NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE

Size: px
Start display at page:

Download "NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE"

Transcription

1 NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE 1 I. Skitzi, 1 E. Paleologos and 2 K. Katsifarakis 1 Technical University of Crete 2 Aristotle University of Thessaloniki ABSTRACT A multi-layer perceptron (MLPs)-neural-network- back-propagation algorithm (BP) has been developed to simulate the daily discharges of two springs that lie in a karstic environment. The correlation of the precipitation and runoff series for different time lags was initially estimated to define the input and output parameters relation. The performance of several types of neural networks with different training functions was assessed based on a mean square error criterion between observed and simulated discharge values. The simulation results showed that our MLP network provides excellent predictions for karstic spring discharges, capturing both local minima and maxima, and resulting in low mean square errors.

2 1. INTRODUCTION The last two decades the application of artificial intelligence algorithms has found broad use in engineering applications [1, 2, 3, 4, 5]. Artificial intelligence refers to simulation techniques that aim to mimic the process of developing general rules from repeated trials and training from known cases, followed by testing of the rules validity in new cases. Neural networks hold promise for complex subsurface hydrologic problems, where the development of constitutive physical relations appears to be elusive. The use of black box models to describe complex processes is not new in hydrology, and in at least surface hydrology it has a long and productive record [6, 7]. Subsurface flow in karstic environments is characterized by a complex interaction of geological, physical, and chemical processes and its study appears to be a natural candidate for the application of neural networks. 1.1 Neural Network s philosophy Artificial neural networks simulate the constitution and function of biological neural networks. The model of an artificial neuron is comprised of a summing and an activation function. The worth of each input value is assessed through synaptic weights, and then, all the weighted inputs are added. To correct for a linearity assumption a distributive value of bias is further added to the summing function (equation 1). The result forms the argument of an activation function φ that acts as a filter and which yields the neuron s response as a single number (equation 2). For hydrologic processes the procedure for a single neuron k, where the input parameters j (e.g., precipitation, temperature, evaporation etc.) are given as time series, x j (t), can be described at each time interval as follows: and φ Here x j (t) is the input value of parameter j at time-step t; w kj (t) is the weight assigned by neuron k to the input value of parameter j at time t; φ is a nonlinear activation function; b k (t) is the bias of the k-neuron at time t, and y k (t) is the output signal from neuron k at time t. The Figure 1. The structure of an artificial neuron k

3 process can be repeated for all entries of the time series and yields an output vector y k. The procedure for one time step if a single artificial neuron were to be used is shown in Figure 1. Neurons can form layers that are fully interconnected creating networks. A typical network consists of three types of layers: a) input layer, b) hidden layer and c) output layer. The input layer refers to the available data that enter the system and the number of neurons that constitute this layer is equal to the number of the parameters that contribute to the simulation. The number of the network s hidden layers can be more than one, according to the problem s complexity. Finally, the output layer returns the output vectors, which are the final responses of the neural network [8]. A typical artificial neural network is shown in Figure 2. Figure 2. A typical artificial neural network The most important issue about artificial neural networks is the phase of learning, which is achieved through examples, mimicking the experience phase of human learning. There are three types of training: 1) Supervised - Associative, 2) Unsupervised - Self-organization and 3) Semi - supervised [8]. The process of learning refers to the adjustment of weights, through which the inputs are linearly related, in order to minimize the error between the network s prediction and the actual response. It is an iterative procedure that adjusts the synaptic weights values as the network gains extra knowledge, after each iteration. The learning rule is described through the following equation: where w kj represents the weight assigned by neuron k on parameter j, and Δw is the adjustment in this weight from time t n to time t n+1. The most common procedures for determination of the value are the [8, 9]: 1) Hebb rule: where is neuron s k output response, is neuron s j input signal, and η is the network s learning rate.

4 2) Delta rule: where is the error :. Here is the predicted value and is the actual response from a neuron k; is a neuron s j input signal, and η is the network s learning rate. 2. SITE DESCRIPTION The Municipality of Rouva is a semi-mountainous and agricultural area of 62,725 km 2 with a population of 2,324 inhabitants, situated at central-southern Crete in the prefecture of Heraklion, Greece. The region is characterized by a large number of natural springs, as Rouva lies at the hydrologic basin of Geropotamos. The area of Rouva is part of the hydrogeologic unit of the Psiloriti Talea Mountain, which is one of the main karstic systems in Crete. Simulating karstic aquifers with traditional mathematical methods, which are based on continuum approaches, is problematic and artificial neural networks have been used as alternative tools for these types of problems [10, 11]. The objective of the present study was to develop a neural network model to predict the discharge from two karstic springs in the region; the first spring is located at Mai Vrisi and the second at Pera Vrisi. The neural network utilized the measured rainfall and discharge data, which were collected on a daily basis between the years (until 14/07/09). 3. MODEL DEVELOPMENT Initially, in order to simulate the two karstic springs, it was necessary to set an appropriate neural network for the specific natural system. The type of network utilized in this study was a back propagation feed-forward Neural Network with one hidden layer. Selection of a single hidden layer was motivated by the fact that the network was to simulate discharges only, by means of precipitation data. A basic condition for training with back propagation was the availability of patterns and targets, since training was supervised during simulation of known cases [8]. Patterns were considered to be all the available data that entered the network, while targets were the responses that the network was to provide as output. In our study daily rainfall and discharge values formed the respective input and output vectors. In order to improve the network s efficiency an extra parameter was added in the input layer. This was a serial number that indicated the date that the precipitation and discharge data were obtained, designated as the day number. Finally, the number of neurons in the hidden layer was determined through trial and error. 3.1 Definition of the time lag An important issue in processing the available data is defining the right time lag [10] between precipitation and spring discharge. This designates the delay between input excitation and output response in a subsurface hydrologic system as water travels from recharge to discharge areas at a rate that depends on an aquifer s hydro-geologic characteristics and the intensity and duration of a precipitation event [12]. The determination of a suitable time lag contributes to the appropriate correlation of input and output variables and improves the efficiency of a neural network. The correlation coefficient of rainfall and discharge time series was used in order to define the time lag. The correlation coefficient is given by:

