Simulation of reservoir outflows using regression tree and support vector machine

Abstract

Water stored in reservoirs has a lot of crucial function, including generating hydropower, supporting water supply, and relieving lasting droughts. During floods, water deliveries from reservoirs must be acceptable, so as to guarantee that the gross volume of water is at a safe level and any release from reservoirs will not trigger flooding downstream. This study aims to develop a well-versed assessment method for managing reservoirs and pre-releasing water outflows by using the machine learning technology. As a new and exciting AI area, this technology is regarded as the most valuable, time-saving, supervised and cost-effective approach. In this study, two data-driven forecasting models, i.e., Regression Tree (RT) and Support Vector Machine (SVM), were employed for approximately 30 years’ hydrological records, so as to simulate reservoir outflows. The SVM and RT models were applied to the data, accurately predicting the fluctuations in the water outflows of a Bhakra reservoir. Different input combinations were used to determine the most effective release. For cross-validation, the number of folds varied. It is found that quadratic SVM for 10 folds with seven different parameters would give the minimum RMSE, maximum R ², and minimum MAE; therefore, it can be considered as the best model for the dataset used in this study.

Keywords

Reservoir outflow / Regression tree / Support vector machine / Error analysis

References

[1] AhmadlouM, KarimiM, AlizadehS, ShirzadiA, ParvinnejhadD, ShahabiH, PanahiM. Flood susceptibility assessment using integration of adaptive network-based fuzzy inference system (anfis) and biogeography-based optimization (bbo) and bat algorithms (ba). Geocarto International, 2019, 34: 1252-1272

[2] BahramiS, WigandE. Daily streamflow forecasting using nonlinear echo state network. International Journal Advance Research Science Engineering Technology, 2018, 5: 3619-3625

[3] BasakD, PalS, PatranabisDC. Support vector regression. Neural Information Processing-Letters and Reviews, 2007, 11: 203-224

[4] BowdenGJ, MaierHR, DandyGC. Optimal division of data for neural network models in water resources applications. Water Resources Research, 2002, 38: 2-1-2-11

[5] BreimanL. Classification and regression trees, 2017 Routledge

[6] ChaventMA. Monothetic clustering method. Pattern Recognition Letters, 1988, 19: 989-996

[7] CollobertR, BengioS. SVM Torch: Support vector machines for large-scale regression problems. Journal of Machine Learning Research, 2001, 1: 143-160

[8] CristianiniN, Shawe-TaylorJ. An introduction to support vector machines and other Kernel-based learning methods, 2000 Cambridge University Press

[9] Drucker, H., Burges, C. J. C., Kaufman, L., Smola, A., Vapnik, V. (1996). Support vector regression machines. Advance in Neural Information Processing System 155–161.

[10] GunnSR. Support vector machines for classification and regression. ISIS Technical Report, 1988, 14: 5-16

[11] HejaziMI, CaiXM. Input variable selection for water resources systems using a modified minimum redundancy maximum relevance algorithm. Advances in Water Resources, 2009, 32(4):582-593

[12] HipniA, El-shafieA, NajahA, KarimOA, HussainA, MukhlisinM. Daily forecasting of dam water levels: Comparing a Support Vector Machine (SVM) Model with Adaptive Neuro Fuzzy Inference System (ANFIS). Water Resour. Manag., 2013, 27: 3803-3823

[13] Hong, Y., Lee, Y. J. (2009). Citing Websites. A loss function approach to model specification testing and its relative efficiency to the GLR test. Retrieved 3rd February 2013.

[14] Hu, C., Wan, F. (2009). Input Selection in Learning Systems: A Brief Review of Some Important Issues and Recent Developments. In Proceedings of the IEEE International Conference on Fuzzy Systems, Jeju Island, Korea, 20–24 August, pp. 530–535.

[15] HussainHW, IshakW, Ku-mahamudKR, NorwawiN. Neural network application in reservoir water level forecasting and release decision. International Journal of New Computer Architectures and Their Applications, 2011, 1: 265-274

[16] KhanMS, CoulibalyP. Application of support vector machine in lake water level prediction. Journal of Hydrologic Engineering, 2006, 11(3):199-205

[17] KimSJ, RyooEC, JungMK, KimJK, AhnHC. Application of support vector regression for improving the performance of the emotion prediction model. Journal of Intelligent Information System, 2012, 18: 185-202

[18] LiPH, KwonHH, SunL, LallU, KaoJJ. A modified support vector machine based prediction model on streamflow at the Shihmen Reservoir, Taiwan. International Journal of Climatology, 2010, 30: 1256-1268

[19] LohWY. Classification and regression trees. Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery., 2011, 1(1):14-23

[20] Mokhtar, A. S., Wan Ishak, W. H., Md Norwawi, N. (2014). Modelling of reservoir water release decision using neural network and temporal pattern of reservoir water level. In: Proceedings of the fifth international conference on intelligent systems, modelling and simulation, pp 127–130.

[21] MullainathanS, SpiessJ. Machine learning: An applied econometric approach. Journal of Economic Perspective, 2017, 31: 87-106

[22] NaghibiSA, PourghasemiHR. A comparative assessment between three machine learning models and their performance comparison by bivariate and multivariate statistical methods in groundwater potential mapping. Water Resources Management., 2015, 29: 5217-5236

[23] NajahAA, El-ShafieA, KarimOA, JaafarO. Integrated versus isolated scenario for prediction dissolved oxygen at progression of water quality monitoring stations. Hydrology and Earth System Sciences Discuss, 2011, 8: 6069-6112

[24] Nwobi-OkoyeCC, IgboanugoAC. Predicting water levels at Kainji dam using artifcial neural networks. Nigerian Journal of Technology, 2013, 32(1):129-136

[25] Onur HınçalA, Burcu Altan-SakaryaA, GerM. Optimization of multireservoir systems by genetic algorithm. Journal Water Resource Management, 2011, 25: 1465-1487

[26] QuinlanJ. Induction of decision trees. Machine Learning, 1986, 1: 1-81

[27] SchwefelHP. Numerical optimization of computer models, 1981 John Wiley & Sons Inc

[28] SeckinN, CobanerM, YurtalR, HaktanirT. Comparison of artifcial neural network methods with l-moments for estimating food fow at ungauged sites. Water Resour Manage J, 2013, 27(7):2103-2124

[29] ShafaeiM, KisiO. Lake level forecasting using Wavelet-SVR, Wavelet-ANFIS and Wavelet-ARMA conjunction models. Water Resources Management, 2016, 30(1):79-97

[30] SharafatiA, KhosraviK, KhosraviniaP, AhmedK, SalmanSA, YaseenZM, ShahidS. The potential of novel data mining models for global solar radiation prediction. International Journal of Environmental Science and Technology, 2019, 16: 7147-7164

[31] SmolaAJ, ScholkopfB. A tutorial on support vector regression. Statistics and Computing, 2004, 14(3):1-24

[32] TokarAS, MarkusM. Precipitation-runoff modeling using artificial neural networks and conceptual models. Journal of Hydrologic Engineering, 2000, 5(2):156-161

[33] VapnikV. The nature of statistical learning theory, 1995 Springer-Verlag

[34] VensC, SchietgatL, StruyfJ, BlockeelH, KocevD, DžeroskiS. Inductive databases and constraint-based data mining, 2010 Springer 365-387

[35] WittenIH, FrankE. Data mining: Practical machine learning tools and techniques with java implementations, 2000 Morgan Kaufmann Publishers

[36] YangT, GaoX, SorooshianS, LiX. Simulating California reservoir operation using the classification and regression-tree algorithm combined with a shuffled crossvalidation scheme. Water Resources Research, 2016, 52: 1626-1651

[37] ZhangD, et al.. Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm. Journal of Hydrology, 2018, 565: 720-736