AI digital twin predicts basin-wide flood depths from few gauges
C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
Artificial Intelligence
Summary
Flood managers need to know how deep floodwater is and where it will go, but they usually only have data from a few river gauges. The authors created C-STRIDE, an AI model that uses a small number of stream gauges along with terrain and rainfall data to create detailed flood maps for an entire river basin. It can quickly update its predictions up to a day ahead without complex recalculations. Tests in a river basin near Chicago showed it predicts water depths much faster and more accurately than traditional models.
What this means in practice
- •For emergency management teams: Provide fast, updated flood maps across a river basin using limited gauge data for improved flood response planning.
- •For water resource planners: Use AI-driven flood depth predictions that incorporate terrain and rainfall to support infrastructure and flood mitigation decisions.
Authors
Yanjie Tong, Phillip Si, Yuan Qiu, Peng Chen
Abstract
Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a flood, however, real-time measurements come from only a handful of stream gauges, and high-resolution hydrodynamic models are too costly to rerun each time new data arrive or to run as large ensembles. We present C-STRIDE, an observation-driven AI digital twin that turns short records from a few stream gauges, together with terrain and rainfall, into basin-wide maps of water depth and extends these predictions up to a day ahead. It is trained on simulations from a calibrated two-dimensional hydrodynamic model and needs no separate data-assimilation step. In the Des Plaines River basin near Chicago, six gauges inform predictions over 4.2 million 30-m grid cells. Terrain improves the predictions most, rainfall keeps errors from growing over longer horizons, and together they reduce errors by about 40% compared with gauge records alone. When future rainfall is known, errors remain near 15% one day ahead, compared with nearly 40% without rainfall. Given real instead of simulated gauge records, the model shifts its predictions toward the observed hydrographs at three of six gauges without retraining, and it runs about 150 times faster than the hydrodynamic model. These results show how sparse gauges, terrain, and rainfall can be combined into fast, continuously updated flood predictions, a step toward operational flood digital twins that still requires testing with real-time data and rainfall forecasts.