Abstract
In the last decades, data-driven (DD) machine-learning models have been rapidly developed and widely applied to solve hydrologic problems. To explore DD approaches’ capability in rainfall-runoff modeling compared to knowledge-driven models, we conducted a thorough comparison between Soil & Water Assessment Tool (SWAT) and Random Forest (RF) models. They were implemented to simulate the daily surface runoff at Santa Lucía Chico watershed in Uruguay. Aiming at making a fair comparison, the same input time series for RF and SWAT models were considered. Both approaches are able to represent the daily surface runoff adequately. The RF model shows a higher accuracy for calibration/training, while the SWAT model yields better results for validation/testing, indicating that the latter has a better generalization capacity. Furthermore, RF outperforms SWAT in terms of computational time needed for a proper calibration/training. Strategies to improve RF performance and interpretability should include feature selection, feature engineering and a more sophisticated sensitivity analysis technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Pappenberger, F., et al.: Cascading model uncertainty from medium range weather forecasts (10 days) through a rainfall-runoff model to flood inundation predictions within the European Flood Forecasting System (EFFS). Hydrol. Earth Syst. Sci. 9(4), 381–393 (2005)
Young, C.C., Liu, W.-C., Wu, M.-C.: A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events. Appl. Soft Comput. 53, 205–216 (2017)
Narbondo, S., Gorgoglione, A., Crisci, M., Chreties, C.: Enhancing physical similarity approach to predict runoff in ungauged watersheds in sub-tropical regions. Water 12, 528 (2020)
Gorgoglione, A., Crisci, M., Kayser, R.H., Chreties, C., Collischonn, W.: A new scenario-based framework for conflict resolution in water allocation in transboundary watersheds. Water 11, 1174 (2019)
Chang, W., Chen, X.: Monthly rainfall-runoff modeling at watershed scale: a comparative study of data-driven and theory-driven approaches. Water 10, 1116 (2018)
Wang, W., Ding, J.: Wavelet network model and its application to the prediction of hydrology. Nat. Sci. 1(1), 67–71 (2003)
Solomatine, D., Ostfeld, A.: Data-driven modelling: some past experiences and new approaches. J. Hydroinform. 10(1), 3–22 (2008). https://doi.org/10.2166/hydro.2008.015
Wu, C.L., Chau, K.L.: Rainfall-runoff modelling using artificial neural network coupled with singular spectrum analysis. J. Hydrol. 399(3–4), 394–409 (2003)
Apostel, A., et al.: Simulating internal watershed processes using multiple SWAT models. Sci. Total Environ. 759, 143920 (2021). https://doi.org/10.1016/j.scitotenv.2020.143920
Chen, H., Luo, Y., Potter, C., Moran, P.J., Grieneisen, M., Zhang, M.: Modeling pesticide diuron loading from the San Joaquin watershed into the Sacramento-San Joaquin Delta using SWAT. Water Res. 121, 374–385 (2017)
Pang, S., Wang, X., Melching, C., Feger, Karl-Heinz.: Development and testing of a modified SWAT model based on slope condition and precipitation intensity. J. Hydrol. 588, 125098 (2020). https://doi.org/10.1016/j.jhydrol.2020.125098
Zhu, X., Wang, X., Zeng, S., Zhou, W.: Simulation of runoff and sediment yield in Zhuxi watershed in Changting county of China based on SWAT model. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, Texas (2017)
Hallouz, F., Meddi, M., Mahé, G., Alirahmani, S., Keddar, A.: Modeling of discharge and sediment transport through the SWAT model in the basin of Harazza (Northwest of Algeria). Water Sci. 32(1), 79–88 (2018)
Cheng, J., et al.: Modeling the sources and retention of phosphorus nutrient in a coastal river system in China using SWAT. J. Environ. Manag. 278, 111556 (2021). https://doi.org/10.1016/j.jenvman.2020.111556
Busico, G., Colombani, N., Fronzi, D., Pellegrini, M., Tazioli, A., Mastrocicco, M.: Evaluating SWAT model performance, considering different soils data input, to quantify actual and future runoff susceptibility in a highly urbanized basin. J. Environ. Manag. 266, 110625 (2020). https://doi.org/10.1016/j.jenvman.2020.110625
Marin, M., et al.: Assessing the vulnerability of water resources in the context of climate changes in a small forested watershed using SWAT: a review. Environ. Res. 184, 109330 (2020). https://doi.org/10.1016/j.envres.2020.109330
Zhang, H., Wang, B., Liu, De Li., Zhang, M., Leslie, L., Qiang, Y.: Using an improved SWAT model to simulate hydrological responses to land use change: a case study of a catchment in tropical Australia. J. Hydrol. 585, 124822 (2020). https://doi.org/10.1016/j.jhydrol.2020.124822
Rezaeianzadeh, M., et al.: Assessment of a conceptual hydrological model and artificial neural networks for daily outflows forecasting. Int. J. Environ. Sci. Technol. 10(6), 1181–1192 (2013). https://doi.org/10.1007/s13762-013-0209-0
