# Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting

arXiv: https://arxiv.org/abs/2609.21381 · HTML: https://mlsanity.com/paper/2609.21381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Fourier Neural Operator with Learned Deformations for PDEs on General Geometries](https://mlsanity.com/paper/2207.05209/) (2022)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [Retrieval Augmented Time Series Forecasting](https://mlsanity.com/paper/2411.08249/) (2024)
- [TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting](https://mlsanity.com/paper/2412.20810/) (2024)
- [Retrieval-Augmented Foundation Models for Water Level Prediction in the Everglades](https://mlsanity.com/paper/2508.04888/) (2025)
- [Physics-Informed Neural Network Surrogate Models for River Stage Prediction](https://mlsanity.com/paper/2503.16850/) (2025)
- [Accelerating HEC-RAS: A Recurrent Neural Operator for Rapid River Forecasting](https://mlsanity.com/paper/2507.15614/) (2025)
- [Learned Response-Field Inertia Operator for HEC-RAS 2D Water-Surface Elevation Prediction](https://mlsanity.com/paper/2606.06385/) (2026)

## Abstract (arXiv)

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.