workshops. The Listening Machine will support scholars who want to decenter Western knowledge, critically examine its assumptions, and discover other ways of knowing through decolonizing data science.
  • PI: Kevin Flores, College of Sciences
  • Co-PI:
    • Jason Haugh, College of Engineering
  • Awarded: $10,000
  • Abstract: The proposed research will advance data science research by further developing our previously published novel computational pipeline combining deep learning and topological data analysis to validate agent-based models (ABMs) for cell migration at high densities that exhibit an important, yet under-explored phenomenon referred to as “fluidization”. We will develop novel ABMs of mesenchymal cell migration by performing model selection and parameterization with multi-scale data. New convolutional neural network models will be developed that utilize pseudo-brightfield, nuclear channel, and fluorescence microscopy images to improve single-cell tracking by incorporating cell alignment, shape, and subcellular signaling. Our team has the ideal and unique combination of expertise required to accomplish these significant research goals among the mathematical modeling community, namely the ability to collect multi-scale experimental data relevant to cell motility, the capacity to develop customized deep-learning based image segmentation and localization methods, and experience with developing and validating mathematical models and inverse problem methods with topological data analysis. We will use the preliminary results generated in this proposed research and publications to submit an NIH R01 proposal to the Modeling and Analysis of Biological Systems Study Section. This study section reviews applications concerned with developing deep learning and mathematical models to understand biological systems at multiple scales, especially those that integrate computational modeling with analytical experimentation.
  • PI: Paul Liu, College of Sciences
  • Co-PIs:
    • Dongkuan Xu, College of Engineering
    • Alice Cheng, College of Humanities and Social Sciences
  • Awarded: $30,000
  • Abstract: This project aims to develop Large Language Model (LLM) agents to enhance accessibility and promote responsible AI in environmental data analysis. By creating intelligent interfaces for complex geoscience datasets (e.g., NetCDF, HDF, GRIB, GeoTIFF), we will democratize access to crucial environmental information. Our interdisciplinary team will focus on two key aspects: (1) designing natural language interfaces that allow researchers, policymakers, and the public to interact with large-scale environmental data without specialized programming skills, and (2) implementing responsible AI practices to ensure ethical use, transparency, and fairness in data interpretation. This project aligns with the DSA’s mission of empowering people to use data ethically, effectively, and accessible to solve important problems. By bridging the gap between complex environmental data and diverse user groups, our work has the potential to accelerate climate research, improve environmental policy-making, and enhance public understanding of critical environmental issues. This project will also involve four graduate students who will assist with data collection, analysis, coding, testing, workshop facilitation, and the collection and analysis of user feedback.
  • PI: Minyoung Suh, Wilson College of Textiles
  • Co-PIs:
    • Arnav Jhala, College of Engineering
    • Reo Song, College of Business, California State University Long Beach
  • Awarded: $35,000
  • Abstract: Due to unavailability and unaffordability, clothing alterations are required for disabled bodies to address their special needs after purchasing general clothing, which are limited to local amendments. The difficulties of purchasing clothes for individuals with physical disabilities significantly impact on their quality of life and willingness to engage in social activities. The current research proposes to develop an AI-powered custom clothing system tailored to the specific needs of individuals with physical disabilities. Leveraging artificial intelligence (AI) and data-driven methods, the innovative aspects of the proposed approach are defined in three areas: clothing function suggestions, unique size and fit requirements, and personalized style options. Another novel feature of incorporated technology is virtual design and prototyping. Through virtual processes, the design outcomes generated by AI are confirmed and tried virtually on each individual body. This eliminates unnecessary trials and errors in the physical world that might leave people with limited mobility helpless. Five research phases are identified with specific plans of work: from data generation and processing, design development, digitization for clothing design platform, algorithm development, to user experience evaluation. The interdisciplinary collaborations between the fields of clothing and textile, computer science, and marketing are proposed. By expanding the project scope to universal design, the research team is in the process of preparing a proposal for future government funding opportunities, such as Measurement Science and Engineering (MSE), Small Business Innovation Research (SBIR) and Small Business Technology Transfer (STTR) Programs.
