Accurate river flow estimation is essential for water resources management, yet continuous in situ observations remain scarce across rivers globally and particularly in Asia and Africa. This study explores the potential of integrating SWOT satellite–derived river width and water surface elevation with limited gauging data to reconstruct river flow of China’s vast river network. The study compared four machine learning models for data integration: Random Forest (RF), XGBoost (XGB), Multi-Layer Perceptron (MLP), and Transformer (TF). A temporally ordered five-fold cross-validation framework was used to evaluate both interpolating and extrapolating performance. Under interpolating mode, RF and XGB effectively reproduced the observed hydrographs, capturing flow variability and extremes. Under extrapolation mode, all models show reduced skill due to short record length, seasonal incompleteness, and zero-flow effects, although neural network models exhibited relatively better performance. These results demonstrate a potential solution for river flow gap filling by using SWOT satellite observations after appropriate data processing, however, the approach requires substantially larger and more diverse training datasets for improving extrapolation performance.
- Open Access
- Article
New Insights in Prediction of Daily River Flow Using SWOT Observations and Machine Learning
Author Information
Received: 09 Feb 2026 | Revised: 22 Mar 2026 | Accepted: 23 Mar 2026 | Published: 13 Apr 2026
Abstract
Keywords
deep learning | interpolation | extrapolation | ensemble tree models | river width | water surface elevation
References
- 1.
Nearing, G.; Cohen, D.; Dube, V.; et al. Global prediction of extreme floods in ungauged watersheds. Nature 2024, 627, 559–563. https://doi.org/10.1038/s41586-024-07145-1.
- 2.
Newman, A.J.; Clark, M.P.; Sampson, K.; et al. Development of a large-sample watershed-scale hydrometeorological data set for the contiguous USA: Data set characteristics and assessment of regional variability in hydrologic model performance. Hydrol. Earth Syst. Sci. 2015, 19, 209–223. https://doi.org/10.5194/hess-19-209-2015.
- 3.
Oubanas, H.; Gejadze, I.; Malaterre, P.-O.; et al. Discharge Estimation in Ungauged Basins Through Variational Data Assimilation: The Potential of the SWOT Mission. Water Resour. Res. 2018, 54, 2405–2423. https://doi.org/10.1002/2017WR021735.
- 4.
Biancamaria, S.; Lettenmaier, D.P.; Pavelsky, T.M. The SWOT Mission and Its Capabilities for Land Hydrology. Surv. Geophys. 2016, 37, 307–337. https://doi.org/10.1007/s10712-015-9346-y.
- 5.
Bjerklie, D.M.; Moller, D.; Smith, L.C.; et al. Estimating discharge in rivers using remotely sensed hydraulic information. J. Hydrol. 2005, 309, 191–209. https://doi.org/10.1016/j.jhydrol.2004.11.022.
- 6.
Ke, L.; Xu, J.; Fan, C.; et al. Remote sensing reconstruction of long-term water level and storage variations of a poorly-gauged river in the Tibetan Plateau. J. Hydrol. Reg. Stud. 2022, 40, 101020. https://doi.org/10.1016/j.ejrh.2022.101020.
- 7.
Scherer, D.; Schwatke, C.; Dettmering, D.; et al. Monitoring river discharge from space: An optimization approach with uncertainty quantification for small ungauged rivers. Remote Sens. Environ. 2024, 315, 114434. https://doi.org/10.1016/j.rse.2024.114434.
- 8.
Alsdorf, D.E.; Rodríguez, E.; Lettenmaier, D.P. Measuring surface water from space. Rev. Geophys. 2007, 45, 2006RG000197. https://doi.org/10.1029/2006RG000197.
- 9.
Tang, Q.; Gao, H.; Lu, H.; et al. Remote sensing: Hydrology. Prog. Phys. Geogr. Earth Environ. 2009, 33, 490–509. https://doi.org/10.1177/0309133309346650.
- 10.
