Abstract
Water resources planning, development, and management need reliable forecasts of river flows. In past few decades, an important dimension has been introduced in the prediction of the hydrologic phenomenon through artificial intelligence-based modeling. In this paper, the performance of three artificial neural network (ANN) and four support vector regression (SVR) models was investigated to predict streamflows in the Upper Indus River. Results from ANN models using three different optimization techniques, namely Broyden-Fletcher-Goldfarb-Shannon, Conjugate Gradient, and Back Propagation algorithms, were compared with one another. A further comparison was made between these ANNs and four types of SVR models which were based on linear, polynomial, radial basis function, and sigmoid kernels. Past 30 years’ monthly data for precipitation, temperature, and streamflow obtained from Pakistan Surface Water Hydrology Department Lahore were used for this purpose. Three types of input combinations with respect to the main input variables (temperature, precipitation, and stream flow) and several types of input combinations with respect to time lag were tested. The best input for ANN and SVR models was identified using correlation coefficient analysis and genetic algorithm. The performance of the ANN and SVR models was evaluated by mean bias error, Nash–Sutcliffe efficiency, root mean square error, and correlation coefficient. The efficiency of the Broyden-Fletcher-Goldfarb-Shannon-ANN model was found to be much better than that of other models, while the SVR model based on radial basis function kernel predicted stream flows with comparatively higher accuracy than the other kernels. Finally, long-term predictions of streamflow have been made by the best ANN model. It was found that stream flow of Upper Indus River has a decreasing trend.
Similar content being viewed by others
References
Aalinejad, M. H., Dinpashoh, Y., & Jahanbakhsh, A. S. L. (2016). Impact of climate change on runoff from snowmelt by taking into account the uncertainty of GCM models (case study: Shahrchay Basin in Urmia). European Online Journal of Natural and Social Sciences, 5(1), 200.
Adnan, R. M., Yuan, X., Kisi, O., & Anam, R. (2017a). Improving accuracy of river flow forecasting using LSSVR with gravitational search algorithm. Advances in Meteorology, 3, 1–23.
Adnan, R. M., Yuan, X., Kisi, O., & Yuan, Y. (2017b). Streamflow forecasting using artificial neural network and support vector machine models. American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), 29(1), 286–294.
Aichouri, I., Hani, A., Bougherira, N., Djabri, L., Chaffai, H., & Lallahem, S. (2015). River flow model using artificial neural networks. Energy Procedia, 74, 1007–1014.
Alfarisy, G. A. F., & Mahmudy, W. F. (2016). Rainfall forecasting in Banyuwangi using adaptive neuro fuzzy inference system. Journal of Information Technology and Computer Science, 1, 65–71.
Ali, Z., Hussain, I., Faisal, M., Nazir, M. H., Hussain, T., Shad, M. Y., Shoukry, M. A., & Gani, S. H. (2017). Forecasting drought using multilayer perceptron artificial neural network model. Advances in Meteorology, 2017, 1–9. https://doi.org/10.1155/2017/5681308.
AlOtabi, K., Ghumman, A. R., Haider, H., Ghazaw, Y., & Shafiquzzan, M. D. (2018). Future predictions of rainfall and temperature using GCM and ANN for arid regions: a case study for the Qassim region. Saudi Arabia, Water, 10, 1–25.
Arena, P., Caponetto, R., Fortuna, L., & Xibilia, M. G. (1992). Genetic algorithms to select optimal neural network topology. In Circuits and Systems, 1992, Proceedings of the 35th Midwest Symposium on (pp. 1381–1383). IEEE.
Aziz, K., Haque, M. M., Rahman, A., Shamseldin, A. Y., & Shoaib, M. (2017). Flood estimation in ungauged catchments: application of artificial intelligence based methods for Eastern Australia. Stochastic Environmental Research and Risk Assessment, 31(6), 1499–1514.