  • PI: Colleen Doherty, College of Agriculture and Life Sciences
  • Co-PIs:
    • Michael Kudenov, College of Engineering
    • Cranos Williams, College of Engineering
    • Dahlia Nielsen, College of Sciences 
  • Awarded: $40,000
  • Abstract: Understanding how plants respond to climate change, particularly cyclical environmental patterns, is a critical challenge. This proposal hypothesizes that current research overlooks the value of dynamic data because of the challenges due to data analysis of cyclical data. Instead, research prioritizes static snapshots, which fail to capture the full complexity of plant responses to daily and seasonal cycles. We aim to quantify the value of dynamic data by incorporating time-based patterns into existing research on plant responses to climate stressors, such as warmer nighttime temperatures (WNT). Using a population of 144 tomato genotypes grown under controlled conditions, we will analyze static and dynamic image data to assess their ability to predict physiological responses. By comparing static and dynamic data, we seek to uncover novel markers and improve predictions of plant responses to climate change. The project will also enhance visualization techniques for complex time-series data, improving analysis and communication. Finally, we will engage the community by sharing image analysis tools with Master Gardeners and Osher Lifelong Learners, expanding access to data science, and promoting understanding of dynamic plant responses in the broader public. This research could drive the development of advanced tools for assessing plant responses to climate change, leading to more accurate predictions and better-informed agricultural practices.

2023 Awardees

  • Team members:
    • Caren Cooper, College of Natural Resources
    • Kelly Lynn Mulvey, College of Humanities and Social Sciences
    • Adam Hartstone-Rose, College of Sciences
  • Initial Award: $48,475
  • Additional 2023 Award: $25,475
  • Description: We request funds to support an interdisciplinary team of students in building, user-, pilot-, and beta-testing a web application for a citizen science project focused on animal and human behaviors during extreme natural phenomena. This project is preparation for a data-intensive project focused on the 2024 solar eclipse, and useful for studies of animal and human behavior during subsequent phenomena including before and after hurricanes and earthquakes. The web app increases the competitiveness of immediate grant proposals for: 1) documenting circadian and anxiety behaviors of a variety of animal taxa in multiple environments and phenomena and 2) broadening public engagement in Earth science to foster belonging and identity in science. The student team will create a well-documented and managed database that balances participant privacy protections and data sharing/re-use, a user-tested data-entry system with automated report-backs to participants in the form of data visualizations. The student team will also draw on multiple disciplines to create recruitment materials, curricula for partners, materials to train project ambassadors, user-friendly protocols and training for participants. We will user- and pilot-test within the Citizen Science Campus program during dawn/dusk scenarios, and beta-test with partners during the 2023 annular eclipse.
  • Team members:
    • Aram Amassian, College of Engineering
    • Harald Ade, College of Sciences
    • Dali Sun, College of Sciences
    • Ryan Chiechi, College of Sciences
    • Brendan O’Connor, College of Engineering
    • Kelly Zering, College of Agriculture & Life Sciences
  • Initial Award: $29,542
  • Additional 2023 Award: $36,944
  • Description: Emerging semiconductor materials, namely conjugated polymers and/or hybrid perovskites, have many energy, electronic, photonic and quantum use cases. A key feature of emerging semiconductors is their chemical and compositional diversity, which creates unique opportunities and challenges, such as a design space explosion. While nearly all 100 Carbon Electronic Cluster members working on these materials, our research can benefit from centralized database and use of informatics to support larger team efforts, especially in relation to how the common material chemistry, structure, properties, and device performances measured by different research units relate to each other. There is tremendous opportunity to making breakthroughs in our research fields by adopting Materials Genomics Initiative 2.0 practices combining data science with theory, computation, and experiment. We aim to develop (1) a data science infrastructure, (2) data science skillsets, workflows, and culture, and (3) extend existing automated data generation workflows to a wider Cluster membership to enable team-based data-driven inquiry. Our vision is for the Cluster to conduct data-driven fundamental and use-based materials research on emerging semiconductors from synthesis all the way to device fabrication collaboratively and become a national leader in data-driven research in emerging semiconductors.