5 where A and B, two time series, i and i their components and and their average values, respectively. Calculation of the correlation coefficients for time lags from zero to thirty days yielded the appropriate time lag, taken as the one that provided the maximum correlation. 3.2 Selection of an optimum network In order to select an optimum network structure five different training algorithms were tested, comprising of one to ten neurons in a single hidden layer. Training algorithms adjusted weights and biases with the goal to minimize a performance function. In feed-forward neural networks the performance function to be minimized is taken to be the mean square error, between model-predicted output and actual response. The mean square error (MSE) is given by: where d i is the measured data, y i is the model prediction, and N the number of available samples. In each synapse between connected neurons the training function calculates the output error and determines the adjustments to the network s weights and bias. The five training algorithms that were tested were as follows [13]: 1. Gradient descent (GD) 2. Gradient descent with momentum (GDM) 3. Gradient descent momentum and an adaptive learning rate (GDX) 4. Levenberg-Marquardt (LM) 5. Bayesian regularization (BR) Tables 1 and 2 show in the fourth column the MSE from the five training algorithms as well as the number of neurons in the hidden layer that correspond to the minimum MSE values. TABLE 1. Mai Vrisi Spring: Optimum MSE values & neuron number in the hidden layer 1 newff, traingd, learngdm Η=9 MSE= (l/s) 2 2 newff, traingdm, learngdm Η=4 MSE= (l/s) 2 3 newcf, traingdx, learngdm Η=4 MSE= (l/s) 2 4 newcf, trainlm, learngdm Η=4 MSE=0.003 (l/s) 2 5 newcf, trainbr Η=3 MSE= (l/s) 2 The optimum value of MSE for the Mai Vrisi spring was obtained by the Levenberg Marquardt training algorithm with four neurons in the hidden layer and is shown with bold characters at the table above.

6 TABLE 2. Pera Vrisi Spring: Optimum MSE values & neuron number in the hidden layer 1 newff, traingd, learngdm Η=6 MSE= (l/s) 2 2 newff, traingdm, learngdm Η=9 MSE= (l/s) 2 3 newcf, traingdx, learngdm Η=8 MSE= (l/s) 2 4 newcf, trainlm, learngdm Η=4 MSE= (l/s) 2 5 newcf, trainbr Η=7 MSE=0.009 (l/s) 2 The optimum value of MSE for the Pera Vrisi spring was obtained again by the Levenberg Marquardt training algorithm with four neurons in the hidden layer and is shown with bold characters at the table above. The Levenberg Marquardt training algorithm is a popular method that is simple, fast, and efficient [14, 15] for determining a function s minimum via the Gauss-Newton and Steepest Descent methods. It is used in moderate-sized feed-forward neural networks [13]. Based on these tests the same neural network structure was used for both springs, and this is depicted in the following figure: 4. RESULTS Figure 3. Optimum neural network structure for both springs 4.1 Optimum network response The optimum neural network architecture and training parameters resulted from testing five different algorithms in a Matlab environment. The available data were normalized between the values of 0 and 1, and then they were portioned into three subsets: a) the training set, b) the validation set, and c) the testing set. The validation phase in learning is needed to supervise the performance of the trained neural network, and to assess the network s behavior with other sets during simulation. The results of the neural network containing the training, validation and testing periods are presented in Figures 4 and 5, for the two springs, respectively. The values of normalized testing mean square error were found to be equal to (l/s) 2 and (l/s) 2 for the Mai Vrisi, and the Pera Vrisi springs, respectively. The neural network was able to capture in a very satisfactory way the trends as well as predict the observed discharge data.

