Metraipolis › archive › dc_ceff0c944931
KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning — arXiv:2610.20640
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20640
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:19:55.013Z
- SHA-256 of the archived text
6731beea19a1def2f94a7df6eca2200bb304cb64eae653d4ea7b5a26e3674f45- Stable URL of this page
https://metraipolis.com/documento/dc_ceff0c944931
How to cite
KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning — arXiv:2610.20640 — arXiv (en), https://arxiv.org/abs/2610.20640 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ceff0c944931 (Metraipolis archive dc_ceff0c944931, sha256 6731beea19a1def2f94a7df6eca2200bb304cb64eae653d4ea7b5a26e3674f45)
BibTeX
@misc{dcceff0c944931,
title = {KNOU-Flood: Advancing global streamflow forecasting with lead-aware probabilistic machine learning — arXiv:2610.20640},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20640},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ceff0c944931; sha256 6731beea19a1def2f94a7df6eca2200bb304cb64eae653d4ea7b5a26e3674f45},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20640. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Global streamflow forecasting supports flood preparedness, yet data-driven models trained on reanalysis lose skill when driven by operational forecasts, increasingly so with lead time. AIFL addresses this shift with a two-stage transfer-learning recipe and a deterministic LSTM, but it feeds one forecast lead time into the whole input window and gives no uncertainty. We ask how far this open recipe can be extended without changing its recurrent core. KNOU-Flood keeps a single-layer LSTM and the two-stage training and changes the information around it: a longer input window (424 days), lead-aware forecast inputs, GraphCast as a second forecast source next to ECMWF HRES, and a latent-noise ensemble trained with the fair CRPS. We compare against a re-implementation of the AIFL recipe (its code is not public) under identical data, stations, splits and metrics. Our contributions are threefold. First, over three seeds and 2,099 test basins (2021-2023), KNOU-Flood reaches a median KGE' of 0.65 at LT1 and 0.48 at LT10 against 0.62 and 0.34, with significant gains at all ten lead times under two scoring protocols, also against a 1024-unit baseline and on held-out basins (one seed each). Second, identical weights give an LT10 KGE' of 0.18 or 0.34 depending on how forecasts are fed, so much of the lead-time decay reported for AIFL is an input-protocol effect; the probabilistic head contributes most to the gain, followed by the raw GraphCast channels, the longer window and mixed fine-tuning. Third, the ensembles reach lower CRPS than probabilistic versions of the baseline, are nearly calibrated with inference-time dropout, and detect 1.5- and 2-year floods better than all baselines; the benefit for rarer floods depends on the seed, and an exploratory tail-weighted variant improves 10-year and larger events. KNOU-Flood is a controlled extension of an open recipe, not a new architecture. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Atmospheric and Oceanic Physics (physics.ao-ph). Pagina del lavoro: https://arxiv.org/abs/2610.20640 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:48:02.639Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).