Ahmadi, M., Moeini, A., Ahmadi, H., Motamedvaziri, B., Zehtabijan, G.R.: Comparison of the performance of SWAT, IHACRES and artificial neural networks models in rainfall-runoff simulation (case study: Kan watershed, Iran). Phys. Chem. Earth A/B/C 111, 65–77 (2019)
Li, M., Zhang, Y., Wallace, J., Campbell, E.: Estimating annual runoff in response to forest change: a statistical method based on random forest. J. Hydrol. 589, 125168 (2020). https://doi.org/10.1016/j.jhydrol.2020.125168
Desai, S., Ouarda, T.: Regional hydrological frequency analysis at ungauged sites with random forest regression. J. Hydrol. 594, 125861 (2021). https://doi.org/10.1016/j.jhydrol.2020.125861
Muñoz, P., Orellana-Alvear, J., Willems, P., Célleri, R.: Flash-flood forecasting in an Andean Mountain catchment—development of a step-wise methodology based on the random forest algorithm. Water 10(11), 1519 (2018). https://doi.org/10.3390/w10111519
Pini, M., Scalvini, A., Liaqat, M.U., Ranzi, R., Serina, I., Mehmood, T.: Evaluation of machine learning techniques for inflow prediction in Lake Como, Italy. Procedia Comput. Sci. 176, 918–927 (2020)
Schoppa, L., Disse, M., Bachmair, S.: Evaluating the performance of random forest for large-scale flood discharge simulation. J. Hydrol. 590, 125531 (2020). https://doi.org/10.1016/j.jhydrol.2020.125531
Abbasi, M., Farokhnia, A., Bahreinimotlagh, M., Roozbahani, R.: A hybrid of random forest and deep auto-encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction. J. Hydrol. (2020). https://doi.org/10.1016/j.jhydrol.2020.125717
Adnan, R.M., Petroselli, A., Heddam, S., Guimaräes, C.A., Kisi, O.: Comparison of different methodologies for rainfall-runoff modelling: machine learning vs conceptual approach. Nat. Hazards 105, 2987–3011 (2021)
Gorgoglione, A., Gregorio, J., Ríos, A., Alonso, J., Chreties, C., Fossati, M.: Influence of land use/land cover on surface-water quality of Santa Lucía River, Uruguay. Sustainability 12(11), 4692 (2020)
MGAP: Uruguayan Integrated Land Use/Land Cover Map. Available online: https://www.gub.uy/ministerio-ganaderia-agricultura-pesca/comunicacion/publicaciones/mapa-integrado-coberturauso-del-suelo-del-uruguay-ano-2018 (2018). Accessed 22 March 2021
MGAP: Soil classification with CONEAT productivity index for Uruguayan soils. Available: https://www.gub.uy/ministerio-ganaderia-agricultura-pesca/tramites-y-servicios/servicios/consulta-coneat. Accessed 24 March 2021
MGAP: Digital terrain map of Uruguay. Available: https://www.gub.uy/ministerio-ganaderia-agricultura-pesca/tramites-y-servicios/servicios/modelo-digital-terreno. Accessed 24 March 2021
Abbaspour, K., et al.: Modelling hydrology and water quality in the pre-alpine/alpine Thur watershed using SWAT. J. Hydrol. 333(2–4), 413–430 (2007). https://doi.org/10.1016/j.jhydrol.2006.09.014
Brieman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(85), 2825–2830 (2011)
Abbaspour, K., Vaghefi, S., Srinivasan, R.: A guideline for successful calibration and uncertainty analysis for soil and water assessment: a review of papers from the 2016 International SWAT Conference. Water 10(1), 6 (2017). https://doi.org/10.3390/w10010006
Mer, F., et al.: SWAT Subcuenca Santa Lucia. https://doi.org/10.17605/OSF.IO/UQB5J (2020, October 11)
Abbaspour, K.C., Johnson, C.A., van Genuchten, M.: Estimating uncertain flow and transport parameters using a sequential uncertainty fitting procedure. Vadose Zone J. 3(4), 1340–1352 (2004). https://doi.org/10.2136/vzj2004.1340
Abbaspour, K.C., Rouholahnejad, E., Vaghefi, S., Srinivasan, R., Yang, H., Kløve, B.: A continental-scale hydrology and water quality model for Europe: calibration and uncertainty of a high-resolution large-scale SWAT model. J. Hydrol. 524, 733–752 (2015). https://doi.org/10.1016/j.jhydrol.2015.03.027
Moriasi, D.N., Arnold, J.G., Van Liew, M.W., Bingner, R.L., Harmel, R.D., Veith, T.L.: Model evaluation guidelines for systematic quantification and accuracy in watershed simulations. Trans. ASABE 50(3), 885–900 (2007)
Lundberg, S.M., Lee, S.: A unified approach to interpreting model predictions. In: 31st Conference on Neural Information Processing Systems (NIPS), Long Beach, California, USA. arXiv:1705.07874 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Vilaseca, F., Castro, A., Chreties, C., Gorgoglione, A. (2021). Daily Rainfall-Runoff Modeling at Watershed Scale: A Comparison Between Physically-Based and Data-Driven Models. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science(), vol 12955. Springer, Cham. https://doi.org/10.1007/978-3-030-87007-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-87007-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87006-5
Online ISBN: 978-3-030-87007-2
eBook Packages: Computer ScienceComputer Science (R0)