7 Spring Discharge (l/s) Spring Discharge (l/s) Mai Vrisi Spring training validation testing Measured Data Model Prediction Data Points Figure 4. Measured Data and Model Prediction for Mai Vrisi Spring Discharge Pera Vrisi Spring training validation testing Measured Data Model Prediction Data Points Figure 5. Measured Data and Model Prediction for Pera Vrisi Spring Discharge 5. CONCLUSION Neural networks provide a promising alternative in flow problems where the applications of models that are based on physical constitutive relations, developed through a continuum assumption appear to be questionable. Studies of carbonate karstic aquifers, where there exists a complex interaction of geologic, hydrologic, and geochemical processes on the geometry of the porous medium and the flow in it, suggest that artificial neural networks result in excellent simulation results [10, 11]. The optimum structure of a neural network, determination of input and output vectors, the number of hidden layers, as well as the number of neurons in each hidden layer, are significant issues that affect a network s performance. Hydrologic problems with many variables require complicated neural networks with many neurons in the hidden layers in order to provide an adequate prediction. Our study dealt with the simulation of daily spring discharge in a karstic environment in Crete. The appropriate network structure was found by testing five different types of

8 algorithms in the Matlab environment and the Levenberg-Marquardt algorithm proved to be the most efficient algorithm, for the two springs considered. The optimum network resulted in simulated discharges that followed closely the patterns of the measured discharge data, and provided predictions of high accuracy. Ongoing research includes investigation of the effect of additional parameters to the input space, with the aim to improve model prediction. Furthermore, we plan to examine the optimization of a neural network s behavior by using as input the precipitation series that correspond to the maximum correlation coefficient for different time lags. ACKNOWLEDGEMENT The authors are indebted to N. Darivianakis for providing the field data. REFERENCES 1. Katsifarakis K.L. and Z. Petala (2006) Combining genetic algorithms and boundary elements to optimize coastal aquifers management, Journal of Hydrology, Vol. 327 (1 2), pp Karamperidou C. (2007) Coastal Aquifer s Management with Artificial Neural Networks, M.Sc. Thesis, Department of Civil Engineering, Aristotle University Thessaloniki. 3. Chen J. and B. J. Adams (2006) Integration of artificial neural networks with conceptual models in rainfall-runoff modeling, Journal of Hydrology, Vol. 318, pp Affandi A., K. Watanabe and H. Tirtomihardjo (2007) Application of an artificial neural network to estimate groundwater level fluctuation Journal of Spatial Hydrology, Vol. 7 (2), pp Hu Z., G. Huang, and C. Chan (2003) A fuzzy process controller for in situ groundwater bioremediation, Engineering Applications of Artificial Intelligence, Vol. 16, pp Abbott M.B. and J.C. Refsgaard (1996) Distributed Hydrological Modelling, Kluwer Academic Publishers. 7. Singh, V. P., and D. A. Woolhiser (2002) Mathematical Modeling of Watershed Hydrology, Journal of Hydrologic Engineering, Vol. 7 (4), pp Haykin S. (1994) Neural Networks: A Comprehensive Foundation, Macmillan Publishing Company, N.Y. 9. Hebb D.O. (1949) "The organization of behavior - A neurophysiological theory", Wiley. 10. Trichakis I., I. Nikolos, G. Karatzas (2009) Optimal selection of artificial neural network parameters for the prediction of a karstic aquifer s response Hydrological Processes, Vol. 23, pp Lallahem S. and J. Mania (2003) A nonlinear rainfall-runoff model using neural network technique: example in fractured porous media Mathematical and Computer Modeling, Vol. 37, pp Hao Y., D. Huang and C. Hu (2005) Response of Karst Spring Discharge to Precipitation in Semiarid Region of China Systems, Man and Cybernetics, 2005 IEEE International Conference, Vol. 2, pp Mathworks, Matlab, R2008a, Tutorial. 14. Affandi A., K. Watanabe, H. Tirtomihardjo (2007) Application of an artificial neural network to estimate groundwater level fluctuation Journal of Spatial Hydrology, Vol. 7 (2), pp Hagan M. T. and B. M. Menhaj (1994) Training Feedforward Networks with the Marquardt Algorithm IEEE Transactions on Neural Networks, Vol. 5 (6), pp

MEASUREMENT AND PREDICTION OF KARSTIC SPRING FLOW RATES

MEASUREMENT AND PREDICTION OF KARSTIC SPRING FLOW RATES Global NEST Journal, Vol 17, No X, pp XX-XX, 2015 Copyright 2015 Global NEST Printed in Greece. All rights reserved MEASUREMENT AND PREDICTION OF KARSTIC SPRING FLOW RATES DARIVIANAKIS N. KATSIFARAKIS

More information

CORRELATION AND PREDICTION OF CHEMICAL PARAMETERS IN GROUND WATER OF THE MUNICIPALITY OF THERMI USING SPSS, G.I.S. AND ARTIFICIAL NEURAL NETWORKS

CORRELATION AND PREDICTION OF CHEMICAL PARAMETERS IN GROUND WATER OF THE MUNICIPALITY OF THERMI USING SPSS, G.I.S. AND ARTIFICIAL NEURAL NETWORKS Proceedings of the 13 th International Conference on Environmental Science and Technology Athens, Greece, 5-7 September 2013 CORRELATION AND PREDICTION OF CHEMICAL PARAMETERS IN GROUND WATER OF THE MUNICIPALITY

More information

An Application of Neural Networks in Market Segmentation

An Application of Neural Networks in Market Segmentation 1 & Marketing An Application of Neural Networks in Market Segmentation Nikolaos Petroulakis 1, Andreas Miaoudakis 2 1 Foundation of research and technology (FORTH), Iraklio Crete, 2 Applied Informatics

More information

WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH

WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH Robin Kumar Biswas MEE0877 Supervisor: Prof. A. W. Jayawardena ABSTRACT The nonlinear relationship

