Enhancing the prediction of the streamflow for SWAT models


  • Venkatesh B Vellore Institute of Technology, Vellore
  • Amit Mahindrakar Baburao Vellore Institute of Technology, Vellore






SWAT, Metamodels, Optimization, Calibration and RBFNN.


The prediction of streamflow helps to identify the disasters and sources of water resources. Different ways to predict the streamflow, among the conceptual models have been gained more popularity due to explanation of processes and visualization in water resources systems. Any model may not obtain the acceptable performance at initial setup and it has to go through calibration or optimization (either manual or auto-calibration). Moreover, the calibration procedure is more concern of computational time for complex conceptual models like Soil and Water Assessment Tool (SWAT).  Where, meta models are the alternative approach to restrict the computationally intensive optimization problems because it is cheaper models to enhance the performance and shows the relationship between input-output response. Our results showed that 1) meta models mimics the original simulation models with effective and efficient outputs and 2) it verified and satisfied the performance of SWAT model with less computational time.  This study helps to planning and designing of hydrological models with effective computational time.


[1] I. Pechlivanidis, B. Jackson, and N. Mcintyre, “Catchment scale hydrological modelling : A review of model types , calibration approaches and uncertainty analysis ...,†Glob. NEST J., vol. 13, no. September, pp. 193–214, 2011.

[2] M. Wegehenkel, “Estimating of the impact of land use changes using the conceptual hydrological model THESEUS –– a case study,†Phys. Chem. Earth, vol. 27, pp. 631–640, 2002.

[3] H. Sellami, S. Benabdallah, I. La Jeunesse, and M. Vanclooster, “Climate models and hydrological parameter uncertainties in climate change impacts on monthly runoff and daily flow duration curve of a Mediterranean catchment,†Hydrol. Sci. J., no. July, pp. 1415–1429, 2016.

[4] A. W. Alansi, M. S. M. Amin, A. . Halim, H. Z. . Shafri, and W. Aimrun, “Validation of SWAT model for stream flow simulation and forecasting in Upper Bernam humid tropical river basin , Malaysia,†Hydrol. Earth Syst. Sci., vol. 6, pp. 7581–7609, 2009.

[5] W. Al Sabhan, M. Mulligan, and G. A. Blackburn, “A real-time hydrological model for flood prediction using GIS and the WWW,†Comput. Environ. Urban Syst., vol. 27, pp. 9–32, 2003.

[6] J. Yang, P. Reichert, K. C. Abbaspour, J. Xia, and H. Yang, “Comparing uncertainty analysis techniques for a SWAT application to the Chaohe Basin in China,†pp. 1–23, 2008.

[7] H. Yen, A. Sharifi, L. Kalin, G. Mirhosseini, and J. G. Arnold, “Assessment of model predictions and parameter transferability by alternative land use data on watershed modeling,†J. Hydrol., vol. 527, pp. 458–470, 2015.

[8] Q. Wu, S. Liu, Y. Cai, X. Li, and Y. Jiang, “Improvement of hydrological model calibration by selecting multiple parameter ranges,†Hydrol. Earth Syst. Sci., vol. 21, pp. 393–407, 2017.

[9] Y. Wu and S. Liu, “Automating calibration , sensitivity and uncertainty analysis of complex models using the R package Flexible Modeling Environment ( FME ): SWAT as an example,†Environ. Model. Softw., vol. 31, pp. 99–109, 2012.

[10] H. Yen, Y. Su, J. E. Wolfe, S. Chen, Y. Hsu, W. Tseng, D. M. Brady, J. Jeong, and J. G. Arnold, “Assessment of input uncertainty by seasonally categorized latent variables using SWAT,†J. Hydrol., vol. 531, pp. 685–695, 2015.

[11] K. P. Sudheer, G. Lakshmi, and I. Chaubey, “Application of a pseudo simulator to evaluate the sensitivity of parameters in complex watershed models,†Environ. Earth Sci., vol. 26, pp. 135–143, 2011.

[12] Y. T. Dile, P. Daggupati, C. George, R. Srinivasan, and J. Arnold, “Introducing a new open source GIS user interface for the SWAT model,†Environ. Model. Softw., vol. 85, pp. 129–138, 2016.

[13] P. W. Gassman, M. R. Reyes, C. H. Green, and J. G. Arnold, “The soil and water assessment tool: historical development, applications, and future research directions,†Am. Soc. Agric. Biol. Eng., vol. 50, no. 4, pp. 1211–1250, 2007.

