Metraipolis › archive › dc_e80e5d26cb53
From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents — arXiv:2611.06382
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06382
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:56.015Z
- SHA-256 of the archived text
72bacc500ca1aebb8e3f31e2a3d14caacaa1f412be08565daca570ac70ad67cb- Stable URL of this page
https://metraipolis.com/documento/dc_e80e5d26cb53
How to cite
From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents — arXiv:2611.06382 — arXiv (en), https://arxiv.org/abs/2611.06382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e80e5d26cb53 (Metraipolis archive dc_e80e5d26cb53, sha256 72bacc500ca1aebb8e3f31e2a3d14caacaa1f412be08565daca570ac70ad67cb)
BibTeX
@misc{dce80e5d26cb53,
title = {From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents — arXiv:2611.06382},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06382},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e80e5d26cb53; sha256 72bacc500ca1aebb8e3f31e2a3d14caacaa1f412be08565daca570ac70ad67cb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dooge asked whether hydrology has laws at the catchment scale. We ask whether a low-dimensional system built under physical laws can match the accuracy of neural networks that outperform process-based models on the same inputs. Three laws constrain a lumped catchment model. Conservation makes it a flux-connected storage network, dissipation fixes the sign of every flux and aggregation determines how the unresolved composition enters the fluxes, through effective laws over threshold distributions and a memory of the forcing. These laws admit four kinds of refinement. A parsimonious model under them, CaRT (11 parameters per catchment), is refined in a loop assisted by AI agents. Each refinement addresses an observed deficit through a hypothesis from the literature. The result, CaRT+, has fourteen states, 35 parameters per catchment and no daily neural network. Most refinements follow from aggregation over thresholds or from variables that carry no water but modulate fluxes. On 602 British and 593 US gauged catchments, single CaRT+ models reach median Nash-Sutcliffe efficiencies of 0.863 and 0.765 in held-out years. A stateful LSTM reaches 0.869 and 0.751 and an entity-aware LSTM 0.862 and 0.754, while three-seed LSTM ensembles remain ahead of the CaRT+ ensemble by 0.003-0.012 in median paired NSE. On 505 drier Australian gauged catchments unused in development, single CaRT+ models reach 0.778 against 0.762 and 0.753 for the two LSTMs. The results suggest that catchment-scale laws exist as laws of form, with the constitutive families shared and only their parameters learned. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Dynamical Systems (math.DS); Geophysics (physics.geo-ph). Pagina del lavoro: https://arxiv.org/abs/2611.06382 — 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 2026-11-05T18:12:49.056Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).