  • Team members:
    • Cranos Williams, College of Engineering
    • Rachel Vann, College of Agriculture & Life Sciences
    • Katherine Stowe, College of Agriculture & Life Sciences
  • Awarded: $24,619
  • Description: To ensure continued on-farm profitability, it will be imperative that farmers have access to dynamic tools that allow them to use data science to advance the economic and environmental sustainability of their operations. The goal of the proposed project is to leverage investments in current cloud computing and analytics infrastructure with data science expertise across NC State University coupled with current small-plot field data to create a farmer decision support tool via the SAS Viya platform that will be easily navigable by farmers across North Carolina. This tool will be created using a dataset from the field generated since 2019 that comprises 50,000 data points demonstrating the relationship of production practices with yield and quality across the state. Coupling this dataset with weather data to create an accessible tool that over 5,000 farmers can use will bring data science off campus into every county of North Carolina. Funds are requested to hire a graduate student with the analytical and programming expertise needed to create this tool in SAS Viya. The outcome of this project will be web-accessible models that provide data-driven solutions about soybean production practices directly to farmers, ultimately leading to an increase in the North Carolina agricultural economy.
  • Related Articles: Seed Grant Awardees Aim to Revolutionize Farming with Data Science
  • Team members:
    • Shuyin Jiao, College of Engineering
    • Warren J. Jasper, Wilson College of Textiles
  • Initial Awarded: $43,465
  • Additional 2023 Award: $9,801
  • Description: Many engineering students enrolled in STEM courses lack the skills needed to design novel methods for collecting data and managing its provenance to support scientific reproducibility and reliability. Without these essential skills, students struggle to validate prototypes and resort to expensive proprietary equipment with restrictive interfaces that may not actually collect the right type of data. While most curricula emphasize data analysis and visualization (two core tenets of data science)[1, 9], there is a paucity of emphasis on data collection, and to a lesser extent on data storage. Students are generally given representative data sets to analyze but are not given the proper tools to design systems which will acquire, collect and store physical measurements – critical experience necessary for success in later years, graduate school, and industry. To better connect engineering education with industrial practices and prepare our students for the STEM workforce of tomorrow, we propose a major change to the current pedagogy centered on open source/open standards and the Raspberry Pi [6]. Adopting an open-source philosophy toward data collection will enable stability, security, interoperability, and reliability across a variety of engineering disciplines that acquire data, both in the classroom and in research labs.
  • Team members:
    • Jonathan Williams, College of Sciences
    • Vanessa Volpe, College of Humanities and Social Sciences
  • Awarded: $50,000
  • Description: In America, Black individuals are at a higher risk for cardiovascular diseases than other ethnic/racial groups. A major contributor to such health disparities is the stress imposed on Black Americans due to racism. This work seeks to uncover the heterogeneity of racial stress responses from Black, young adults through the application of Bayesian hidden Markov models (HMMs) on cardiac output data, namely respiratory sinus arrhythmia (RSA). This approach will allow for an accurate assessment of the magnitude with which RSA changes due to stress, as well as provide an approach for classifying participants based on their physiological response to stress. Ultimately, this research aims to bring more awareness to the racial health disparities witnessed in America through the application of new statistical methods to psychophysiological data.
