Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Recently, rainfall‐runoff simulations in small headwater basins have been improved by methodological advances such as deep neural networks (NNs) and hybrid physics‐NN models—particularly, a genre called differentiable modeling that intermingles NNs with physics to learn relationships between variables. However, hydrologic routing simulations, necessary for simulating floods in stem rivers downstream of large heterogeneous basins, had not yet benefited from these advances and it was unclear if the routing process could be improved via coupled NNs. We present a novel differentiable routing method ( δ MC‐Juniata‐hydroDL2) that mimics the classical Muskingum‐Cunge routing model over a river network but embeds an NN to infer parameterizations for Manning's roughness ( n ) and channel geometries from raw reach‐scale attributes like catchment areas and sinuosity. The NN was trained solely on downstream hydrographs. Synthetic experiments show that while the channel geometry parameter was unidentifiable, n can be identified with moderate precision. With real‐world data, the trained differentiable routing model produced more accurate long‐term routing results for both the training gage and untrained inner gages for larger subbasins (>2,000 km 2 ) than either a machine learning model assuming homogeneity, or simply using the sum of runoff from subbasins. The n parameterization trained on short periods gave high performance in other periods, despite significant errors in runoff inputs. The learned n pattern was consistent with literature expectations, demonstrating the framework's potential for knowledge discovery, but the absolute values can vary depending on training periods. The trained n parameterization can be coupled with traditional models to improve national‐scale hydrologic flood simulations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The use of accurate estimates of channel bankfull depth and top-width improves channel flow routing models (Bindas et al., 2024;Brackins et al., 2021;Getirana et al., 2013;Han et al., 2020).”
From Enhancing River Channel Dimension Estimation: A Machine Learning Approach Leveraging the National Water Model, Hydrographic Networks, and Landscape Characteristics (2024) · cites this paper as Bindas et al., 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
The hydraulic geometry of stream channels and some physiographic implications
Leopold, L. B., & Maddock, T. (1953) · Professional Paper · doi:10.3133/pp252 · Cited by 2,966 · cited 1×
“For this, because at-a-site hydraulic geometries (Gleason, 2015; Leopold & Maddock, 1953; Orlandini & Rosso, 1998) lead to a power-law relation between top width ( w [m]) and depth ( d [m]), we can assume such a relationship: where p [m] and q [−] are linear and exponential parameters,…”
BackgroundThe Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
Hochreiter, S. (1998) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488598000094 · Cited by 2,939
Feng, D., Fang, K., & Shen, C. (2020) · Water Resources Research · doi:10.1029/2019wr026793 · Cited by 633
Self-citationFeng, D., Beck, H., Lawson, K., & Shen, C. (2023) · Hydrology and Earth System Sciences · doi:10.5194/hess-27-2357-2023 · Cited by 197
