In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

Harvesting Geographical Microdata of Flash Flood from Social Media

Authors: Lei Zou*, Texas A&M University, Nasir Gharaibeh, Texas A&M University, Michelle Meyer, Texas A&M University, Francisco Olivera, Texas A&M University, Garett Sansom, Texas A&M University
Topics: Geographic Information Science and Systems, Hazards, Risks, and Disasters, Spatial Analysis & Modeling
Keywords: Social media, flash flood, web harvesting, microdata, disaster mitigation
Session Type: Paper
Presentation File: No File Uploaded


Flash floods hit with little lead time for warning and are of such velocity and force, making them one of the most lethal forms of natural hazards. Over the past two decades, approximately 72% of all flood-related fatalities, 72% of all flood-related injuries, and 52% of flood-related economic losses in the U.S. are attributed to flash flooding. However, studies of the circumstances of flash flood deaths and injuries rarely provide adequate data on the underlying causes of these impacts and the socioeconomic characteristics of the victims and affected communities, making it difficult to develop effective interventions to reduce these negative impacts. Social media provides an innovative approach to share flash flood information and impacts at very fine geographical scale. This research aims to harvest geographical microdata of flash flood from social media. First, flash flood related data are collected from Flash Flood Observation Database and social media platforms. Second, the information is extracted at the finest possible scale on five data components (3W2H): incident site (Where), the incident time (When), socioeconomic information on the victim or affected community (Who), flood conditions (Hydro-meteorology), and the causes of injury or death (How). Third, we analyze the spatial-temporal patterns of flash flood occurrences and public awareness. Finally, the underlying social, natural, and built environmental factors leading to flash flood deaths and injuries are identified. The developed geographical microdata of flash flood will shed light on modeling the causal pathways leading to flash flood fatalities/injuries, and inform flash flood mitigation and preparedness.

To access contact information login