More information

EFFECT OF TRAINING DATASET LENGTH ON THE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK MODEL

EFFECT OF TRAINING DATASET LENGTH ON THE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK MODEL EFFECT OF TRAINING DATASET LENGTH ON THE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK MODEL *Jitendra Sinha, Rajendra Kumar Netam and Rekha Bai Department of Agricultural Engineering, Indira Gandhi Krishi

More information

Artificial Neural Network Model for Rainfall-Runoff -A Case Study

Artificial Neural Network Model for Rainfall-Runoff -A Case Study , pp. 263-272 http://dx.doi.org/10.14257/ijhit.2016.9.3.24 Artificial Neural Network Model for Rainfall-Runoff -A Case Study P.Sundara Kumar 1, T.V.Praveen 2 and M. Anjanaya Prasad 3 1 Research scholar,

More information

Modeling of Rainfall - Runoff relationship using Artificial Neural Networks

Modeling of Rainfall - Runoff relationship using Artificial Neural Networks Modeling of Rainfall - Runoff relationship using Artificial Neural Networks Nimiya Baby Department of Applied Mechanics and Hydrauliics National Institute of Technology Karnataka, Surathkal Karnataka,

More information

Application of Artificial Neural Networks in Prediction: A Case Study in Consumer Propensity to Buy Insurance

Application of Artificial Neural Networks in Prediction: A Case Study in Consumer Propensity to Buy Insurance Application of Artificial Neural Networks in Prediction: A Case Study in Consumer Propensity to Buy Insurance Rosmayati Mohemad 609-6683106 rosmayati@umtedumy Noor Azliza Che Mat 609-6683106 azliza@umtedumy

More information

Analysis of Mean Monthly Rainfall Runoff Data of Indian Catchments Using Dimensionless Variables by Neural Network

Analysis of Mean Monthly Rainfall Runoff Data of Indian Catchments Using Dimensionless Variables by Neural Network Journal of Environmental Protection, 2010, 1, 155-171 doi:10.4236/jep.2010.12020 Published Online June 2010 (http://www.scirp.org/journal/jep) 1 Analysis of Mean Monthly Rainfall Runoff Data of Indian

More information

QUALITATIVE MODELING FORTHE MINÂB RIVER USING MULTI-LAYER NEURAL NETWORKS

QUALITATIVE MODELING FORTHE MINÂB RIVER USING MULTI-LAYER NEURAL NETWORKS QUALITATIVE MODELING FORTHE MINÂB RIVER USING MULTI-LAYER NEURAL NETWORKS Mehrdad Fereydooni and * Reza Jafari Rangbar Department of Civil Engineering, Larestan Branch, Islamic Azad University, Larestan,

More information

Study of Pile Cap Lateral Resistance using Artificial Neural Networks

Study of Pile Cap Lateral Resistance using Artificial Neural Networks International Journal of Computer Applications (975 8887) Volume 21 No.1, May 211 Study of Pile Cap Lateral Resistance using Artificial Neural Networks Utpal K. Nath Assistant Professor Civil Engineering

More information

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Contents Biological problem: promoter modeling Basics of neural networks Perceptrons

More information

IJSRD - International Journal for Scientific Research & Development Vol. 4, Issue 03, 2016 ISSN (online):

IJSRD - International Journal for Scientific Research & Development Vol. 4, Issue 03, 2016 ISSN (online): IJSRD - International Journal for Scientific Research & Development Vol. 4, Issue 03, 2016 ISSN (online): 2321-0613 Development of Stage Discharge Relationship at Barman Station on Narmada River M.D. Maitri

More information

Research Article ANN-Based Estimation of Groundwater Quality Using a Wireless Water Quality Network

Research Article ANN-Based Estimation of Groundwater Quality Using a Wireless Water Quality Network Hindawi Publishing Corporation International Journal of Distributed Sensor Networks Volume 214, Article ID 458329, 8 pages http://dx.doi.org/1.1155/214/458329 Research Article ANN-Based Estimation of Groundwater

More information

Neural Networks and Applications in Bioinformatics

Neural Networks and Applications in Bioinformatics Contents Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Biological problem: promoter modeling Basics of neural networks Perceptrons

More information

Seawater intrusion into the aquifer of Eleftherae-N. Peramos, Kavala, Greece

Seawater intrusion into the aquifer of Eleftherae-N. Peramos, Kavala, Greece River Basin Management IV 3 Seawater intrusion into the aquifer of Eleftherae-N. Peramos, Kavala, Greece C. Karamperidou, E. Karamperidou & K. L. Katsifarakis Department of Civil Engineering, Aristotle

More information

CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK

CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK Asst. Prof. S. V. Shah 1, Ms. Deepika A. Pawar 2, Ms. Aishwarya S. Patil 3, Mr. Prathamesh S. Bhosale 4, Mr. Abhishek S. Subhedar 5, Mr. Gaurav D. Bhosale

More information

Artificial Neural Network Based Modelling of Photovoltaic System

Artificial Neural Network Based Modelling of Photovoltaic System Artificial Neural Network Based Modelling of Photovoltaic System H. Parmar Department of Mechanical Engineering, Ujjain Engineering College, Ujjain (M.P.)- INDIA Abstract- Photovoltaic system (PV) is alternate