  • Team members:
    • William Rand, Poole College of Management
    • Ana-Maria Staicu, College of Sciences
    • Xiaoxia Champon, College of Sciences
    • Nikhil Ankolkar, College of Sciences
    • David Roycroft, College of Sciences
    • Landon Smith, Poole College of Management
    • Nate Schaefer, Poole College of Management
  • Awarded: $20,000
  • Description: Social media influencers play a significant role in shaping the information transmitted on any social media platform and there are growing concerns over disinformation and manipulated messages. A systematic understanding of influencer behaviors and information diffusion could assist in reducing the effect of mis/disinformation. Motivated by the Modeling Influence Pathways project (MIPs), our interdisciplinary team used Tweets related to the Skripal case to investigate users’ time dependent behavioral differences and assess multiple social media platforms’ interaction effects on different campaigns. However, the limited MIPs funding only allows us to explore a solitary case. Upon the depletion of the MIPs funding, this seed funding will facilitate our continuous effort to support our interdepartmental team, help the transition to secure additional external funding. This funding offers an opportunity to continue expanding our team and test our methodology on additional cases like the war on Ukraine. The goal of this research is to build a tool to identify the most important users involved in information diffusion and map out the information transfer pathways. This project aims to connect information that flows into pathways which are used to disseminate and amplify mis/disinformation, and helps to mitigate the effect of disinformation.
  • Team members:
    • Zhen Qu, College of Sciences
    • Xiaourui Liu, College of Engineering
    • Kofi Boone, College of Design
    • Katy May, Center for Human Health and the Environment
  • Initial Award: $49,973
  • Additional 2023 Award: $23,924
  • Description: Air pollution is the fifth leading risk factor for mortality worldwide. In the US, air pollution causes 100,000 premature deaths per year, 80% of which is due to fine particulate matter (PM2.5). Effective regulation of air pollution requires a better understanding of PM2.5 concentrations than we have at present. The current PM2.5 monitoring stations are mainly located in high-income and predominantly White areas, leaving the most vulnerable communities in the dark about their levels of exposure. The existing PM2.5 predictions by the EPA air quality model can fill these spatial gaps but still have large uncertainties. To resolve these challenges, we will apply novel semi-supervised deep learning techniques such as Graph Neural Networks (GNNs) to predict PM2.5 concentrations over the entire US. We will compare the resulting PM2.5 predictions with those from existing machine learning and air quality models, perform environmental justice analysis, disseminate our results to planners and key decision-makers, and outreach to disadvantaged communities in North Carolina. This seed grant will initiate collaborations between three Colleges and a Center, support two early career PIs to build their research program, and produce preliminary results for collaborative research proposals for external grant applications.
  • Team members:
    • Veljko Dubljević, College of Humanities and Social Sciences
    • George List, College of Engineering
    • Darby Orcutt, NC State University Libraries
    • William Bauer, College of Humanities and Social Sciences
    • Munindar Singh, College of Engineering
    • Crystal Lee, College of Education
  • Initial Award: $25,837
  • Additional 2023 Award: $11,246
  • Description: Fostering diverse connections and engaged interdisciplinary community of NC State researchers working on wicked problems around AI in Society will RAISE the University’s profile as a leading voice on matters of science and society. RAISE would provide two day-long ideation and workshopping sessions, a half-day grant-writing retreat, support for honoraria to grow and extend the existing AI in Society colloquium, Most notably, this seed grant will support one cross-college graduate student position and two undergraduate research assistant positions (from multiple colleges) to support activities, maintain the website and listservs, and manage communications between and among participating researchers. The goals of RAISE are to increase the number of colleges at NC State actively engaged in the AI in Society community, to work on the submission of major interdisciplinary AI in Society-related research grant proposals in 2024, and to develop of a new National Science Foundation (NSF) Research Traineeship (NRT) grant application. In our view, values are inherent to the very consideration of the place of AI in society. Ensuring the morality of AI agent interactions with each other and with humans requires anticipating challenges including: (1) avoiding coding bias; (2) achieving a comprehensive view; (3) providing safety guarantees; and (4) public engagement.
  • Related Articles: NC State Secures $500K NEH Grant to Launch AI Center in CHASS
  • Team members:
    • Shadow Huang, College of Engineering
    • Logan Opperman, College of Sciences
  • Initial Award: $40,000
  • Additional 2023 Award: $27,000
  • Description: In computational materials science and mechanics of lithium batteries and beyond lithium, statistics is critical for evaluating the confidence in predictions and models with substantial potential for impact on battery materials development and qualification. The role for statistical techniques is not limited to obtaining uncertainty intervals on phase boundaries. These methods can drive the development of selection criteria for the best combinations of datasets of battery materials and mechano-electrochemical descriptions that support each other for a given electrochemical system. The proposed work will be accompanied by a comparison of the use of statistical techniques in mechano-electrochemistry to inform critical lithium battery design choices and gleaning scientific insights.