Self-citationThe Value of SMAP for Long-Term Soil Moisture Estimation With the Help of Deep Learning
Fang, K., Pan, M., & Shen, C. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2872131 · Cited by 186
Self-citation
Research works printed but not linked: 89
- 10.5194/bg-20-2671-2023 · DOI
- 10.1007/s11069-020-04438-2 · DOI
- Arcement G. J., 1989, Guide for selecting Manning’s roughness coefficients for natural channels and flood plains
- Baydin A. G., 2018, Automatic differentiation in machine learning: A survey, Journal of Machine Learning Research, 18, 1
- 10.1016/j.jhydrol.2005.07.007 · DOI · Paper page
- 10.1029/2008wr007536 · DOI
- 10.1016/j.jhydrol.2005.01.023 · DOI
- 10.14358/PERS.72.3.287 · DOI · Paper page
- 10.1029/2018WR022797 · DOI · Paper page
- 10.1080/00221686909500264 · DOI · Paper page
- 10.1002/hyp.8070 · DOI
- 10.1175/2011JHM1345.1 · DOI · Paper page
- 10.1016/j.envsoft.2012.12.011 · DOI
- 10.1038/s41558-018-0257-z · DOI · Paper page
- 10.1002/ird.239 · DOI · Paper page
- 10.3389/frwa.2020.00028 · DOI
- Falcone J. A.(2011).GAGES‐II: Geospatial attributes of gages for evaluating streamflow[Dataset]. InGAGES‐II: Geospatial Attributes of Gages for Evaluating Streamflow. USGS Unnumbered Series.U.S. Geological Survey.https://doi.org/10.3133/70046617 · DOI · Paper page
- Fan W. Ma Y. Li Q. He Y. Zhao E. Tang J. &Yin D.(2019).Graph neural networks for social recommendation. arXiv.https://doi.org/10.48550/arXiv.1902.07243 · DOI · Paper page
- 10.1002/2016WR020283 · doi:10.1002/2016wr020283
- 10.1002/2017gl075619 · DOI · Paper page
- 10.1029/2022WR032404 · DOI · Paper page
- France‐Presse A., 2022, At least 59 dead and millions stranded as floods devastate India and Bangladesh
- 10.1016/j.jhydrol.2019.04.068 · DOI
- Friedl M. &Sulla‐Menashe D.(2019).MCD12Q1 MODIS/Terra+Aqua land cover type yearly L3 global 500 m SIN grid V006[Dataset].https://doi.org/10.5067/MODIS/MCD12Q1.006 · doi:10.5067/modis/mcd12q1.006 · Paper page
- 10.1175/JHM-D-12-021.1 · DOI · Paper page
- 10.1177/0309133314567584 · DOI · Paper page
- Glorot X., 2010, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249
- 10.5194/hessd-12-10289-2015 · doi:10.5194/hessd-12-10289-2015
- 10.2118/479-G · doi:10.2118/479-g
- 10.3390/w14101643 · DOI
- 10.1109/ICCIA52082.2021.9403565 · DOI
- 10.1002/2017GL075860 · DOI
- 10.1029/2018WR023897 · DOI
- 10.1137/1.9781611976700.69 · DOI
- 10.5194/nhess-19-2405-2019 · DOI · Paper page
- Kalyanapu A. J., 2009, Effect of land use‐based surface roughness on hydrologic model output, Journal of Spatial Hydrology, 9, 51
- 10.1016/j.envsoft.2017.02.001 · DOI · Paper page
- 10.1016/j.jhydrol.2023.129682 · DOI
- Kingma D. P. &Ba J.(2017).Adam: A method for stochastic optimization. arXiv.https://doi.org/10.48550/arXiv.1412.6980 · DOI · Paper page
- 10.1080/09535314.2016.1232701 · DOI
- 10.5194/hess-23-5089-2019 · DOI · Paper page
- 10.1016/S0893-6080(05)80131-5 · DOI · Paper page
- 10.1175/JHM-D-12-015.1 · DOI · Paper page
- 10.5194/hess-26-665-2022 · DOI
- 10.1016/j.apr.2021.101260 · doi:10.1016/j.apr.2021.101260
- 10.5194/gmd-16-1553-2023 · DOI
- 10.1029/2021GL096847 · DOI
- 10.1016/j.jhydrol.2022.127819 · DOI
- 10.1002/hyp.14936 · DOI
- 10.1029/2009WR008294 · DOI · Paper page