More information

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) EFFORT ESTIMATION USING A SOFT COMPUTING TECHNIQUE

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) EFFORT ESTIMATION USING A SOFT COMPUTING TECHNIQUE INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print), ISSN 0976 6367(Print) ISSN 0976 6375(Online)

More information

Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes

Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes Vasile S. Radu Institute for Nuclear Research Piteşti vasile.radu@nuclear.ro 1 st Research Coordination Meeting for the CRP Prediction of

More information

Air Quality Prediction Using Artificial Neural Network

Air Quality Prediction Using Artificial Neural Network Air Quality Prediction Using Artificial Neural Network Suraya Ghazali 1 and Lokman Hakim Ismail 2 1 Faculty of Civil and Environmental Engineering, Universiti Tun Hussein Onn Malaysia (UTHM), Batu Pahat,

More information

Application of Hybrid FFNN-Genetic Algorithm for Predicting Evaporation in Storage Dam Reservoirs

Application of Hybrid FFNN-Genetic Algorithm for Predicting Evaporation in Storage Dam Reservoirs AGRICULTURAL COMMUNICATIONS, 2014, 2(4): 57-62. Application of Hybrid FFNN-Genetic Algorithm for Predicting Evaporation in Storage Dam Reservoirs MOHAMMAD ALI IZADBAKHSH 1 AND HOSAIN JAVADIKIA 2 1 Department

More information

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load L. EKONOMOU 1 D.S. OIKONOMOU 2 1 Hellenic American University, 12 Kaplanon Street,

More information

Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production

Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production Alireza Zendehboudi, Xianting Li*, Siyuan Ran Department of Building Science, School of

More information

DEVELOPMENT OF A NEURAL NETWORK MATHEMATICAL MODEL FOR DEMAND FORECASTING IN FLUCTUATING MARKETS

DEVELOPMENT OF A NEURAL NETWORK MATHEMATICAL MODEL FOR DEMAND FORECASTING IN FLUCTUATING MARKETS Proceedings of the 11 th International Conference on Manufacturing Research (ICMR2013), Cranfield University, UK, 19th 20th September 2013, pp 163-168 DEVELOPMENT OF A NEURAL NETWORK MATHEMATICAL MODEL

More information

International Journal of Industrial Engineering Computations

International Journal of Industrial Engineering Computations International Journal of Industrial Engineering Computations 2 (2011) 431 438 Contents lists available at GrowingScience International Journal of Industrial Engineering Computations homepage: www.growingscience.com/ijiec

More information

Time Series Modeling in Water Resources Planning and Management

Time Series Modeling in Water Resources Planning and Management 247 Y. R. Satyaji Rao, B. Krishna, and P. C. Nayak Deltaic Regional Centre, National nstitute of Hydrology, Kakinada, Andhra Pradesh, ndia ABSTRACT: Most of the times continuous hydrological time series

More information

Nonconventional Technologies Review no. 4/2011 MODELING THE PLASMA ARC CUTTING PROCESS USING ANN

Nonconventional Technologies Review no. 4/2011 MODELING THE PLASMA ARC CUTTING PROCESS USING ANN MODELING THE PLASMA ARC CUTTING PROCESS USING ANN Miroslav RADOVANOVIC, Milos MADIC University of Nis, Faculty of Mechanical Engineering in Nis, Serbia Abstract: This paper deals with modeling of plasma

More information

Case Study: STE-Neural Energy Production Forecast for Run-Of-River Hydro Power Plants. By Mario Arquilla and Fabio Pasut, S.T.E.

Case Study: STE-Neural Energy Production Forecast for Run-Of-River Hydro Power Plants. By Mario Arquilla and Fabio Pasut, S.T.E. Case Study: STE-Neural Energy Production Forecast for Run-Of-River Hydro Power Plants By Mario Arquilla and Fabio Pasut, S.T.E. Energy, Italy ABSTRACT The possibility to accurately predict the actual tendencies

More information

Modelling hydrological time series data using wavelet neural network analysis

Modelling hydrological time series data using wavelet neural network analysis New Approaches to Hydrological Prediction in Data-sparse Regions (Proc. of Symposium HS. at the Joint AHS & AH Convention, Hyderabad, ndia, September 9). AHS Publ. 333, 9. 11 Modelling hydrological time

More information

CHAPTER 4: Risk Assessment Risk in Groundwater Contamination

CHAPTER 4: Risk Assessment Risk in Groundwater Contamination CHAPTER 4: Risk Assessment Risk in Groundwater Contamination Instructor: Dr. Yunes Mogheir -١ Introduction: Water pollution is nowadays one of the most crucial environmental problems world-wide. Pollution

More information

LOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK AT AL BATINAH REGION OMAN

LOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK AT AL BATINAH REGION OMAN Journal of Engineering Science and Technology Vol. 7, No. 4 (01) 498-504 School of Engineering, Taylor s University LOAD FORECASTING FOR POWER SYSTEM PLANNING AND OPERATION USING ARTIFICIAL NEURAL NETWORK

