Logo image
Back
HydroGAT: Distributed Heterogeneous Graph Attention Transformer for Spatiotemporal Flood Prediction
Conference proceeding   Open access

HydroGAT: Distributed Heterogeneous Graph Attention Transformer for Spatiotemporal Flood Prediction

Aishwarya Sarkar, Autrin Hakimi, Xiaoqiong Chen, Hai Huang, Chaoqun Lu, Ibrahim Demir and Ali Jannesari
Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems, pp.1019-1030
ACM Conferences
SIGSPATIAL '25: 33rd ACM International Conference on Advances in Geographic Information Systems
11/03/2025
DOI: 10.1145/3748636.3764172
url
https://doi.org/10.1145/3748636.3764172View
Published (Version of record) Open Access

Abstract

Accurate flood forecasting remains a critical challenge for water-resource management, as it demands simultaneous modeling of local, time-varying runoff drivers (e.g., rainfall-induced peaks, base- flow trends) and complex spatial interactions across a river network. Traditional data-driven approaches, such as convolutional networks and sequence-based models, ignore topological information about the region. Graph Neural Networks (GNNs), in contrast, propagate information exactly along the river network, making them ideal for learning hydrological routing. However, state-of-the-art GNN-based flood prediction models still collapse pixels to coarse catchment polygons because the cost of training explodes with graph size and higher resolution. Furthermore, most existing methods treat spatial and temporal dependencies separately, either applying GNNs solely on spatial graphs or transformers purely on temporal sequences, thus failing to simultaneously capture spatiotemporal interactions critical for accurate flood prediction. To address these limitations, we introduce a heterogenous basin graph to represent every land and river pixel as a node connected by both physical hydrological flow directions as well as inter-catchment relationships. We also propose HydroGAT, a novel spatiotemporal network that adaptively learns both local temporal importance as well as most influential upstream locations. Evaluated in two Midwestern US basins and across five baseline architectures, our model achieves higher NSE (up to 0.97), improved KGE (up to 0.96), and low bias (PBIAS within ± 5%) in hourly discharge prediction, while offering interpretable attention maps that reveal sparse, structured intercatchment influences. To support high-resolution basin-scale training, we develop a distributed data-parallel pipeline that scales efficiently up to 64 NVIDIA A100 GPUs on NERSC Perlmutter supercomputer, demonstrating up to 15× speedup across machines. Our code is available at https://github.com/swapp-lab/HydroGAT.
 Computing methodologies -- Artificial intelligence -- Distributed artificial intelligence Computing methodologies -- Modeling and simulation -- Model development and analysis

Details

Metrics

7 Record Views
Logo image