Ahmad, W.; Kim, D. Estimation of flow in various sizes of streams using the Sentinel-1 Synthetic Aperture Radar (SAR) data in Han River Basin, Korea. Int. J. Appl. Earth Obs. Geoinf. 2019, 83, 101930. https://doi.org/10.1016/j.jag.2019.101930.
- 11.
Mengen, D.; Ottinger, M.; Leinenkugel, P.; et al. Modeling River Discharge Using Automated River Width Measurements Derived from Sentinel-1 Time Series. Remote Sens. 2020, 12, 3236. https://doi.org/10.3390/rs12193236.
- 12.
McCabe, M.F.; Rodell, M.; Alsdorf, D.E.; et al. The future of Earth observation in hydrology. Hydrol. Earth Syst. Sci. 2017, 21, 3879–3914. https://doi.org/10.5194/hess-21-3879-2017.
- 13.
Bjerklie, D.M.; Lawrence Dingman, S.; Vorosmarty, C.J.; et al. Evaluating the potential for measuring river discharge from space. J. Hydrol. 2003, 278, 17–38. https://doi.org/10.1016/S0022-1694(03)00129-X.
- 14.
Altenau, E.H.; Pavelsky, T.M.; Durand, M.T.; et al. The Surface Water and Ocean Topography (SWOT) Mission River Database (SWORD): A Global River Network for Satellite Data Products. Water Resour. Res. 2021, 57, e2021WR030054. https://doi.org/10.1029/2021WR030054.
- 15.
Andreadis, K.M.; Coss, S.P.; Durand, M.; et al. A first look at river discharge estimation from SWOT satellite observations. Geophys. Res. Lett. 2025, 52, e2024GL114185.
- 16.
Eggleston, J.; Mason, C.; Bjerklie, D.; et al. Siting Considerations for Satellite Observation of River Discharge. Water Resour. Res. 2024, 60, e2023WR034583. https://doi.org/10.1029/2023WR034583.
- 17.
Gleason, C.J.; Smith, L.C. Toward global mapping of river discharge using satellite images and at-many-stations hydraulic geometry. Proc. Natl. Acad. Sci. USA 2014, 111, 4788–4791. https://doi.org/10.1073/pnas.1317606111.
- 18.
Hagemann, M.W.; Gleason, C.J.; Durand, M.T. BAM: Bayesian AMHG-Manning Inference of Discharge Using Remotely Sensed Stream Width, Slope, and Height. Water Resour. Res. 2017, 53, 9692–9707. https://doi.org/10.1002/2017WR021626.
- 19.
Durand, A.; Baron, Y.; Redjem, W.; et al. Broad Diversity of Near-Infrared Single-Photon Emitters in Silicon. Phys. Rev. Lett. 2021, 126, 083602. https://doi.org/10.1103/PhysRevLett.126.083602.
- 20.
Gleason, C.J.; Durand, M.T. Remote Sensing of River Discharge: A Review and a Framing for the Discipline. Remote Sens. 2020, 12, 1107. https://doi.org/10.3390/rs12071107.
- 21.
Kim, D.; Yu, H.; Lee, H.; et al. Ensemble learning regression for estimating river discharges using satellite altimetry data: Central Congo River as a Test-bed. Remote Sens. Environ. 2019, 221, 741–755. https://doi.org/10.1016/j.rse.2018.12.010.
- 22.
Shen, C. A transdisciplinary review of deep learning research and its relevance for water resources scientists. Water Resour. Res. 2018, 54, 8558–8593. https://doi.org/10.1029/2018WR022643.
- 23.
Kratzert, F.; Klotz, D.; Herrnegger, M.; et al. Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning. Water Resour. Res. 2019, 55, 11344–11354. https://doi.org/10.1029/2019WR026065.
- 24.
Mosavi, A.; Ozturk, P.; Chau, K.-W. Flood prediction using machine learning models: Literature review. Water 2018, 10, 1536. https://doi.org/10.3390/w10111536.