More information

A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column

A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column Sanjay R. Patil 1 *, V. N. Ghate 2 1 Department of Instrumentation Engineering, Government College of

More information

Energy Forecasting using Artificial Neural Networks

Energy Forecasting using Artificial Neural Networks Energy Forecasting using Artificial Neural Networks G.Tamizharasi, S.Kathiresan, K.S.Sreenivasan Assistant Professor, Dept. of E&I,Bharath University,Chennai-600073, India Professor,Departmentment of Mechanical

More information

A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network

A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network Cagatay Bal, 1 *, Serdar Demir, 2 and Cagdas Hakan Aladag 3 Abstract Feed Forward

More information

Journal of Applied Hydrology

Journal of Applied Hydrology Journal of Applied Hydrology (1) (2) (2014) 43-53 http://jap.haraz.ac.ir Journal of Applied Hydrology Licensed by; MSRT of I.R.of Iran; No. 3/18/557925 January 29, 2014 Groundwater level fluctuation forecasting

More information

Neural Network Approximation of a Hydrodynamic Model in Optimizing Reservoir Operation

Neural Network Approximation of a Hydrodynamic Model in Optimizing Reservoir Operation Neural Network Approximation of a Hydrodynamic Model in Optimizing Reservoir Operation D.P. Solomatine International Institute for Infrastructural, Hydraulic and Environmental Engineering, P.O.Box 3015,

More information

MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB

MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB Journal of Engineering Science and Technology Vol. 10, No.11 (2015) 1477-1486 School of Engineering, Taylor s University MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB K. S.

More information

WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK

WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK VINAYAK K PATKI, S. SHRIHARI, B. MANU Research scholar, National Institute of Technology Karnataka (NITK), Surathkal,

More information

This is a refereed journal and all articles are professionally screened and reviewed

This is a refereed journal and all articles are professionally screened and reviewed Advances in Environmental Biology, 5(6): 1202-1208, 2011 ISSN 1995-0756 1202 This is a refereed journal and all articles are professionally screened and reviewed ORIGINAL ARTICLE Using Artificial Neural

More information

SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE NETWORK ALGORITHM

SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE NETWORK ALGORITHM Journal of Engineering Science and Technology Vol. 13, No. 3 (2018) 755-765 School of Engineering, Taylor s University SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE

More information

Artificial neural networks and particle swarm optimization based model for the solution of groundwater management problem

Artificial neural networks and particle swarm optimization based model for the solution of groundwater management problem European Water 57: 345-352, 2017. 2017 E.W. Publications Artificial neural networks and particle swarm optimization based model for the solution of groundwater management problem S. Gaur *, A. Dave, A.

More information

An artificial neural network approach for short-term wind power forecasting in Portugal

An artificial neural network approach for short-term wind power forecasting in Portugal Eng Int Syst (29) 1: 5 11 Engineering 29 CRL Publishing Ltd Intelligent Systems An artificial neural network approach for short-term wind power forecasting in Portugal J P S Catalão 1,HMIPousinho 1 and

More information

Software Effort Estimation with Different Artificial Neural Network

Software Effort Estimation with Different Artificial Neural Network Software Effort with Different Artificial Neural Network Jagannath Singh Department of Computer Sc. and Engineering National Institute of Technology Rourkela Rourkela, India E-mail: jagannath.singh@gmail.com

More information

Reservoirs performances under climate variability: a case study

Reservoirs performances under climate variability: a case study 526 Evolving Water Resources Systems: Understanding, Predicting and Managing Water Society Interactions Proceedings of ICWRS24, Bologna, Italy, June 24 (IAHS Publ. 364, 24). Reservoirs performances under

More information

Anticipating milk yield using artificial neural network

Anticipating milk yield using artificial neural network Int. Journal of Applied Sciences and Engineering Research, Vol. 3, Issue 3, 2014 www.ijaser.com 2014 by the authors Licensee IJASER- Under Creative Commons License 3.0 editorial@ijaser.com Research article

More information

Research on Evaluation of Enterprise Performance Based on BP Neural Network Improved by Levenberg-Marquardt Algorithm Wanyin Du

Research on Evaluation of Enterprise Performance Based on BP Neural Network Improved by Levenberg-Marquardt Algorithm Wanyin Du International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2015) Research on Evaluation of Enterprise Performance Based on BP Neural Network Improved by Levenberg-Marquardt

More information

Prediction of organic matter removal from pulp and paper mill wastewater using artificial neural network

Prediction of organic matter removal from pulp and paper mill wastewater using artificial neural network FEDERAL UNIVERSITY OF BAHIA, BRAZIL POLYTECHNIC SCHOOL DEPARTMENT OF ENVIRONMENTAL ENGINEERING RESEARCH GROUP ON SOLID WASTE AND WASTEWATER RESEARCH NETWORK ON CLEAN TECHNOLOGIES http://www.teclim.ufba.br

More information

Research Article Forecasting Bank Deposits Rate: Application of ARIMA and Artificial Neural Networks

Research Article Forecasting Bank Deposits Rate: Application of ARIMA and Artificial Neural Networks Research Journal of Applied Sciences, Engineering and Technology 7(3): 527-532, 2014 DOI:10.19026/rjaset.7.286 ISSN: 2040-7459; e-issn: 2040-7467 2014 Maxwell Scientific Publication Corp. Submitted: February

