A Hybrid Decision Support System for Driving Resiliency in Texas Coastal Communities (NOAA Sea Grant, $300,000, 2020-2022)
This research seeks to augment current flood management practices in Texas coastal communities using citizen science, artificial intelligence (AI), and decision science, and cyberinfrastructure. In this project, we use citizen science and machine learning to compare pre-flood and post-flood photos of the same traffic “STOP” sign location to estimate the depth of floodwater at street level. The traffic “STOP” signs are used as benchmarks since their shapes and sizes are standardized anywhere in the country. Generated data will be further incorporated in a CyberGIS-enabled spatial decision support tool for residents and first responders to improve the quality and timeliness of decision-making in the event of a flood.
The research group has organized several lab sessions and lectures for the K-12 students that come from Texas A&M Chinese School, Texas A&M Consolidated High School, and Allen Academy. As a result, K-12 students have published a poster at AAG 2020 annual meeting on the topic of "The Pathological and Economic Consequences of Houston's Air Pollution Catastrophe: A Youth's Perspective".
2020 Saari, S., Wang, R., Cairns, J., Wang, C., Li, A., Yang, E., and Brody, A., Urban Social Vulnerability Assessment under COVID-19 and Natural Disasters. University Consortium for Geographic Information Science Symposium Poster. Texas A&M GIS and Geography K-12 Education Program.
Available from the web:
Saari S., Wang, C., Cairns J., Li, A., Yang, E., Cairns, L., 2020. The Pathological and Economic Consequences of Houston’s Air Pollution Catastrophe: A Youth's Perspective. AAG Annual Meeting poster. Available from the web:
Innovation [X] Project (Funded by Texas A&M School of Innovation, $20,000, 2020-2021)
Natural disasters globally cause significant human loss and economic damage. Disaster responders often need to make quick decisions in complex situations under heavy duress. The decision goals are usually achieved through inquiry into a series of spatial parameters closely tied to specific decision objectives and their associated evaluation criteria based on diverse social, socioeconomic, and demographic conditions. In this project, we aim to design an interactive and collaborative spatial decision support system (SDSS) based on advanced cyberinfrastructure, WebGIS, and citizen science to improve situational awareness in disaster management. The proposed SDSS considers spatial and social vulnerability priorities to enhance knowledge elicitation and sharing among a diverse range of disaster responders and communities.
Social Vulnerability, Mobility, and COVID-19 Spatial Mortality Patterns (NSF Funded Converge COVID-19 Working Groups, $1000, 2020)
This Working Group aims to observe the spatial variation of the COVID-19 mortality rate with various sociodemographic and spatial variables. This science-driven project integrates advanced cyberinfrastructure, geospatial statistical models, and novel AI algorithms to analyze spatial COVID-19 mortality patterns.
A Spatial Decision Support System in Response to the COVID-19 Pandemic
Texas A&M Institute of Data Science, $ 27,000, 2020-2021
The research team is working on analyzing massive social media data and mobility data to predict the disease spread pattern at a spatiotemporal scale.
We have developed a Health Space &Time web application to visualize people's risk perception under COVID-19 using social meida data mining and artificial intelligence.
The Health Space&Time web application is available at:
FASTER -Fostering Accelerated Scientific Transformations, Education, and Research (National Science Foundation, $3,000,000, 2020-2023)
The National Science Foundation has funded a $3 million high-performance data-analysis and computing instrument project, named FASTER (Fostering Accelerated Scientific Transformations, Education, and Research). FASTER will enable transformative advances in scientific fields that rely on artificial intelligence and machine learning (AI/ML) techniques, big data practices, and high-performance computing (HPC) technologies. The FASTER platform removes significant bottlenecks in research computing by leveraging a technology that can dynamically allocate resources to support workflows.
Funded by National Science Foundation announcement