Development of a National-Scale Big Data Analytics Pipeline to Study the Potential Impacts of Flooding on Critical Infrastructures and Communities
Date of Award
Open Access Thesis
Computer Science and Engineering
With the rapid development of the Internet of Things (IoT) and Big data infrastructure, crowdsourcing techniques have emerged to facilitate data processing and problem solving particularly for flood emergences purposes. A Flood Analytics Information System (FAIS) has been developed as a Python Web application to gather Big data from multiple servers and analyze flooding impacts during historical and real-time events. The application is smartly designed to integrate crowd intelligence, machine learning (ML), and natural language processing of tweets to provide flood warning with the aim to improve situational awareness for flood risk management and decision making. FAIS allows the user to submit search request from the United States Geological Survey (USGS) as well as Twitter through a series of queries, which is used to modify request URL sent to data sources. This national scale prototype combines flood peak rates and river level information with geotagged tweets to identify a dynamic set of at-risk locations to flooding. The list of prioritized areas can be updated every 15 minutes as the crowdsourced data and environmental information and condition change. In addition, FAIS uses Google Vision API (application programming interface) and image processing algorithms to detect objects (flood, road, vehicle, river, etc.) in time-lapse digital images and build valuable metadata into image catalog. The application performs Flood Frequency Analysis (FFA) and computes design flow values corresponding to specific return periods that can help engineers in designing safe structures and in protection against economic losses due to maintenance of civil infrastructure. FAIS is successfully tested in real-time during Hurricane Dorian flooding event across the Carolinas where the storm made extensive damage and disruption to critical infrastructure and the environment. The prototype is also verified during historical events such as Hurricanes Matthew and Florence flooding for the Lower PeeDee Basin in the Carolinas.
Donratanapat, N.(2019). Development of a National-Scale Big Data Analytics Pipeline to Study the Potential Impacts of Flooding on Critical Infrastructures and Communities. (Master's thesis). Retrieved from https://scholarcommons.sc.edu/etd/5506