More information

Recurrent Neural Network Based Approach for Solving Groundwater Hydrology Problems

Recurrent Neural Network Based Approach for Solving Groundwater Hydrology Problems Universidade de São Paulo Biblioteca Digital da Produção Intelectual - BDPI Departamento de Engenharia Elétrica - EESC/SEL Livros e Capítulos de Livros - EESC/SEL 2013 Recurrent Neural Network Based Approach

More information

Application of Artificial Neural Networks Model as Analytical Tool for Groundwater Salinity

Application of Artificial Neural Networks Model as Analytical Tool for Groundwater Salinity Journal of Environmental Protection, 2011, 2, 56-71 doi:10.4236/jep.2011.21006 Published Online March 2011 (http://www.scirp.org/journal/jep) Application of Artificial Neural Networks Model as Analytical

More information

Long-term Peak Load Forecasting Using LM- Feedforward Neural Network for Java-Madura-Bali Interconnection, Indonesia

Long-term Peak Load Forecasting Using LM- Feedforward Neural Network for Java-Madura-Bali Interconnection, Indonesia Long-term Peak Load Forecasting Using LM- Feedforward Neural Network for Java-Madura-Bali Interconnection, Indonesia Yusak Tanoto* 1, Weerakorn Ongsakul +, and Charles O.P. Marpaung + Abstract This paper

More information

Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm

Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm Journal of Optimization in Industrial Engineering 13 (2013) 49-54 Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm Mohammad Saleh Meiabadi

More information

Documentation of Groundwater Agent-based Model

Documentation of Groundwater Agent-based Model Documentation of Groundwater Agent-based Model Comments or suggestions to 1. Introduction In environmental resources management there is the recognition of need for combined socio-environmental

More information

MODELLING THE GROUNDWATER FLOW FOR ESTIMATING THE PUMPING COST OF IRRIGATION IN THE AQUIFER OF N. MOUDANIA, GREECE

MODELLING THE GROUNDWATER FLOW FOR ESTIMATING THE PUMPING COST OF IRRIGATION IN THE AQUIFER OF N. MOUDANIA, GREECE Proceedings of the 13 th International Conference on Environmental Science and Technology Athens, Greece, 5-7 September 2013 MODELLING THE GROUNDWATER FLOW FOR ESTIMATING THE PUMPING COST OF IRRIGATION

More information

Management Science Letters

Management Science Letters Management Science Letters 4 (2014) 2057 2064 Contents lists available at GrowingScience Management Science Letters homepage: www.growingscience.com/msl Predicting product life cycle using fuzzy neural

More information

Using Artificial Neural Networks for the construction of contour maps of thermal conductivity

Using Artificial Neural Networks for the construction of contour maps of thermal conductivity Using Artificial Neural Networks for the construction of contour maps of thermal conductivity SOTERIS A. KALOGIROU, PAUL CHRISTODOULIDES, GEORGIOS A. FLORIDES, PANAYIOTIS D. POULOUPATIS, IOSIFINA IOSIF-STYLIANOU*

More information

Wastewater Effluent Flow Control Using Multilayer Neural Networks

Wastewater Effluent Flow Control Using Multilayer Neural Networks Wastewater Effluent Flow Control Using Multilayer Neural Networks Heidar A. Malki University of Houston 304 Technology Building Houston, TX 77204-4022 malki@uh.edu Shayan Mirabi University of Houston 304

More information

Modeling of Rainfall-Runoff by Artificial Neural Network for Micro Hydro Power Plant: A Case Study in Cameroon

Modeling of Rainfall-Runoff by Artificial Neural Network for Micro Hydro Power Plant: A Case Study in Cameroon Modeling of Rainfall-Runoff by Artificial Neural Network for Micro Hydro Power Plant: A Case Study in Cameroon Kengne Signe Elie Bertrand (1&2)*, O. Hamandjoda 1, Fanyep Nana Antoine 2, Gubong Takam Charles

More information

INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCES Volume 2, No 3, Copyright 2010 All rights reserved Integrated Publishing Association

INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCES Volume 2, No 3, Copyright 2010 All rights reserved Integrated Publishing Association INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCES Volume 2, No 3, 2012 Copyright 2010 All rights reserved Integrated Publishing Association Research article ISSN 0976 4402 Multilayer perceptron modeling

More information

Asian Research Consortium

Asian Research Consortium Asian Research Consortium Asian Journal of Research in Social Sciences and Humanities Vol. 6, No. 11, November 2016, pp. 26-40. Asian Journal of Research in Social Sciences and Humanities ISSN 2249-7315

More information

Artificial Neural Network Model Prediction of Glucose by Enzymatic Hydrolysis of Rice Straw

Artificial Neural Network Model Prediction of Glucose by Enzymatic Hydrolysis of Rice Straw Journal of Engineering Science, Vol. 10, 85 94, 2014 Artificial Neural Network Model Prediction of Glucose by Enzymatic Hydrolysis of Rice Straw Erniza Mohd Johan Jaya, Nur Atiqah Norhalim and Zainal Ahmad