  • Team members:
    • Lizzette Lorenz, College of Veterinary Medicine
    • Jasmine Olivares, College of Veterinary Medicine
    • Nelson Vinueza Benitez, Wilson College of Textiles
  • Awarded: $16,418
  • Description: In computational materials science and mechanics of lithium batteries and beyond lithium, statistics is critical for evaluating the confidence in predictions and models with substantial potential for impact on battery materials development and qualification. The role for statistical techniques is not limited to obtaining uncertainty intervals on phase boundaries. These methods can drive the development of selection criteria for the best combinations of datasets of battery materials and mechano-electrochemical descriptions that support each other for a given electrochemical system. The proposed work will be accompanied by a comparison of the use of statistical techniques in mechano-electrochemistry to inform critical lithium battery design choices and gleaning scientific insights.
  • Team members:
    • Oguz Akbilgic, Wake Forest University School of Medicine
    • James Dieffenderfer, College of Engineering
  • Awarded: $40,000
  • Description: Evaluation of Left Arm ECG for Deep Learning Risk  Prediction of Heart Failure seeks to achieve a first step in solving two big issues in cardiovascular disease prevention: The current standard of diagnostic prediction is (1) infrequent and (2) not easily accessible due to the expensive nature of the equipment. This research builds upon previous work accomplished in the field (including work performed by the PIs) and aims to build an ECG armband that utilizes artificial intelligence in order to provide a prediction for risk of cardiovascular disease.

2022 Awardees

  • Team members:
    • Steve McDonald, College of Humanities & Social Sciences
    • Andrew Davis, College of Humanities & Social Sciences
    • Branda Nowell, College of Humanities & Social Sciences
    • Robin Dodsworth, College of Humanities & Social Sciences
  • Awarded: $35,000
  • Description: Social Network Analysis (SNA) is a methodological tool frequently deployed as part of data science, though it is not currently one of the courses offered by the Data Science Academy. Many faculty members and graduate students at NC State use SNA as part of their research, but they tend to work within rather than across disciplinary units. There is a growing need to develop an interdisciplinary community of SNA scholars at NC State in order to advance our institution’s goal of conducting high impact and cutting edge research, while also preparing students to become future leaders in the field of data science. Under the heading of WolfWebs, we aim to develop interdisciplinary connections among faculty and graduate students at NC State who conduct or are interested in conducting research using SNA. These efforts will develop social infrastructure of SNA expertise to facilitate research collaboration, grant submission, and training. Specifically, the seed grant funds will be used to support a high profile speaker series, research panels to introduce and connect SNA faculty, grant proposal ideation workshops, and intensive SNA training sessions for faculty and students.
  • Team members:
    • J. Aaron Hipp, College of Natural Resources
    • Deepti Adlakha, College of Design
    • Laura Tateosian, Center for Geospatial Analytics
    • Jason Bocarro, College of Natural Resources
    • Jing-Huei Huang, Center for Geospatial Analytics
  • Initial Award: $32,417
  • Additional 2023 Award: $21,533.75
  • Description: The COVID-19 pandemic has highlighted the importance of access and use of quality outdoor spaces including parks and trails. The pandemic has also exacerbated the downward trends in survey response rate and increased survey fatigue. Parks and recreation and public health professionals face challenges in recruiting and responding to diverse voices in their communities to deliver the programs, policies, and spaces desired. Social media data, here specifically Twitter data, may provide a reliable and valid source of social and behavioral science data for appropriating parks, recreation, and public health resources. With this seed funding we seek to bring together two Colleges, a Center, and an Initiative, as well as two early career researchers, to explore the feasibility of using social media data mining to inform program, policy, and design decision-making for park and community health professionals. Aim 1 is to use and compare two distinct Twitter datasets to scrape North Carolina originating tweets with park-related and physical activity-related text. Aim 2 is to validate content and topic results against existing survey data related to parks and physical activity amongst the public and parks and recreation practitioners. Aim 3 to disseminate this work and seek extramural funding.
