[cosc-grad-students-list] RESEARCH PROPOSAL SEMINAR NOTICE - TITLE: MULTISCALE and MULTIMODAL GEOAI ANALYSIS OF COVID-19 VACCINATION DISPARITIES - Hossein Naderi

[Eulenfeld, Menda]

We cordially invite you to attend Hossein Naderi's Research Proposal. Your support would be great!



RESEARCH PROPOSAL SEMINAR NOTICE
GEOSPATIAL COMPUTER SCIENCE PROGRAM
COLLEGE OF SCIENCE AND ENGINEERING
TEXAS A&M UNIVERSITY-CORPUS CHRISTI

TITLE: MULTISCALE and MULTIMODAL GEOAI ANALYSIS OF COVID-19 VACCINATION DISPARITIES
SPEAKER: Hossein Naderi
ADVISOR: Dr. Lucy Huang
COMMITTEE: Dr. Hassan Aziz, Dr. Mahdi Sookhak, Dr. Taoran Ji, and Dr. Veysel Avsar
DATE: September 24, 2025 (Wednesday)
TIME: 10:00 AM Central Time (US and Canada)
PLACE: NRC 1232 Conference Room at CBI
Zoom Link:  https://tamucc.zoom.us/j/92458135288?pwd=Vl5J3eIQMwueCXjyKfMyZ2EK1057kH.1<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Ftamucc.zoom.us%2Fj%2F92458135288%3Fpwd%3DVl5J3eIQMwueCXjyKfMyZ2EK1057kH.1&data=05%7C02%7Ccosc-grad-students-list%40listserv.tamucc.edu%7C84c2a578f07745b3afb108ddf6de4620%7C34cbfaf167a64781a9ca514eb2550b66%7C0%7C0%7C638938156691978093%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=RnHSweeO%2FG5EGP1Lj%2FfR76fKWyIQ%2FpmLxetHQFfG3Ik%3D&reserved=0>
Meeting ID: 924 5813 5288
Passcode: 361291

Abstract
The COVID-19 pandemic exposed critical disparities in vaccine uptake, with underserved populations facing barriers shaped by geography, sociodemographic conditions, and neighborhood context. While individual-level determinants such as age, race, and ethnicity are well documented, less attention has been given to fine-scale geographic accessibility and the influence of built environments. This dissertation develops an integrated, multi-phase framework to examine disparities in COVID-19 vaccination uptake in Nueces County, Texas, by progressively combining survival analysis, graph-based learning, and multimodal contextual data. The research begins by quantifying disparities between expected spatial accessibility, estimated using the Two-Step Floating Catchment Area method, and actual travel time to vaccination sites. Using both traditional and machine learning-based survival models, these analyses reveal how travel time discrepancies, demographic characteristics, and social vulnerability shape the timing of full and booster vaccinations. Building on these findings, the study advances to a spatial deep learning stage, where Graph Neural Networks (GNNs) and Graph Attention Networks (GATs) model neighborhood-level vaccination rates across census tracts and block groups. These models capture relational dependencies among adjacent communities and, through the use of interpretability tools such as GNNExplainer, highlight the most influential predictors of vaccination disparities. Finally, the framework incorporates Google Street View imagery to integrate neighborhood visual features-such as sidewalks, greenery, and signs of disorder-into graph-based models. By combining these multimodal signals with sociodemographic and spatial attributes, the approach provides a richer, context-aware explanation of vaccination behavior. Together, these phases form a continuous, multi-scale analysis that advances GeoAI methods for public health, offering new insights into the drivers of vaccine disparities and supporting equitable, data-driven strategies for vaccine delivery.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.tamucc.edu/pipermail/cosc-grad-students-list/attachments/20250918/8ad39792/attachment-0001.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: text/calendar
Size: 9285 bytes
Desc: not available
URL: <http://listserv.tamucc.edu/pipermail/cosc-grad-students-list/attachments/20250918/8ad39792/attachment-0001.ics>