Project Title

Estimating Road Inundation Levels Due to Recurrent Flooding from Image Data

Collaborating Universities

Old Dominion University
1 Old Dominion University
Norfolk, VA 23529

University of Virginia
351 McCormick Dr.
P.O. Box 400742
Charlottesville, VA 22904-4742

Principal Investigator(s)

Cetin, Mecit (ODU)

Iftekharuddin, Khan M. (ODU)

Goodall, Jon (UVA)

Total Project Costs


Start Date


Completion Date



The frequency of nuisance flooding events according to a recent report by NOAA[1] is increasing and accelerating in many locations especially along much of the U.S. East Coast which is attributable to Sea Level Rise (SLR). Based on median values of relative SLR projections, by 2050, the majority of US coastal cities will experience recurrent flooding thirty or more days per year due to the accelerating impacts of SLR [2]. Whereas monitoring conditions of all public-serving infrastructures is important under the threat of flooding, it is particularly valuable to know the inundations on roadways since many societal functions depend on a functioning transportation infrastructure including routing of emergency vehicles and delivery of goods and services to support commerce. Today, there is no effective system for monitoring inundations in near real-time for large-scale transportation networks and for communities that are particularly vulnerable to SLR (e.g., Hampton Roads VA, Wilmington DE). In addition, there is no exiting system to collect, archive, and automatically analyze inundation levels effectively for largescale networks. Such data are essential for making both operational and planning decisions. Accurate and rich datasets for quantifying the impacts of flooding are necessary for developing sustainable and resilient policies and solutions.


Overall, this research proposes to develop fundamental methodologies, algorithms, and predictive capabilities to survey and estimate water inundations due to flooding based on image data. Even though the images for this research will primarily be obtained from video surveillance cameras, the principles and methodologies developed will be applicable to other image sources (e.g., from smartphones, social media). Specific research goals are: (i) Collection of a large image dataset to support the estimation of inundation levels; (ii) Development of machine learning algorithms to extract inundation levels from image data; (iii) Evaluation of the accuracy of the algorithms in predicting inundation levels under different conditions; (iv) Development of data-driven methods for predicting future inundation levels based on various factors (e.g., expected and past rainfall, drainage, topography). After the basic tools are developed, the research team plans to evaluate them based on images collected during an actual flooding event(s) in Norfolk, VA.



Web Links to Reports and to the Project website