← Back to all news
arXiv AI By Edward Holmberg, Elias Ioup, Mahdi Abdelguerfi

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

Read the original on arXiv AI →

The paper introduces KG‑Chronos‑2, a surrogate forecasting model that augments a frozen Chronos‑2 time‑series predictor with knowledge‑graph‑conditioned retrieval and correction mechanisms for HEC‑RAS water‑surface elevation (WSE) prediction. In a benchmark involving 64 24‑hour windows across 4,675 cross sections, KG‑Chronos‑2 outperforms persistence, residual LSTM, GeoFNO, and hydraulic DCRNN‑style models, achieving a 0.246970 event‑balanced RMSE and reducing error by 14.13% relative to frozen Chronos‑2. The model also attains the lowest active‑window and final‑lead RMSE among the evaluated systems, demonstrating the benefit of coupling a frozen temporal predictor with project‑specific knowledge for warm‑start HEC‑RAS forecasting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 28

AIFL: A Global Daily Streamflow Forecasting Model Using a Deterministic LSTM Pre-trained on ERA5-Land and Fine-tuned on IFS

arXiv:2602. 16579v2 Announce Type: replace-cross Abstract: Reliable global streamflow forecasting is essential for flood preparedness and water resource management, yet data-driven models often suffer from a performance gap when transitioning from historical reanalysis to operational forecast products.

By Maria Luisa Taccari, Kenza Tazi, Ois\'in M. Morrison, Andreas Grafberger, Juan Colonese, Corentin Carton de Wiart, Christel Prudhomme, Cinzia Mazzetti, Matthew Chantry, Florian Pappenberger
fine-tuningbenchmarks
More like this →
arXiv Machine Learning
1d ago

Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography

Varda‑single‑1.0 is a medium‑range, data‑driven weather prediction system designed for Switzerland’s Alpine region, delivering hourly deterministic forecasts at 1 km resolution and global forecasts at 31 km. It uses two independently trained stretched‑grid Graph Transformer models—an autoregressive forecaster and a temporal downscaler—trained through a curriculum that starts with ERA5 reanalysis, proceeds to a 20‑year regional reanalysis, and ends with fine‑tuning on operational analyses. Over a one‑year verification, Varda‑single matches or surpasses MeteoSwiss’s numerical weather prediction baselines for most key metrics, though it underestimates local wind peaks and produces smoother convective precipitation fields. whyItMatters":"The system demonstrates that high‑resolution machine‑learning models can rival traditional numerical weather prediction in complex terrain, offering a complementary tool for operational forecasting and research."

By Alberto Pennino, Francesco Zanetta, Michele Cattaneo, Claire Merker, Radi Radev, Jonas Bhend, Louis Frey, Hugues de Laroussilhe, Oph\'elia Miralles, Carlos Osuna, Daniele Nerini, Andreas Pauling, Daniel Hupp, Ulrich Hamann, Mary McGlohon, Marti Bosch, Luca Lanzilao, Marco Arpagaus, Lukas Jansing, Daniel Leuenberger, Mark A. Liniger, Katrin Ehlert, Matthew Chantry, H\aa{}vard Homleid Haugen, Gert Mertes, Ana Prieto Nemesio, Mario Santa Cruz, Jasper Wijnands, Gabriel Moldovan, Harrison Cook, Oliver Fuhrer
llmsfine-tuning
More like this →