Leveraging Deep Learning Recurrence and Attention Mechanisms for Flood Forecasting and Assessment

Author

• Elnaz HeidariFollow

Date of Award

8-2026

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Civil Engineering

Committee Chair/Advisor

Abdul A. Khan

Committee Member

Nadarajah Ravichandran

Committee Member

M.Z. Naser

Committee Member

Chao Fan

Abstract

Predicting how much water will flow in rivers and streams is important for managing floods, water supply, and the environment. Traditionally, government agencies have used complex models, such as the National Water Model (NWM), which simulate how much water moves through landscapes using physical laws and real-world data. However, recent advances in Artificial Intelligence (AI) have enabled new ways to make these predictions. This research explored whether AI-based models could predict river discharge more accurately. These AI models learn patterns from past data instead of relying only on physical rules. To find out how well they work, the AI models were trained using past records of river and weather conditions. The AI models’ predictions were compared with those made by NWMv3.0, which is currently used in many official settings. The results showed that the AI models were not only accurate but also often performed better than the NWMv3.0 in forecasting streamflow. This suggests that AI can be a powerful tool in obtaining an improved streamflow forecast, which could help better prepare for floods, manage water resources, and protect ecosystems.

Recommended Citation

Heidari, Elnaz, "Leveraging Deep Learning Recurrence and Attention Mechanisms for Flood Forecasting and Assessment" (2026). All Dissertations. 4406.
https://open.clemson.edu/all_dissertations/4406

Author ORCID Identifier

0009-0009-3865-5532