  • Team members:
    • Adriana San Miguel, College of Engineering
    • Kevin Flores, College of Sciences
  • Initial Award: $48,606
  • Additional 2023 Award: $24,090
  • Description: Morphological changes in organs, tissues, and cells are indicative of underlying disorders or decline induced by aging. Images can be highly informative for diagnosing, understanding, and treating disease. However, identification of the relevant features from biological images is a very challenging task. In this work, we propose to integrate deep-learning approaches with high-throughput, high-content images in the model organism C. elegans. We plan to develop pipelines that enable analyzing and extracting informative insights from images of neurodegenerating neurons and declining tissues, by converting biological images into large descriptive data-sets amenable to statistical and mathematical examination. This work will allow the identification of neuronal defects and the in-depth analysis of features that can reveal mechanisms that lead to diverse structural changes, such as the drivers of neurodegeneration in different contexts. This grant brings together a strong team with expertise in high-throughput imaging, C. elegans aging and neurodegeneration, and machine learning applied to biological prediction problems.
  • Team members:
    • Amato Nocera, College of Education
    • Christy Byrd, College of Education
    • Shiyan Jiang, College of Education
  • Initial Award: $50,000
  • Additional 2023 Award: $25,000
  • Description: This proposed project aims to bring machine learning to high school history classrooms to foster historical thinking and critical AI (Artificial Intelligence) literacy. This project will build on an innovative pilot study that the PI team conducted in five history classrooms in North Carolina in May 2022. Our study had students use StoryQ—a web-based text mining and AI modeling platform for K-12—to investigate patterns across primary source texts, gain a deeper understanding of the systemic nature of historical discrimination, and foster AI literacy in evaluating bias and sources of data. With support from the Seed Grant program, we will hire a full-time graduate student to analyze the rich data collected from the initial pilot study (including pre- and post-surveys, in-class assignments, field notes, and interviews), help refine the unit (based on student learning outcomes from the first iteration), and implement a second iteration next academic year, following a design-based approach. The resulting data and analysis will provide an important foundation for the PI team to write a compelling NSF grant proposal for the ITEST program.
  • Team members:
    • Karen Daniels, College of Sciences
    • Karl Wegmann, College of Sciences
    • Vrinda Desai, College of Sciences
    • Nakul Deshpande, College of Sciences
    • Al Handwerger, Jet Propulsion Laboratory, California Institute of Technology
    • Vashan Wright, Scripps Institution of Oceanography, University of California at San Diego
    • Ted Brzinski, Haverford College
  • Initial Award: $46,016
  • Additional 2023 Award: $5,000
  • Description: The ground beneath our feet shifts over time: sometimes slowly creeping downhill, sometimes in sudden landslides and the separation in length scales — between soil particles and the landforms — is similarly immense. As global warming creates extreme weather events that destabilize the earth’s surface, and population growth pushes development into unfavorable building sites, there is an urgent need to understand how to identify and protect vulnerable populations from such hazards. Physicists and engineers have made great strides in performing laboratory studies of particulate materials which connect grain-scale deformation, applied loads, and the flow rules that relate them. Similarly, geoscientists have developed satellite technology to monitor the shifting landforms. However, these length and time scales remain far removed from the grain scale, and measurements of the internal forces within the earth’s surface are much less well-developed. How do we take our nascent understanding beyond the lab, to address real earth data? How do we take the most pressing earth hazard concerns and use laboratory data to seek solutions? This seed grant would fund open data science that maps out the most promising routes for bridging the chasm of dramatically different length and time scales, and targets those projects for external funding.