- 25.
Reichstein, M.; Camps-Valls, G.; Stevens, B.; et al. Deep learning and process understanding for data-driven Earth system science. Nature 2019, 566, 195–204. https://doi.org/10.1038/s41586-019-0912-1.
- 26.
Braca, G. Stage-Discharge Relationships in Open Channels: Practices and Problems; Dipartimento di Ingegneria Civile e Ambientale, Università di Trento: Trento, Italy, 2008.
- 27.
Chen, Z.; Jiang, F.; Cheng, Y.; et al. XGBoost Classifier for DDoS Attack Detection and Analysis in SDN-Based Cloud. In Proceedings of the 2018 IEEE International Conference on Big Data and Smart Computing (BigComp), Shanghai, China, 15–17 January 2018; pp. 251–256.
- 28.
Cheng, M.; Fang, F.; Kinouchi, T.; et al. Long lead-time daily and monthly streamflow forecasting using machine learning methods. J. Hydrol. 2020, 590, 125376. https://doi.org/10.1016/j.jhydrol.2020.125376.
- 29.
Fang, W.; Ren, K.; Liu, T.; et al. An evaluation of random forest based input variable selection methods for one month ahead streamflow forecasting. Sci. Rep. 2024, 14, 29766. https://doi.org/10.1038/s41598-024-81502-y.
- 30.
Kratzert, F.; Klotz, D.; Brenner, C.; et al. Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol. Earth Syst. Sci. 2018, 22, 6005–6022. https://doi.org/10.5194/hess-22-6005-2018.
- 31.
Nearing, G.S.; Kratzert, F.; Sampson, A.K.; et al. What Role Does Hydrological Science Play in the Age of Machine Learning? Water Resour. Res. 2021, 57, e2020WR028091. https://doi.org/10.1029/2020WR028091.
- 32.
Du, B.; Jin, T.; Liu, D.; et al. Accurate Discharge Estimation Based on River Widths of SWOT and Constrained At-Many-Stations Hydraulic Geometry. Remote Sens. 2023, 15, 1672. https://doi.org/10.3390/rs15061672.
- 33.
Yoon, Y.; Durand, M.; Merry, C.J.; et al. Estimating river bathymetry from data assimilation of synthetic SWOT measurements. J. Hydrol. 2012, 464–465, 363–375. https://doi.org/10.1016/j.jhydrol.2012.07.028.
- 34.
Frasson, R.P.D.M.; Durand, M.T.; Larnier, K.; et al. Exploring the Factors Controlling the Error Characteristics of the Surface Water and Ocean Topography Mission Discharge Estimates. Water Resour. Res. 2021, 57, e2020WR028519. https://doi.org/10.1029/2020WR028519.
- 35.
Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed.; Springer: New York, NY, USA, 2009.
- 36.
Durand, M.; Neal, J.; Rodríguez, E.; et al. Estimating reach-averaged discharge for the River Severn from measurements of river water surface elevation and slope. J. Hydrol. 2014, 511, 92–104. https://doi.org/10.1016/j.jhydrol.2013.12.050.
- 37.
Tarpanelli, A.; Mondini, A.C.; Camici, S. Effectiveness of Sentinel-1 and Sentinel-2 for flood detection assessment in Europe. Nat. Hazards Earth Syst. Sci. 2022, 22, 2473–2489. https://doi.org/10.5194/nhess-22-2473-2022.
- 38.
Solomatine, D.P.; Ostfeld, A. Data-driven modelling: Some past experiences and new approaches. J. Hydroinformatics 2008, 10, 3–22. https://doi.org/10.2166/hydro.2008.015.
- 39.
McMillan, H.K.; Westerberg, I.K.; Krueger, T. Hydrological data uncertainty and its implications. Wiley Interdiscip. Rev. Water 2018, 5, e1319. https://doi.org/10.1002/wat2.1319.
