aiqbench analysis
This study demonstrates how integrating domain-specific hydraulic knowledge graphs with the Chronos-2 time-series foundation model significantly improves water-surface elevation forecasting accuracy. By leveraging graph-conditioned retrieval and residual decoding, the approach outperforms both standard deep learning baselines and traditional physics-informed models on complex river systems. The results validate a promising pathway for enhancing specialized scientific simulations through hybrid AI architectures that combine temporal prediction with structured domain knowledge.
Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting
arXiv:2609.21381v1 Announce Type: cross Abstract: We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface elevation (WSE). We present KG-Chronos-2, which combines a frozen Chronos-2 predictor with exact-state residual decoding, graph-conditioned historical retrieval, and input-aligned correction. We compare the method with persistence, a residual LSTM, project-conditioned recurrent GeoFNO, a hydraulic DCRNN-style model, and frozen Chronos-2. Task-specific fitting uses the 2008 simulation. Evaluation covers 64 fixed 24-hour windows from the 2011 and 2002 simulations at 4,675 cross sections in 71 reaches on a shared geometry. KG-Chronos-2 achieves event-balanced root-mean-square error 0.246970 in native WSE units. It reduces RMSE by 14.13% relative to frozen Chronos-2, 29.38% relative to the hydraulic DCRNN-style model, and 39.54% relative to recurrent GeoFNO. The 95% hierarchical-bootstrap interval for its event-balanced RMSE difference from frozen Chronos-2 is [-0.075177, -0.016317]. KG-Chronos-2 also achieves the lowest active-window and final-lead RMSE among the six completed systems. These results support coupling a frozen temporal predictor to project knowledge for warm-start HEC-RAS forecasting on the fixed benchmark.
Abstract:We investigate whether coupling a time-series foundation model to hydraulic project knowledge improves surrogate forecasting of HEC-RAS water-surface elevation (WSE). We present KG-Chronos-2, which combines a frozen Chronos-2 predictor with exact-state residual decoding, graph-conditioned historical retrieval, and input-aligned correction. We compare the method with persistence, a residual LSTM, project-conditioned recurrent GeoFNO, a hydraulic DCRNN-style model, and frozen Chronos-2. Task-specific fitting uses the 2008 simulation. Evaluation covers 64 fixed 24-hour windows from the 2011 and 2002 simulations at 4,675 cross sections in 71 reaches on a shared geometry. KG-Chronos-2 achieves event-balanced root-mean-square error 0.246970 in native WSE units. It reduces RMSE by 14.13% relative to frozen Chronos-2, 29.38% relative to the hydraulic DCRNN-style model, and 39.54% relative to recurrent GeoFNO. The 95% hierarchical-bootstrap interval for its event-balanced RMSE difference from frozen Chronos-2 is [-0.075177, -0.016317]. KG-Chronos-2 also achieves the lowest active-window and final-lead RMSE among the six completed systems. These results support coupling a frozen temporal predictor to project knowledge for warm-start HEC-RAS forecasting on the fixed benchmark.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.21381 [cs.LG]
(or arXiv:2609.21381v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.21381 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation
arXiv · Jul 24, 2026
TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion
arXiv · Aug 3, 2026
ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
arXiv · Sep 21, 2026
Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Edge-Deployable Virtual Sensing
arXiv · Aug 26, 2026