Beale E. M. L. (1972). A derivation of conjugate gradients. In: F. A. Lootsma (Ed.), Numerical methods for non-linear optimization pp. 39–43. London: Academic Press.
Blanco, A., Delgado, M., & Pegalajar, M. C. (2000). A genetic algorithm to obtain the optimal recurrent neural network. International Journal of Approximate Reasoning, 23(1), 67–83.
Bray, M., & Han, D. (2004). Identification of support vector machines for runoff modelling. Journal of Hydroinformatics, 6(4), 265–280.
Burnham, K. P. (2002). Information and likelihood theory: a basis for model selection and inference. In Model selection and multi model inference: a practical information-theoretic approach (2nd ed., pp. 49–97). New York Berlin Heidelberg Barcelona Hong Kong London Milan Paris Singapore Tokyo: Springer.
Byrd, R. H., Hansen, S. L., Nocedal, J., & Singer, Y. (2016). A stochastic quasi-Newton method for large-scale optimization. SIAM Journal on Optimization, 26(2), 1008–1031.
Chang, C. C., & Lin, C. J. (2011). LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3), 27.
Dhamge, N. R., Atmapoojya, S. L., & Kadu, M. S. (2012). Genetic algorithm driven ANN model for runoff estimation. Procedia Technology, 6, 501–508.
Evans, D., & Jones, A. J. (2002). A proof of the Gamma test. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, 458(2027), 2759–2799 The Royal Society.
Fletcher R. (1987). Practical methods of optimization, 2nd ed. New York: Wiley.
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(1), 2096–2030.
Ghorbani, M. A., Zadeh, H. A., Isazadeh, M., & Terzi, O. (2016). A comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction. Environmental Earth Sciences, 75(6), 476.
Ghumman, A. R., Al-Salamah, I. S., AlSaleem, S. S., & Haider, H. (2017). Evaluating the impact of lower resolutions of digital elevation model on rainfall-runoff modeling for ungauged catchments. Environmental Monitoring and Assessment, 189(2), 54.
Goyal, M. K., Bharti, B., Quilty, J., Adamowski, J., & Pandey, A. (2014). Modelling of daily pan evaporation in sub- tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS. Expert Systems with Applications, 41(11), 5267–5276.
Humphrey, G. B., Gibbs, M. S., Dandy, G. C., & Maier, H. R. (2016). A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network. Journal of Hydrology, 540, 623–640.
Imen, A., Azzedine, H., Nabil, B., Larbi, D., Hicham C., & Sami, L. (2015). River flow model using artificial neural networks. Energy Procedia, 74, 1007–1014.
Jajarmizadeh, M., Lafdani, E. K., Harun, S., & Ahmadi, A. (2015). Application of SVM and SWAT models for monthly streamflow prediction, a case study in South of Iran. KSCE Journal of Civil Engineering, 19(1), 345–357.
Kawase, H., Murata, A., Mizuta, R., Sasaki, H., Nosaka, M., Ishii, M., & Takayabu, I. (2016). Enhancement of heavy daily snowfall in central Japan due to global warming as projected by large ensemble of regional climate simulations. Climatic Change, 139(2), 265–278.
Kecman, V. (2001). Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models (1st ed.). Cambridge, Massachusetts London, England: MIT Press ISBN: 9780262112550.
Kisi, O. (2015). Streamflow forecasting and estimation using least square support vector regression and adaptive neuro-fuzzy embedded fuzzy c-means clustering. Water Resources Management, 29(14), 5109–5127.
Kovačević, M., Ivanišević, N., Dašić, T., & Marković, L. (2018). Application of artificial neural networks for hydrological modelling in karst. Građevinar, 70(1), 1–10. https://doi.org/10.14256/JCE.1594.2016.
Krause, P., Boyle, D. P., & Bäse, F. (2005). Comparison of different efficiency criteria for hydrological model assessment. Advances in Geosciences, 5, 89–97.
Kyada, P. M., & Kumar, P. (2015). Daily rainfall forecasting using adaptive neurofuzzy inference system (ANFIS) models. International Journal of Science and Nature, 6, 382–388.
