Skip to main content
You have permission to edit this article.
Texas A&M researchers develop flood prediction tool

Texas A&M researchers develop flood prediction tool

  • 0

Texas A&M University researchers have developed a flood prediction tool that can improve emergency response during hurricanes.

The almost real-time device uses an algorithm to determine the flow of water with the help of information about a city’s architecture, drainage systems and flood gauges, according to a Texas A&M Engineering website news release. 

Ali Mostafavi, assistant professor in the Zachry Department of Civil and Environmental Engineering, said in the release that knowing where water will flow is critical for first responders as they plan their rescues.

“Our new algorithm considers the underground drainage channels to provide an accurate representation of how floods propagate,” Mostafavi said in the release. “This tool, we think, can vastly help disaster management because first responders will be able to see which way flood water will flow in real time.”  

Drainage channels meet together at junctions called nodes, the release states. Flooding one channel can cause floods to spread. 

When creating the probability-based model, Mostafavi and his team used water-level readings on flood gauges from events such as Hurricane Harvey in 2017 and Houston’s Memorial Day flood in 2015. When the algorithm learned the water flow patterns of the drainage network for the heavy rainfalls, they checked if it could predict the flood pattern that happened on Houston’s Tax Day in 2016. In the test, the model was 85% accurate. 

Mostafavi said in the release that the test proves that the model should be able to predict how new floods will occur, and can help emergency responders take early action for evacuations.

Before the new tool, physics-based models have been used to predict where floods may occur by looking at physical features of the area and how those features will impact the flow of water. Mostafavi said in the release that those methods are useful for understanding when and where floods happen in normal rainfall, they are not as helpful for torrential rainfall. 

“Physics-based models offer one perspective on how floods can spread, which is extremely useful, but the picture they provide is somewhat incomplete,” Mostafavi said in the release. “We wanted to use existing data on how past floods have spread through the drainage channels to develop a model that would be able to predict, within a certain level of preciseness, how future floods will spread.”

The new algorithm, however, could be inaccurate if sensors on flood gauges don’t work. But in the release, Mostafavi said the predictions coming from physics-based models with the ones from the algorithm could make it accurate in those scenarios. 

“Traditional models and our data-driven models can be used to complement each other to give a more precise picture of where flood water will go next,” Mostafavi in the release. “Hurricanes of the magnitude of Harvey or Katrina are generally considered a one-in-a-thousand-year event, but they may not be as rare if we consider the changes in global weather patterns because of climate change. But we now have more robust tools to weather the storm.”

More information on the algorithm is in the December issue of the Computer-Aided Civil and Infrastructure Engineering journal and at

Get local news delivered to your inbox!

* I understand and agree that registration on or use of this site constitutes agreement to its user agreement and privacy policy.

Related to this story

Most Popular

Recommended for you

Get up-to-the-minute news sent straight to your device.


Breaking News

Weekend Things to Do

News Alert