An FIU team has developed an AI model that offers near-real-time simulations of flood scenarios and suggests actionable strategies for water managers responding to flooding in Florida’s vast canal system. “Accuracy is obviously very important to us, because overestimation of water stages can cause false alarms and panic while underestimation can result in unexpected and dangerous flooding events,” says researcher Giri Narasimhan.

Using historical data collected by the South Florida Water Management District, the system was trained to recognize how rainfall, tides, groundwater, and storm surge interact across the region. Past storms were used to fine-tune the model, which was then tested on the Miami River, which runs through Miami and drains into Biscayne Bay. In addition to helping manage immediate flood risks, the model could also support long-term infrastructure planning.

• GIRI NARASIMHAN
• Jayantha Obeysekera