Lafdani, E. K., Nia, A. M., & Ahmadi, A. (2013). Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology, 478, 50–62.
Leong, W. J., Hassan, M. A., & Yusuf, M. W. (2011). A matrix-free quasi-Newton method for solving large-scale nonlinear systems. Computers & Mathematics with Applications, 62(5), 2354–2363.
Londhe, S. N., & Gavraskar, S. (2018). Stream flow forecasting using least square support vector regression. Journal of Soft Computing in Civil Engineering, 2, 56–88.
Lutz, A. F., Immerzeel, W. W., Kraaijenbrink, P. D. A., Shrestha, A. B., & Bierkens, M. F. (2016). Climate change impacts on the upper Indus hydrology: sources, shifts and extremes. PLoS One, 11(11), e0165630.
Martınez, J. M. (2000). Practical quasi-Newton methods for solving nonlinear systems. Journal of Computational and Applied Mathematics, 124(1–2), 97–121.
Mehr, A. D., & Kahya, E. (2017). A Pareto-optimal moving average multigene genetic programming model for daily streamflow prediction. Journal of Hydrology, 549, 603–615.
Mishra, N., Soni, H. K., Sharma, S., & Upadhyay, A. K. (2018). Development and analysis of artificial neural network models for rainfall prediction by using time-series data. International Journal of Intelligent Systems and Applications, 10(1), 16–23. https://doi.org/10.5815/ijisa.2018.01.03.
Molden, D. J., Shrestha, A. B., Nepal, S., & Immerzeel, W. W. (2016). Downstream implications of climate change in the Himalayas. In Water security, climate change and sustainable development (pp. 65–82). Singapore: Springer.
Oyerinde, G. T., Wisser, D., Hountondji, F. C., Odofin, A. J., Lawin, A. E., Afouda, A., & Diekkrüger, B. (2016). Quantifying uncertainties in modeling climate change impacts on hydropower production. Climate, 4(3), 34.
Pellakuri, V., & Rao, D. R. (2016). Training and development of artificial neural network models: single layer feedforward and multi-layer feedforward neural network. Journal of Theoretical and Applied Information Technology, 84(2), 150.
Rauf, A., & Ghumman, A. R. (2018). Impact assessment of rainfall-runoff simulations on the flow duration curve of the Upper Indus River—a comparison of data-driven and hydrologic models. Water, 10, 876. https://doi.org/10.3390/w10070876.
Rauf, A., et al. (2016). Data-driven modelling for real-time flood forecasting. 2nd International Multi-Disciplinary Conference, Gujrat, Pakistan, December 19–20, Vol. 2, no 90.
Schölkopf, B., & Smola, A. J. (2002). Learning with kernels: support vector machines, regularization, optimization, and beyond (1st ed.). Cambridge, Massachusetts London, England: MIT press ISBN: 9780262194754.
Seyam, M., Othman, F., & El-Shafie, A. (2017). Prediction of stream flow in humid tropical rivers by support vector machines. In MATEC Web of Conferences (vol. 111, p. 01007). EDP Sciences.
Shamim, M. A., Hassan, M., Ahmad, S., & Zeeshan, M. (2016). A comparison of artificial neural networks (ANN) and local linear regression (LLR) techniques for predicting monthly reservoir levels. KSCE Journal of Civil Engineering, 20(2), 971–977.
Slater, L. J., & Villarini, G. (2017). Evaluating the drivers of seasonal stream flow in the U.S. Midwest. Water, 9, 695. https://doi.org/10.3390/w9090695.
Smola, A. J. (1996). Regression estimation with support vector learning machines. Doctoral dissertation, Master’s thesis, Technische Universität München.
Sofaer, H. R., Skagen, S. K., Barsugli, J. J., Rashford, B. S., Reese, G. C., Hoeting, J. A., … & Noon, B. R. (2016). Projected wetland densities under climate change: habitat loss but little geographic shift in conservation strategy. Ecological Applications, 26(6), 1677–1692.
Tahir, A. A., Chevallier, P., Arnaud, Y., Ashraf, M., & Bhatti, M. T. (2015). Snow cover trend and hydrological characteristics of the Astore River basin (Western Himalayas) and its comparison to the Hunza basin (Karakoram region). Science of the Total Environment, 505, 748–761.
Tayyab, M., Zhou, J., Zeng, X., & Adnan, R. (2016). Discharge forecasting by applying artificial neural networks at The Jinsha River Basin, China. European Scientific Journal, ESJ, 12(9).
Veraart, J. A., van Duinen, R., & Vreke, J. (2017). Evaluation of socio-economic factors that determine adoption of climate compatible freshwater supply measures at farm level: a case study in the southwest Netherlands. Water Resources Management, 31(2), 587–608.
Wang, D., Luo, H., Grunder, O., Lin, Y., & Guo, H. (2017a). Multi-step ahead electricity price forecasting using a hybrid model based on two-layer decomposition technique and BP neural network optimized by firefly algorithm. Applied Energy, 190, 390–407.
Wang, J., Shi, P., Jiang, P., Hu, J., Qu, S., Chen, X., … & Xiao, Z. (2017b). Application of BP neural network algorithm in traditional hydrological model for flood forecasting. Water, 9(1), 48.
Woldemeskel, F. M., Sharma, A., Sivakumar, B., & Mehrotra, R. (2016). Quantification of precipitation and temperature uncertainties simulated by CMIP3 and CMIP5 models. Journal of Geophysical Research-Atmospheres, 121(1), 3–17.
Yaseen, Z. M., Ebtehaj, I., Bonakdari, H., Deo, R. C., Mehr, A. D., Mohtar, W. H. M. W., & Singh, V. P. (2017). Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model. Journal of Hydrology, 554, 263–276.
Yazdani, M. R., & Zolfaghari, A. A. (2017). Monthly River forecasting using instance-based learning methods and climatic parameters. Journal of Hydrologic Engineering, 22(6), 04017002.
Yousuf, I., Ghumman, A. R., & Hashmi, H. N. (2017). Optimally sizing small hydropower project under future projected flows. KSCE Journal of Civil Engineering, 21(5), 1964–1978.
Zaini, N., Malek, M. A., Yusoff, M., Mardi, N. H., & Norhisham, S. (2018). Daily River flow forecasting with hybrid support vector machine—particle swarm optimization. IOP Conference Series: Earth and Environmental Science, 140, 012035. https://doi.org/10.1088/1755-1315/140/1/012035.
Zhao, M., Golaz, J. C., Held, I. M., Ramaswamy, V., Lin, S. J., Ming, Y., & Guo, H. (2016). Uncertainty in model climate sensitivity traced to representations of cumulus precipitation microphysics. Journal of Climate, 29(2), 543–560.
Acknowledgments
The authors would like to thank Almighty Allah, the source of all knowledge and wisdom within and beyond our comprehension. We wish to express our sincere thanks to all the contributing authors and review editors. Without their expertise, commitment, integrity, and vast investments of time, a paper of this quality would never have been completed. We are much obliged to Dr. Asim Rauf, Director and Engr. Mian Waqar Ali Shah, a research associate at Pakistan Glacier Management and Research Centre, whose expertise and guidance were pivotal to carry out this study. We would also like to thank the staff of the Pakistan Surface Water Hydrology Department, especially Director Abdul Majid and Data keeper Mr. Tariq Khan for their assistance and providing the necessary data. We are deeply indebted to them.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claimsin published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ateeq-ur-Rauf, Ghumman, A.R., Ahmad, S. et al. Performance assessment of artificial neural networks and support vector regression models for stream flow predictions. Environ Monit Assess 190, 704 (2018). https://doi.org/10.1007/s10661-018-7012-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10661-018-7012-9