- 40.
Bargam, B.; Boudhar, A.; Kinnard, C.; et al. Evaluation of the support vector regression (SVR) and the random forest (RF) models accuracy for streamflow prediction under a data-scarce basin in Morocco. Discov. Appl. Sci. 2024, 6, 306. https://doi.org/10.1007/s42452-024-05994-z.
- 41.
He, M.; Xu, X.; Wu, S.; et al. Multi-step ahead forecasting of daily streamflow based on the transform-based deep learning model under different scenarios. Sci. Rep. 2025, 15, 5451. https://doi.org/10.1038/s41598-025-89837-w.
- 42.
Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. https://doi.org/10.1023/A:1010933404324.
- 43.
Moriasi, D.N.; Arnold, J.G.; Van Liew, M.W.; et al. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans. ASABE 2007, 50, 885–900. https://doi.org/10.13031/2013.23153.
- 44.
Nash, J.E.; Sutcliffe, J.V. River flow forecasting through conceptual models part I—A discussion of principles. J. Hydrol. 1970, 10, 282–290. https://doi.org/10.1016/0022-1694(70)90255-6.
- 45.
Willmott, C.J.; Matsuura, K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE). Clim. Res. 2005, 30, 79–82. https://doi.org/10.3354/cr030079.
- 46.
Karpatne, A.; Atluri, G.; Faghmous, J.H.; et al. Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data. IEEE Trans. Knowl. Data Eng. 2017, 29, 2318–2331. https://doi.org/10.1109/TKDE.2017.2720168.
- 47.
Durand, M.; Gleason, C.J.; Garambois, P.A.; et al. An intercomparison of remote sensing river discharge estimation algorithms from measurements of river height, width, and slope. Water Resour. Res. 2016, 52, 4527–4549. https://doi.org/10.1002/2015WR018434.
- 48.
Pavelsky, T.M.; Durand, M.T.; Andreadis, K.M.; et al. Assessing the potential global extent of SWOT river discharge observations. J. Hydrol. 2014, 519, 1516–1525. https://doi.org/10.1016/j.jhydrol.2014.08.044.
- 49.
NASA Jet Propulsion Laboratory. Surface Water and Ocean Topography (SWOT) science requirements document (JPL D-61923, Rev. B); California Institute of Technology: Pasadena, CA, USA, 2018.
- 50.
Shapley, L.S. A Value for n-Person Games. In Contributions to the Theory of Games II; Kuhn, H.W., Tucker, A.W., Eds.; Princeton University Press: Princeton, NJ, USA, 1953; pp. 307–317.
- 51.
Lundberg, S.M.; Lee, S.-I. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30; Guyon, I., Von Luxburg, U., Bengio, S., et al., Eds.; NIPS: La Jolla, CA, USA, 2017; pp. 4765–4774.
- 52.
Durand, M.; Andreadis, K.M.; Alsdorf, D.E.; et al. Estimation of bathymetric depth and slope from data assimilation of swath altimetry into a hydrodynamic model. Geophys. Res. Lett. 2008, 35, 2008GL034150. https://doi.org/10.1029/2008GL034150.
- 53.
Box, G.E.P.; Jenkins, G.M.; Reinsel, G.C.; et al. Time Series Analysis: Forecasting and Control, 5th ed.; Wiley: Hoboken, NJ, USA, 2015.
- 54.
Kratzert, F.; Klotz, D.; Shalev, G.; et al. Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets. Hydrol. Earth Syst. Sci. 2019, 23, 5089–5110. https://doi.org/10.5194/hess-23-5089-2019.
- 55.
Fu, L.; Pavelsky, T.; Cretaux, J.; et al. The Surface Water and Ocean Topography Mission: A Breakthrough in Radar Remote Sensing of the Ocean and Land Surface Water. Geophys. Res. Lett. 2024, 51, e2023GL107652. https://doi.org/10.1029/2023GL107652.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com