[14] M. Rezaeianzadeh, A. Stein, H. Tabari, H. Abghari, N. Jalalkamali, E. Z. Hosseinipour, and V. P. Singh, “Assessment of a conceptual hydrological model and artificial neural networks for daily outflows forecasting,†Int. J. Environ. Sci. Technol., vol. 10, pp. 1181–1192, 2013.

[15] A. I. J. Forrester and A. J. Keane, “Recent advances in surrogate-based optimization,†Prog. Aerosp. Sci., vol. 45, pp. 50–79, 2009.

[16] X. Zhang, R. Srinivasan, and M. Van Liew, “APPROXIMATING SWAT MODEL USING ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE,†J. Am. Water Resour. Assoc., vol. 45, no. 2, pp. 460–474, 2009.

[17] C. Wang, Q. Duan, W. Gong, A. Ye, Z. Di, and C. Miao, “An evaluation of adaptive surrogate modeling based optimization with two benchmark problems,†Environ. Model. Softw., vol. 60, pp. 167–179, 2014.

[18] S. Razavi, B. A. Tolson, and D. H. Burn, “Review of surrogate modeling in water resources,†Water Resour. Res., vol. 48, pp. 1–32, 2012.

[19] K. Lindhorst, M. C. Haupt, P. Horst, T. U. Braunschweig, and D.- Braunschweig, “Efficient Surrogate Modelling of Nonlinear Aerodynamics in Aerostructural Coupling Schemes,†AIAA J., vol. 52, no. 9, 2014.

[20] I. Pan, M. Babaei, A. Korre, and S. Durucan, “Artificial Neural Network based surrogate modelling for multi- objective optimisation of geological CO 2 storage operations,†Energy Procedia, vol. 63, pp. 3483–3491, 2014.

[21] J. Kusiak, Å. Sztangret, and M. Pietrzyk, “Advances in Engineering Software Effective strategies of metamodelling of industrial metallurgical processes,†Adv. Eng. Softw., vol. 89, pp. 90–97, 2015.

[22] M. Alla, M. Hinze, O. Hinze, and O. Lass, “Model order reduction approaches for the optimal design of permanent magnets in optimal desig,†IFAC-PapersOnLine, vol. 48, no. 1, pp. 242–247, 2015.

[23] F. Passos, E. Roca, and F. V Fernández, “Radio-frequency inductor synthesis using evolutionary computation and Gaussian-process surrogate modeling,†Appl. Soft Comput. J., vol. 60, pp. 495–507, 2017.

[24] F. Lamperti, A. Roventini, and A. Sani, “lamperti2018.pdf,†Agent_based Model calibration using Mach. Learn. Surrog., vol. 90, pp. 366–389, 2018.

[25] H. R. Maier, A. Jain, G. C. Dandy, and K. P. Sudheer, “Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions,†Environ. Model. Softw., vol. 25, no. 8, pp. 891–909, 2010.

[26] J. G. Arnold, J. R. Kiniry, R. Srinivasan, J. R. Williams, E. B. Haney, and S. L. Neitsch, Soil & Water Assessment Tool Input/ Output Documentation Version 2012. 2012.

[27] S. L. Neitsch, J. G. Arnold, J. R. Kiniry, and J. R. Williams, Soil & Water Assessment Tool Theoretical Documentation Version 2009. 2009.

[28] B. Tang, “Orthogonal Array-Based Latin Hypercubes Orthogonal Array-Based Latin Hypercubes,†J. Am. Stat. Assoc., pp. 1392–1397, 1993.

[29] G. H. Roshani, E. Nazemi, and M. M. Roshani, “Intelligent recognition of gas-oil-water three-phase flow regime and determination of volume fraction using radial basis function,†Flow Meas. Instrum., vol. 54, no. June 2016, pp. 39–45, 2017.

[30] J. E. Nash and J. V Sutcliffe, “River flow forecasting through conceptual models part-1 - a discussion of principles,†J. Hydrol., vol. 10, pp. 282–290, 1970.

[31] D. N. Moriasi, J. G. Arnold, M. W. Van Liew, R. L. Bingner, R. D. Harmel, and T. L. Veith, “Model Evaluation Guidelines For Sytematic Quantification Of Accuracy In Watershed Simulations,†Am. Soc. Agric. Biol. Eng., vol. 50, no. 3, pp. 885–900, 2007.

View Full Article: