Evaluation of the Performance of Artificial Neural Network and Support Vector Machine Models in Estimation of Daily Evaporation amounts (Case study: Tabriz and Maragheh Synoptic Stations)

Document Type : Full length article


1 PhD Student, Water Resources Engineering, Faculty of Agriculture, Tabriz University

2 MSc student of Remote Sensing and GIS, Faculty of Geography and Planning, Tabriz University

3 Associate Professor of Climatology, Faculty of Geography and Planning, University of Tabriz


Evaporation is a fundamental component of the hydrology cycle and has an important role in water resources management. Daily evaporation is an important variable in reservoir capacity, rainfall-runoff modeling, crop management and water balance. Measurement of actual evaporation is almost impossible, but evaporation can be estimated using several methods. There are two general viewpoints for estimation of evaporation: direct and indirect methods. It is inoperative to measurement of the evaporation by direct methods in all locations. The direct methods are usually used for proximate reservoirs or irrigation projects. The indirect methods of evaporation estimation need various input data that are not easily available. Moreover, the evaporation have very complex and nonlinear process that simulation of its complex process using simple methods is impractical. In recent years, the artificial intelligent methods such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been successfully utilized for modeling the hydrological nonlinear process such as rainfall, precipitation, rainfall-runoff, evaporation, temperature, water quality, stream flow, water level and suspended sediment, etc. Therefore, this research evaluates the performance of ANN and SVM models in daily evaporation estimation.
Materials and methods
The daily climatic data, air temperature, wind speed, air pressure, relative humidity, rainfall, dew point temperature and sun shine hours of Tabriz and Maragheh synoptic stations are used as inputs to the ANN and SVM models to estimate the daily evaporation. For this purpose, 75 percent of the daily evaporation data were selected to calibrate the models and 25 percent of the data were used to validate the models. Different combinations of seven input and then individual inputs have been applied for  evaporation estimation.
ANNs are parallel information processing systems consisting of a set of neurons arranged in layers. These neurons provide suitable conversion functions for weighted inputs. In this study, we used Multilayer feed-forward perceptron (MLP) network. The MLP is trained with the use of back propagation learning algorithm. The back-propagation training algorithm is a supervised training mechanism and is normally adopted in most of the engineering applications. The neurons in the input layer have no transfer function. The logarithmic sigmoid transfer function was used in the hidden layer and linear transfer function was employed as an activation function from the hidden layer to the output layer, because the linear function is known to be robust for a continuous output variable. The optimal number of neuron in the hidden layer was identified using a trial and error procedure by varying the number of hidden neurons from 1 to 20. In recent years, SVM as one of the most important data-driven models has been considered in this regards. This model is a useful learning system based on constrained optimization theory that uses induction of structural error minimization principle and results as a general optimized answer. The SVM is a computer algorithm that are learnt by example to find the best function of classifier/hyperplane to separate the two classes in the input space. The SVM analyzes two kinds of data, i.e., linearly and non-linearly separable data. For a given training data with N number of samples, represented by, where x is an input vector and y is a corresponding output value, SVM estimator (f) on regression can be represented by:
Where w is a weight vector, b is a bias, and “.” denotes the dot product and  is a non-linear mapping function. Typically, three kernel functions, radial basis, polynomial and linear are applied in SVM. Use of each function with various parameters for evaporation estimation may have different results. Therefore, it is necessary to evaluate the accuracy of each of these functions and select the appropriate kernel functions for evaporation estimation. Two performance criteria are used in this study to assess the goodness of fit in the models. These are Correlation Coefficient (CC) and Root Mean Square Error (RMSE).
Results and discussion
In this paper, ten different combinations of seven inputs and then individual inputs are applied to  estimate the evaporation. Results of evaporation estimation in Tabriz station indicate that the first and eighth combinations have minimum RMSE and maximum CC in test period of ANN and SVM models, respectively. Also results of evaporation estimation in Maragheh station indicate that the first and Seventh combinations have minimum RMSE and maximum CC in test period of ANN and SVM models, respectively. The ANN model using first combination including air temperature, wind speed, air pressure, relative humidity, rainfall, dew point temperature and sun shine hours of climate data can achieve the values of 2.12 (mm) and 0.78 for RMSE and R statistics in test period for Tabriz station. The SVM model using eighth combination including wind speed, air pressure, relative humidity, rainfall, dew point temperature and sun shine hours of climate data, also achieve the values of 2.17 (mm) and 0.78 for RMSE and R statistics in test period for Tabriz station. Evaporation estimation of Maragheh station using ANN and SVM models, respectively, returned 1.62 (mm) and 1.43 (mm) for RMSE statistic in the test period. In next step, individual input results show that ANN model has better estimation of evaporation values in Tabriz station and SVM model in Maragheh station. The results also indicate that the SVM and ANN models have better estimation of evaporation values using individual inputs including average temperature and sun shine hours  compaired with other inputs, respectively.
The results of these models indicate that both ANN and SVM models have acceptable performance in evaporation estimation. Evaluation results show that the average temperature is better input than other six parameters in estimation of evaporation. The investigations of this study indicate that although there is no significant difference in the results of three kernel functions of support vector machine, but the Radial Basis kernel function has high accuracy and better performance in estimation of daily evaporation in comparison to other kernel functions.


Main Subjects

اسکندری، ع.؛ نوری، ر.؛ معراجی، ح. و کیاقادی، ا. (1390). توسعة مدلی مناسب بر مبنای شبکة عصبی مصنوعی و ماشین بردار پشتیبان برای پیش‏بینی به هنگام اکسیژن‏خواهی بیوشیمیایی 5 روزه، محیطشناسی، 38(61): 71ـ82.
بامری، م. (1393). برآورد تبخیر استان سیستان و بلوچستان به روش رگرسیون خطی و شبکة عصبی مصنوعی، پایان‌نامة کارشناسی ارشد مهندسی آب، دانشکدة آب و خاک دانشگاه زابل.
زارع ابیانه، ح.؛ نوری، ح.؛ لیاقت، ع.؛ نوری، ح. و کریمی، و. (1390). مقایسة روش پنمن مانتیث فائو و تشت تبخیر کلاس A با داده‏های لایسیمتری در برآورد تبخیر و تعرق گیاه برنج در منطقة آمل، پژوهشهایجغرافیایطبیعی، 76: 71ـ83.
علیزاده، ا. (1390). اصولهیدرولوژیکاربردی، چ 33، مشهد: انتشارات دانشگاه امام رضا.
عیسی‏زاده، م. (1394). تخمین جریان رودخانة زرینه‏رود با استفاده از مدل‏های هیبریدی فراکاوشی، پایان‌نامة کارشناسی ارشد مهندسی آب، دانشکدة کشاورزی، دانشگاه تبریز.
نجفی، ا.؛ صفاری، ا.؛ قنواتی، ع. و کرم، ا. (1394). شبیه‏سازی و تحلیل دبی‏های حداکثر لحظه‏ای با استفاده از شبکة عصبی مصنوعی (مطالعة موردی: ایستگاه‏های هیدرومتری هفت حوض، سولقان، قلاک، و مقصودبیک در کلان‌شهر تهران)، پژوهشهایژئومورفولوژیکمی، 4(1): 90ـ103.
Alizadeh, A. (2011). The principle of applied hydrology, Imam Reza Publication, Mashhad (In Persian).
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology (2000). Artificial neural networks in hydrology, I: preliminary concepts, Journal of Hydrologic Engineering,  5(2): 115-123.
Bamri, M. (2014). Evaporation estimation of Sistan and Baluchestan province using linear regression method and artificial neural network, Water Engineering master's thesis, Supervisor doctor Parviz Haghighatjoo, water and soil Faculty of the University of Zabol (In Persian).
Baofeng, G.; Gunn, S.R.; Damper, R.I. and Nelson, J.D.B. (2008). Customizing kernel Functions for SVM-based hyperspectral image classification, IEEE Transactions on Image Processing, 17(4): 622-629.
Basak, D.; Pal, S. and Patranabis, D.C. (2007). Support vector regression, Neural Inf. Process, 11: 203-225.
Bruton, J.M.; McClendon, R.W. and Hoogenboom, G. (2000). Estimating daily pan evaporation with artificial neural network, Trans. ASAE, 43(2): 492-496.
Dibike, Y.; Velickov, S.; Solomatine, D. and Abbott, M. (2001). Model induction with of support vector machines: Introduction and applications, Journal of Computing in Civil Engineering, 15(3): 208-216.
Eskandari, A.; Nouri, R.; Meraji, H. and Kiaghadi, A. (2012). Development of appropriate model based on artificial neural network and support vector machine for forecasting 5-Days Biochemical Oxygen Demand (BOD5), Journal of Ecology, 61: 71-82 (In Persian)
Fletcher, R. (1987). Practical methods of optimization, Wiley, New York. 456p.
Kavzoglu, T. and Colkesen, I. (2009). A kernel functions analysis for support vector machines for land cover classification, International Journal of Applied Earth Observation and Geoinformation, 11(5): 352-359.
Kim, S. and Kim, HS. (2008). Neural networks and genetic algorithm approach for nonlinear evaporation and evapotranspiration modeling, Journal of Hydrology, 351: 299-317.
Kisi, O. (2009). Modeling monthly evaporation using two different neural computing, Techniques Irrigation Science, 27(5): 417-430.
Kisi, O. (2016). Pan evaporation modeling using least square support vector machine, multivariate adaptive regression splines and M5 model tree, Journal of Hydrology, 528: 312-320.
Liu, G.Q. (2011). Comparison of regression and ARIMA models with Neural Network models to forecast the daily stream flow, PhD thesis, University of Delaware, 545p.
Liu, S.; Bai, J.; Jia, Z.; Jia, L.; Zhou, H. and Lu, L. (2010). Estimation of evapotranspiration in the Mu Us Sandland of China, Hydrology and Earth System sciences, 14: 573-584.
Misra, D.; Oommen, T.; Agarwal, A. and Mishra, S.K. (2009). Application and analysis of support vector machine based simulation for runoff and sediment yield, Journal of Bio Systems Engineering, 103 (9): 527-535.
Moghaddamnia, A.; Ghafari Gousheh, M.; Piri, J.; Amin, S. and Han, D. (2009). Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques, Advances in Water Resources, 32(1): 88-97.
Najafi, A.; Safari, A.; Ghanavati, A. And Karam, A. (2015). Simulation and analysis of maximum instantaneous flows using artificial neural network (Case study: hydrometric stations of Haft Hoz, Soghalan, Ghalak and Maghsod Beg in Tehran, Quantitative Geomorphological Researches, 4(1): 90-103 (In Persian).
Nourani, V. and Sayyah Fard, M. (2012). Sensitivity analysis of the artificial neural network outputs in simulation of the evaporation process at different climatologic regimes, Advances in Engineering Software, 47: 127-146.
Piri, J.; Amin, S.; Moghaddamnia, A.; Keshavarz, A.; Han, D. and Remesan, R. (2009). Daily pan evaporation modeling in a hot and dry climate, Journal of Hydrologic Engineering, 14(8): 803-811.
Tabari, H.; Marofi, S. and Sabziparvar, A.A. (2010). Estimation of daily pan evaporation using artificial neural network and multivariate non-linear regression, Irrigation Sciences, 28: 399-406.
Terzi, O. and Erol Keskn, M. (2005). Modeling of daily pan evaporation, Journal of Applied Sciences, 5(2): 368-372.
Tezel, G. and Buyukyildiz, M. (2015). Monthly evaporation forecasting using artificial neural networks and support vector machines, Theoretical and Applied Climatology.
Vapnik, V. and Chervonenkis, A. (1991). The necessary and sufficient conditions for consistency in the empirical risk minimization method, Pattern Recognition and Image Analysis, 1(3): 283-305.
Zare Abyaneh, H.; Nori, H.; Liyaghat, A.; Nori, A. and Karimi, V. (2011). Compare Penman-Monteith method and pan class A by lysimeter data to estimate evapotranspiration of rice plant in the Amol region, Physical Geography Research Quarterly, 76: 71-83 (In Persian).
Zealand, C.M.; Burn, D.H. and Simonovic, S.P. (1999). Short term stream flow forecasting using artificial neural networks, Journal of Hydrology, 214: 32-48.
Volume 49, Issue 1
April 2017
Pages 151-168
  • Receive Date: 05 April 2016
  • Revise Date: 23 October 2016
  • Accept Date: 23 November 2016
  • First Publish Date: 21 March 2017