By Sarah Sell, University Communications and Marketing
One year after hurricanes Helene and Milton brought historic flooding to the Tampa Bay region, the CRIS-HAZARD app has become a critical tool in helping local communities monitor and respond to extreme storms.
Launched in 2024 by a team of researchers led by USF St. Petersburg GIS and Remote Sensing Professor Barnali Dixon, the Community Resiliency Information System (CRIS) HAZARD app utilizes crowdsourced photos and artificial intelligence (AI) to track flood conditions in real time and to help residents identify potential dangers.
By uploading flood photos, residents can share the information about conditions in their neighborhoods, allowing others nearby to stay informed and respond accordingly.
Dixon compares the app to Waze, the community-driven navigation platform that delivers real-time traffic updates and safety alerts.
“The more accurately we can predict floods, the better we can prepare for them,” Dixon said. “The CRIS-HAZARD app helps both residents and decision-makers by providing up-to-date information.”
A major upgrade over the past year is the addition of 23 static cameras placed throughout Pinellas County. These cameras capture images every 15 minutes from flood-prone areas and are uploaded directly to the CRIS-HAZARD system during a flooding event.
An example of one of the pictures uploaded on the CRIS-HAZARD app near St. Pete Beach during Hurricane Helene.
The CRIS-HAZARD platform combines these camera images with user-submitted, geolocated photos. A specially trained machine learning model analyzes the visuals to estimate water depth and the extent of flooding.
“We can determine the severity of flooding, whether it’s minor, moderate or major,” Dixon said. “By turning people’s real-life experiences into usable data, we can train our AI and machine learning models to make flood predications more accurate.”
Available on both smartphones and desktops, the CRIS-HAZARD app enables users to submit photos of flooding, along with estimated water depths using body reference points such as ankle or knee height. This community input strengthens the system’s accuracy and usefulness during major storms.
Alec Colarusso, a PhD candidate in USF’s School of Geoscience and assistant to Dixon, emphasized the importance of this input during Hurricane Helene.
“Users uploaded photos with a known flood height, and it not only helped others understand what was happening in real time, but it also helped validate our models and future predictions,” he said.
The CRIS-HAZARD app had a soft launch on Sept. 18, 2024. On Sept. 26, Hurricane Helene made landfall on Florida’s west coast, north of Tampa Bay, as a powerful Category 4 hurricane. Less than two weeks later, on Oct. 9, Hurricane Milton struck just south of Tampa Bay as a Category 3 hurricane.
The back-to-back storms caused widespread flooding, and the images collected during these events provided the CRIS-HAZARD team with valuable insight into where the flooding occurred and its severity.
At the time, only eight cameras were in operation in St. Petersburg. Today, the team has expanded to 31 cameras positioned across communities throughout Pinellas County, including Clearwater, Belleair Beach and Tarpon Springs.
“We worked with the flood plain managers and used historical flood data and damage reports to help determine the best locations for the cameras,” Dixon said.
This strategic placement not only ensures broad coverage across high-risk zones but also improves the platform’s ability to interpret and verify crowdsourced data from residents. When residents upload photos, the system automatically identifies the nearest camera and uses computer vision to analyze water depth. That data is then compared with camera images to increase accuracy.
With each new storm, the CRIS-HAZARD app receives data to improve performance, evolving as a vital resource for both emergency officials and everyday residents. By combining AI with community participation, it delivers a faster way to track flooding, support emergency response and adapt to a changing environment.