Tracked coastal flooding during Hurricanes Helen and Milton

A team of researchers led by USF St. Petersburg GIS and Remote Sensing Professor Barnali Dixon used the CRIS-HAZARD application to analyze real-time flooding in Pinellas County, which has 588 miles of coastline. The app also received data from users in neighboring Hillsborough County during Hurricane Milton, allowing the team to expand its research.

Developed in collaboration with researchers at Georgia Tech, the app combines volunteer-provided geographic information and crowdsourced community data, such as photos and videos, with near real-time flood data. Using dynamic modeling and mapping tools, including artificial intelligence (AI), the application can determine and extract estimated water level heights from submitted images, which will be used to inform emergency managers and policymakers.

The CRIS-HAZARD app was launched on September 18th. Eight days later, Hurricane Helen struck the west coast of Florida north of Tampa Bay as a Category 4 hurricane. On October 9, Hurricane Milton struck the west coast of Florida south of Tampa Bay as a Category 3 hurricane.

Images captured during successive hurricanes gave the team important information about how much flooding occurred and where in the Tampa Bay area.

“People were using it to report what was happening in their backyard,” said Dixon, who is also executive director of the USF Initiative on Coastal Adaptation and Resilience (iCAR). “This information is their life experience, and we want to take that experience and turn it into data using artificial intelligence tools that will process the images and determine the depth of the water. We can use this data to calibrate and validate models.”

In addition to the data provided to researchers, images and videos are made available to other users so they can see where flooding is occurring, which helps inform them of hazards in the community.

Dixon compares it to the real-time traffic app Waze, where drivers can see traffic data and police activity on roads and highways.

“We display the data in real time for about seven days, then the data is archived,” Dixon said. “For example, if it’s raining heavily today, you want to know what’s happening today, not a month or two months ago. But the data remains there for us to access and analyze.”

In 2023, Dixon received a $1.5 million National Science Foundation grant to create the app. Since then, her team has made significant progress. They have installed 14 cameras in St. Petersburg and plan to install 30 more throughout Pinellas County.

The cameras are positioned in front of five-foot posts with reflective tape that shows flooding occurring. Each strip is spaced six inches apart. Images captured by cameras during Hurricane Helen show that in many places the water level rose above the levee by about 3.5 feet.

The new application, which provides an interactive user interface, is based on the existing Community Resilience Information System (CRIS), a website created in 2020 by iCAR.

The CRIS platform uses crowdsourced data to identify climate-related vulnerabilities in local communities. Residents can enter information related to issues such as floods and power outages. This information can then be used by politicians and local leaders to make decisions about policies and resource allocation. The data also allows emergency managers to identify congested areas of people who need transportation assistance or who rely on power for medical needs.

Dixon has been working with community leaders for several years in the Childs and Bartlett Park neighborhoods of St. Petersburg, where residents have successfully used the system to prepare for extreme storms. Through the CRIS website, members can view maps and assess the risk of storm surge and sea level rise. They can also share their own information and suggest ways to improve the system.

“We have used this app in all of our local municipalities,” said Erica Hall, executive director of the Florida Food Policy Council. “As a community leader and liaison, it will help communities understand the connections between sea level rise, climate change, extreme heat and coastal flooding. Some vulnerable coastal areas also exhibit problems of food insecurity and health disparities. Having a CRIS map of these issues shows that we are a community leader and connector. a story that will allow the community to understand.”

As principal investigator, Dixon developed the app with co-principal investigators Yi Qiang of the USF School of Geosciences and two other Georgia Tech researchers: Subhrajit Guhathakurta of the College of Design and Peng Chen of the College of Computing.

The research team will continue to work with community partners in St. Petersburg and other flood-prone coastal areas of Pinellas County to improve the app. As the CRIS-HAZARD app gains new users and data, the team hopes to make it available to communities across the country.