Missouri Data Science & Informatics Symposium 2024

Title: The next frontiers of geospatial

Abstract: It’s been a year since I accepted the challenge of becoming the inaugural Executive Director of the Taylor Geospatial Institute – a new institute, funded via a philanthropic gift in St. Louis, to fuel geospatial research and innovation with a consortium of universities and research centers, and an eye on commercialization and impact at scale. As expected, the experience has been both exciting and challenging. In this keynote, I share my observations on the evolution of our geospatial ecosystem and the changing roles of organizations (national mapping agencies, academia & research, non-profits, and more) and how these observations are shaping our priorities at the Taylor Geospatial Institute.
In particular, I note (1) how today’s problems (climate, food security, health, disasters, sustainability, etc) require a more deliberate collaborative approach for research & innovation that transcends disciplinary and organization boundaries; (2) the mismatch between the investment in research & innovation and solutions to “real-world” problems; (3) the gap between research and commercialization and how it can be bridged; and (4) my most sincere appreciation to all the non-profits in the geospatial sector working on increasing collaboration, problem solving, and interoperability. Although geospatial has come a long way, we still have a lot of work to do to achieve our full potential, but one thing is for sure, our time is NOW!

Bio:
Executive Director, Taylor Geospatial Institute
Dr. Nadine Alameh is the inaugural Executive Director of the Taylor Geospatial Institute –founded to fuel collaborative geospatial science & technology to solve global problems. Dr. Alameh is a recognized leader (and cheerleader) in the geospatial field with experience in Aviation, Intelligent Transportation Systems, Earth Observations, Public Safety, and Defense.

Prior to joining the Taylor Geospatial Institute, she was CEO & President of the Open Geospatial Consortium (OGC) where she led the global consortium in making geospatial information Findable, Accessible, Interoperable, and Reusable (FAIR). During her career, Nadine held various roles in industry from the Chief Architect for Innovation at Northrop; to CEO of an Aviation startup; to senior technical advisor to NASA’s Applied Science Program.

Dr. Alameh is an appointed member of the U.S. National Geospatial Advisory Committee (NGAC) and sits on the board of the UN Committee of Experts on Global Geospatial Information Management (UN-GGIM) Private Sector Network. She has received multiple awards – the 2024 St. Louis Business Journal Most Influential Businesswoman award, the 2023 Annual Women in Technology Leadership award, the 2022 Geospatial World Diversity Champion award, and the 2019 Geomatics Canada Diversity Leadership Award.
Nadine holds a Ph.D. and 2 M.S. degrees from MIT.

Title: Development of Geospatial AI and Deep Learning Models to Estimate High-Resolution Multi-Pollutant Ground Air Quality Using Satellite Remote Sensing

Abstract: Air pollution is associated with different health issues, including heart and lung problems and even premature death. The World Health Organization reports an alarming figure nearly 7 million deaths per year worldwide due to exposure to ambient air pollution. The prevalent methodology for monitoring air quality heavily relies on a network of ground-based sensors, which, despite their accuracy, are limited by their sparse distribution and high operational costs. This scarcity and the resultant lack of coverage impede the ability to capture the nuanced spatial and temporal variations in air quality, thereby failing to delineate localized zones of heightened pollution within urban settings.

An alternative approach is modeling ground air quality from satellite imageries. With the advancement of computational technologies and the outstanding performance of deep learning (DL) in statistical modeling, DL is being applied in extracting ground air quality indicators from satellite data. This later approach of air quality modeling, with or without applications of DL, mostly focused on country or regional level as they mostly used low resolution images. In addition, the DL models are usually employed without considering the geographical principles, which are pivotal for accurately reflecting the spatial dynamics of air pollution. This research aims to develop geospatial deep learning models to estimate high resolution ground air quality, i.e., six criteria air pollutants utilizing satellite imageries.

Title: Modeling the spatiotemporal distributions of ticks and tick-borne diseases.

Abstract:
Ticks and tick-borne diseases as well as other arthropods and arthropod-borne diseases are to a large extent regulated by ambient conditions to which these vectors are exposed. This renders the study of their spatial and population dynamics, and to a lesser extent also the prevalence of diseases transmitted by them possible through geospatial and computational methods. Tick-borne diseases have increased in intensity (i.e., number of cases seen) as well as in the spatial distribution over the past couple of decades. The spatiotemporal distribution and exact nature of the driving factors behind such surge are not clearly understood. Fine-resolution vector and disease data at patient-level, and matching remote sensing and demographic/socio-economic data are useful. Additionally, novel geospatial models need to be developed to find meaningful associations and actionable information.

Bio:

Dr. Raghavan is broadly interested in spatially-enabled computational epidemiology of vector-borne and infectious diseases and applications of geospatial approaches for enhancing animal/public health. He extensively uses Geographic Information Science (GIS) and remote-sensing concepts in his research alongside geo-statistical, correlative modeling, and Bayesian modeling approaches for understanding spatio-temporal dynamics of non-stationary epidemiological processes. His current and prior research have identified important spatio-temporal patterns and spatial determinants for vector/water-borne zoonotic diseases from climatic, environmental, and socio-economic themes. Increasingly, his research strives to identify consistencies in complex meteorological variable associations (i.e. climate-change) with vector-borne diseases through the utilization of high-resolution ground-based and NASA Earth Observing System (EOS) datasets.

Title: Achieving AI for Good

Abstract
AI systems are developing by leaps and bounds to the point that we will arrive at Artificial General Intelligence (i.e., human-level AI) sooner or later. Along the way, collective effort is needed now to ensure that this technology is designed, developed, and deployed for good. However, a fundamental question remains: how do we achieve AI for good and how do we contribute towards its realization? Through the lens of Responsible Research Innovation, this talk will present theoretical and practical insights on how individuals and society at large can achieve AI for good.

Bio
Dr. Bautista is an Assistant Professor at the Sinclair School of Nursing, University of Missouri-Columbia (MU). He also holds other MU appointments, such as MizzouForward Faculty, MUIDSI Core Faculty in Health Informatics, and MU Provost’s AI Teaching Fellow. He has an interdisciplinary background in health (nursing and public health), informatics (health, social, and social justice informatics), and communication science (health and organizational communication), with specific training and expertise in both qualitative (interviews, observations, and document analysis) and quantitative (primary and secondary survey data) research. As an early career researcher, he has received fellowships and internal grants to conduct socio-technical research to identify the benefits and risks of using smartphones, social media, blockchain, and artificial intelligence (AI) for health-related purposes. Since 2022, he has gained valuable insights and knowledge on the ethical and responsible use of AI by attending competitive workshops (e.g., Global Sandpit on Trustworthy Autonomous Systems and Work in the Age of Intelligent Machines Workshop) and facilitating workshops (e.g., at UT Austin, Johns Hopkins, and Yale).

Title. Potential applications of AI in clinical medicine

Abstract: This brief talk will explore potential applications of AI in clinical medicine. Areas to be covered include large language models, imaging, and clinical decision algorithms. In addition, barriers to implementation will be discussed.

Bio
Dr. Richard Hammer is highly trained hematopathologist/surgical pathologist with extensive experience and a focus on providing state-of-the-art diagnosis and evaluation using the latest evidence-based medicine. His lab provides high-level service in hematopathology, flow cytometry, coagulation, and molecular diagnostics in hematology. He also is involved in bioinformatics and developing tools to apply digital solutions to clinical practice and clinical decision support.