  • Team members:
    • Mengmeng Zhu, Wilson College of Textiles
    • Xiangwu Zhang, Wilson College of Textiles
  • Awarded: $5,000
  • Description: Driven by stricter emission regulations, energy intensity, and lower cost, Lithium-ion (Li-ion) battery technology is emerging to be one of the most prominent sources for powertrain electrification and large-scaleenergy storage systems. Safety and reliability are the critical concerns impeding the adoption of Li-ion battery technology. Traditional methods to assess battery health, such as electrochemical models, rely on multiple partial differential equations, which are time-consuming and computationally expensive. The research objective of this proposal is to develop a data-driven reliability analysis framework of the battery pack by understanding the dependence and variation of degradation behaviors of cells in Li-ion battery pack and leverage the gained insights to advance modeling and computing on Li-ion battery pack health management. The proposed data-driven approach consists of data collection, stochastic process-based modeling capturing the heterogeneities of battery cells, and model validation using the collected data greatly improve the robustness and accuracy in evaluating the health of Li-ion battery pack, thereby improving safety, reliability, and efficiency of battery-driven applications and further adoption of Li-ion battery technology. In addition, we will organize small-group proposal ideation workshops within NC State to bring together experts in data science, materials, communications, and power systems for future research projects.
  • Team members:
    • Manuel Kleiner, College of Agriculture and Life Sciences
    • Benjamin Callahan, College of Veterinary Medicine
  • Initial Award: $41,712
  • Additional 2023 Award: $23,612
  • Description: Horizontal gene transfer (HGT) between microbes is critical for the evolution of microorganisms in communities and global health threats such as the rapid spread of antibiotics resistance in microbiomes. We have developed and published a novel approach, termed “transductomics”, that allows for the sequence determination of genome fragments that are horizontally transferred between microbes by viruses. Currently, this approach requires extensive manual inspection of metagenomic sequencing data by an expert which limits its user-range. In this project, we will develop machine learning approaches to automate the detection of HGT events in transductomics datasets to enable faster analysis of larger datasets by non-experts. This interdisciplinary research project will combine the expertise of the computational research group of Dr. Callahan and the meta-omics data generation and analysis focused research group of Dr.Kleiner. The project will fund a graduate student – who has already done some preliminary work on developing transductomics machine learning approaches. The key goal of this seed project is to provide preliminary data for a favorably reviewed R01 grant resubmission, as well as additional planned grant submissions.
  • Team members:
    • Tania Allen, College of Design
    • Sara Queen, College of Design
  • Initial Award: $50,000
  • Additional 2023 Award: $12,500
  • Description:  The primary goal of this project is to build on new perspectives at the intersection of data science, ethics, representation and bias specifically as it relates to equity, inclusion and systems of oppression that may or may not be evident in the way that data is collected, cleaned, manipulated and communicated. Funding from this grant will support a colloquium of scholars and practitioners from multiple fields who are actively collecting and using a variety of quantitative and qualitative data in their work to discuss how they account for and address issues of equity and access. Through this proposal we hope to strengthen our cross-disciplinary network of researchers exploring how data and data visualization contribute to inequity and injustice as oppressive and liberating tools, and to collectively build an impactful body of research that diversifies the dimensions used to describe and study these wicked challenges and expands critical conversations to initiate change.

2021 Awardees

  • Team members:
    • Shiyan Jiang, College of Education
    • Bita Akram, College of Engineering
  • Awarded: $25,000
  • Team members:
    • Xu Wu, College of Engineering
    • Ralph Smith, College of Sciences
  • Awarded: $25,000
  • Team members:
    • Kathie Dello, North Carolina State Climate Office
    • Jessica Matthews, North Carolina Institute for Climate Studies
    • Carl Schreck, North Carolina Institute for Climate Studies
    • Bjorn Brooks, North Carolina Institute for Climate Studies
    • Sheila Saia, College of Agriculture and Life Sciences
    • Yuhan Rao, North Carolina Institute for Climate Studies
    • Micah Vandegrift, NC State University Libraries
  • Awarded: $25,000
About Seed Grants