- Mays L. W., 2010, Water resources engineering
- Mays L. W., 2019, Water resources engineering
- 10.3389/frwa.2020.574917 · DOI
- 10.5194/gmd-9-2223-2016 · DOI
- 10.1111/1752-1688.12389 · DOI
- 10.1016/0022-1694(70)90255-6 · DOI · Paper page
- Natural Environment Research Council, 1975, Flood routing studies
- 10.1029/2001wr001187 · DOI
- 10.1029/98wr00257 · DOI
- 10.1038/s41597-021-00964-1 · DOI · Paper page
- 10.1016/j.jhydrol.2021.126455 · DOI · Paper page
- 10.5194/hess-17-4577-2013 · DOI · Paper page
- 10.1061/(ASCE)0733-9429(1986)112:8(716)[ · doi:10.1061/(asce)0733-9429(1986)112:8(716)[
- 10.1038/nclimate3168 · DOI · Paper page
- 10.1029/2023WR034420 · DOI
- 10.1088/1748-9326/abd501 · DOI
- 10.1002/hyp.14400 · DOI
- 10.3133/tm6B9 · doi:10.3133/tm6b9
- Rice D., 2019, Mississippi river flood is longest‐lasting in over 90 years, since “Great Flood” of 1927
- 10.1016/j.scitotenv.2023.162930 · DOI
- 10.1038/s43017-023-00450-9 · DOI · Paper page
- 10.3389/frwa.2021.681023 · DOI
- 10.1002/9781119646181.ch19 · DOI
- 10.1016/j.envsoft.2014.05.006 · DOI
- 10.1002/wrcr.20189 · DOI · Paper page
- 10.1016/j.advwatres.2010.09.002 · DOI · Paper page
- 10.1002/2015WR018086 · DOI
- 10.1029/2021WR030394 · DOI
- 10.5194/hess-26-5163-2022 · DOI
- 10.1038/s41467-021-26107-z · DOI · Paper page
- 10.1038/s41592-019-0686-2 · DOI · Paper page
- 10.1038/nclimate2893 · DOI · Paper page
- 10.1038/s41467-022-28770-2 · DOI · Paper page
- Xia Y. Mitchell K. Ek M. Sheffield J. Cosgrove B. Wood E. et al. (2009).NLDAS primary forcing data L4 hourly 0.125 x 0.125 degree V002 (NLDAS_FORA0125_H)[Dataset].Goddard Earth Sciences Data and Information Services Center (GES DISC).https://doi.org/10.5067/6J5LHHOHZHN4 · DOI
- 10.1029/2011JD016048 · DOI · Paper page
- 10.1029/2019WR025326 · DOI · Paper page
- 10.2166/nh.2018.175 · doi:10.2166/nh.2018.175
- 10.1021/acs.est.0c06783 · DOI · Paper page
- 10.1109/TGRS.2021.3094321 · DOI
Cited by
Deep learning for water quality
Zhi, W., Appling, A. P., Golden, H. E., Podgorski, J., & Li, L. (2024) · Nature Water · doi:10.1038/s44221-024-00202-z · Cited by 364
Modaresi Rad, A., Johnson, J. M., Ghahremani, Z., Coll, J., & Frazier, N. (2024) · Journal of Geophysical Research: Machine Learning and Computation · doi:10.1029/2024jh000173 · Cited by 11
Li, P., Song, Y., Pan, M., Lawson, K., & Shen, C. (2025) · Hydrology and Earth System Sciences · doi:10.5194/hess-29-6829-2025 · Cited by 7
Self-citation
Metadata
- Authors
- Bindas, T., Tsai, W., Liu, J., Rahmani, F., Feng, D., Bian, Y., Lawson, K., & Shen, C.
- Affiliations
- Civil and Environmental Engineering The Pennsylvania State University University Park PA USA
- Hydraulic and Ocean Engineering National Cheng Kung University Tainan City ROC
- Amazon Search Palo Alto CA USA
- ORCID
- Venue
- Water Resources Research
- Publisher
- American Geophysical Union (AGU)
- Published
- 2024-01
- Volume
- 60
- Issue
- 1
- ISSN
- 0043-1397
- 1944-7973
- Cited by
- 82
- References
- 6
- Language
- en
- Licence
- creativecommons.org/licenses/by/4.0/ (am, 7 d)
- creativecommons.org/licenses/by/4.0/ (vor, 7 d)
- doi.wiley.com/10.1002/tdm_license_1.1 (tdm)
- Funders
- National Oceanic and Atmospheric Administration (NA22NWS4320003)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.