Title: DART Seed Grant Recipient Presentations, Session 1
Presenter(s): Xiao Huang and Ahmed Abu Halimeh
Date: September 28, 2022


This month’s webinar will feature two presentations from the recently awarded DART YR 3 Seed Grant Recipients.

  • Dr. Xiao Huang (UAF)will present on AI-Supported Cyberinfrastructure for Scalable Flood Resilience Assessment. This project is part of the CI research theme.
  • Dr. Ahmed Abu Halimeh (UALR)will present on Developing Machine Learning Models to Improve the Effectiveness of Automated Data Curation Processes. This project is part of both the DC and LP research themes.

AI-Supported Cyberinfrastructure for Scalable Flood Resilience Assessment

Efforts to raise awareness of the flood hazards for flood-prone communities and vulnerable populations are far from enough. In addition, community-level flood resilience and adaptation are often investigated in an unscalable manner, making the entire investigation workflow rather community-specific with low transferability to other communities or to a large geographical scale. Taking advantage of a series of advances in information retrieval, simulation, and web portal design, this proposed project aims to develop artificial intelligence (AI)-supported cyberinfrastructure for scalable flood resilience assessment, aiming to improve awareness of flood-prone residents and benefit community-tailored flood mitigation strategies. The specific objects include 1) deriving fine-grained building-level flood exposure using United States national building footprints and cross-referenced floodplain products, 2) exploring a scalable workflow of lowest floor elevation retrieval, taking advantage of street view images, 3) proposing a flood damage simulation paradigms incorporating building characteristics and simulated flood intensity, 4) associating flood damage with residents’ socioeconomic statuses via advanced and robust statistical analysis, 5) developing an online portal for scalable flood resilience assessment, with the capability of interactive updates, flood scenario selection, location query, and report generation. The developed AI-supported cyberinfrastructure and the proposed flood damage simulation framework are expected to renovate and transform large-scale flood damage assessment and flood situational awareness communication.

Developing Machine Learning Models to Improve the Effectiveness of Automated Data Curation Processes

Machine learning is making strides in achieving remarkable successes in many areas and there is no reason why it can’t also contribute to the improvement of data curation and data quality as well. A primary data curation tool to be considered in this proposal is the Data Washing Machine (DWM) developed in the NSF DART Data Life Cycle and Curation research theme and which has already demonstrated the capability to automatically detect and correct certain types of data quality errors and to perform unsupervised entity resolution to identify redundant records. However, in its current form, the DWM operations are driven by algorithmic pattern rules. The goal of this research is to improvement the effectiveness of the DWM by augmenting or replacing these rules with ML-based Quality Learning models. The proposed Quality Learning models will further support the goals of the Data Life Cycle and Curation research theme to create unsupervised and scalable methods that significantly increase the level of automation in the data curation process from data acquisition to disposal. The objective of the proposed research is to develop ML models that will complement the research already underway in the Data Life Cycle and Curation Thrust of the DART Project to develop methods and techniques for unsupervised data curation. We propose to understand how ML models can be used to augment existing methods and develop new unsupervised methods for data quality assessment, data quality error detection and correction, entity resolution and data clustering, and data integration

Presenter Bios

Dr. Xiao Huang is an Assistant Professor in the Department of Geosciences at the University of Arkansas. Before he joined University of Arkansas, he obtained his Ph.D. degree in Geography from University of South Carolina and Master’s degree in GISscience from Georgia Institute of Technology. His research primarily focuses on geospatial analysis, geovisualization, environmental modeling, computer and data science, and Big Data analytics. Dr. Huang has authored/co-authored more than 120 peer-reviewed publications across various disciplines. Professionally, he serves as an Associated Editor for Computational Urban Science and sits on the Editorial Board for Big Earth Data, International Journal of Digital Earth, Frontiers Remote Sensing, Nature Scientific Reports, Journal of Remote Sensing, and PLOS ONE. He also served as a reviewer for NASA and NSF grants and for 48 international/national journals.

Dr.Ahmed Abu Halimeh is an Assistant Professor of information science at University of Arkansas at Little Rock. He serves as a consultant and Research Informatics Program Manager at the Arkansas Research Institute at Arkansas Children’s Hospital. Abu Halimeh was previously an Associate Professor of computer and information sciences at The American University of the Middle East in Kuwait for 5 years. He holds a master’s degree in information science and information quality, and a PhD degree in integrated computing from University of Arkansas at Little Rock. His research interests include: Information/Data Quality, Blockchain Technology, Data Governance, Health informatics, Data Analytics and Human Computer Interaction Applications.