More information

Domestic water demand forecasting for Makkah, Saudi Arabia

Domestic water demand forecasting for Makkah, Saudi Arabia European Water 58: 481-487, 2017. 2017 E.W. Publications Domestic water demand forecasting for Makkah, Saudi Arabia M.F.M. Abushammala 1* and A.K. Bawazir 2 1 Department of Civil Engineering, Middle East

More information

Study on strength parameters of steel fiber reinforced high. strength concrete

Study on strength parameters of steel fiber reinforced high. strength concrete www.ijaser.com 2012 by the authors Licensee IJASER- Under Creative Commons License 3.0 editorial@ijaser.com Research article ISSN 2277 9442 Study on strength parameters of steel fiber reinforced high strength

More information

Genetic Algorithm based Simulation Optimization Approach to Seawater Intrusion

Genetic Algorithm based Simulation Optimization Approach to Seawater Intrusion International Symposium on Genetic Algorithm based Simulation Optimization Approach to Seawater Intrusion 1313 Integrated Water Resources Management (IWRM 2014) February 19 21, 2014, CWRDM, Kozhikode,

More information

Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand

Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand Emrah Dogan, a Asude Ates, b Ece Ceren Yilmaz, b Beytullah Eren b a Department of Civil

More information

Projection of future availability of teak wood from forest plantations and its prices in Kerala State, India

Projection of future availability of teak wood from forest plantations and its prices in Kerala State, India Projection of future availability of teak wood from forest plantations and its prices in Kerala State, India M.Sivaram Statistics Discipline Division of Forest Information Management System Kerala Forest

More information

CHAPTER 8 ARTIFICIAL NEURAL NETWORKS

CHAPTER 8 ARTIFICIAL NEURAL NETWORKS 247 CHAPTER 8 ARTIFICIAL NEURAL NETWORKS 8.1 GENERAL Artificial neural networks are biologically inspired and they are composed of elements that perform in a manner that is analogous to the most elementary

More information

Artificial Neural Network Modeling of an Inverse Fluidized Bed Bioreactor *RAJASIMMAN, M, GOVINDARAJAN, L, KARTHIKEYAN, C

Artificial Neural Network Modeling of an Inverse Fluidized Bed Bioreactor *RAJASIMMAN, M, GOVINDARAJAN, L, KARTHIKEYAN, C JASEM ISSN 1119-8362 All rights reserved Full-text Available Online at www.bioline.org.br/ja J. Appl. Sci. Environ. Manage. June, 27 Vol. 11 (2) 65-69 Artificial Neural Network Modeling of an Inverse Fluidized

More information

Application of Legendre Neural Network for Air Quality Prediction

Application of Legendre Neural Network for Air Quality Prediction The 5 th PSU-UNS International Conference on Engineering and Technology (ICET-211), Phuket, May 2-3, 211 Prince of Songkla University, Faculty of Engineering Hat Yai, Songkhla, Thailand 9112 Application

More information

Neural Network Modeling and HDP for Neutralized ph Value Control in the Clarifying Process of Sugar Cane Juice

Neural Network Modeling and HDP for Neutralized ph Value Control in the Clarifying Process of Sugar Cane Juice Neural Network Modeling and HDP for Neutralized ph Value Control in the Clarifying Process of Sugar Cane Juice Xiaofeng Lin, Shengyong Lei and Huixia Liu Abstract Neutralizing ph value of sugar cane juice

More information

Using groundwater flow simulation of the Chania Plain area to propose a proper irrigation plan

Using groundwater flow simulation of the Chania Plain area to propose a proper irrigation plan European Water 57: 467-473, 2017. 2017 E.W. Publications Using groundwater flow simulation of the Chania Plain area to propose a proper irrigation plan C. Goumas 1, Z. Dokou 1, G.G. Morianou 1, N.N. Kourgialas

More information

Prediction of Groundwater Levels Using Artificial Neural Network: A Case Study of Gandhinagar and Kalol Taluka

Prediction of Groundwater Levels Using Artificial Neural Network: A Case Study of Gandhinagar and Kalol Taluka Prediction of Groundwater Levels Using Artificial Neural Network: A Case Study of Gandhinagar and Kalol Taluka Kaushal C. Raval 1, Dr.Falguni Parekh 2 P.G. Student, Water Resources Engineering and Management

More information

A Mirsepassi: Application of Chemical Dosage Alum, Polymer Lime, Chlorine Mixers Chemical Dosage Chlorine, Fluoride Carbon dioxide, Lime Filter Media

A Mirsepassi: Application of Chemical Dosage Alum, Polymer Lime, Chlorine Mixers Chemical Dosage Chlorine, Fluoride Carbon dioxide, Lime Filter Media Iranian J Env Health Sci Eng, 2004, Iranian Vol.1, No.2, J Env pp.51-57 Health Sci Eng, 2004, Vol.1, No.2, pp.51-57 Application of Intelligent System for Water Treatment Plant Operation *A Mirsepassi Dept.

More information

Forecasting of Groundwater Level using Artificial Neural Network by incorporating river recharge and river bank infiltration

Forecasting of Groundwater Level using Artificial Neural Network by incorporating river recharge and river bank infiltration Forecasting of Groundwater Level using Artificial Neural Network by incorporating river recharge and river bank infiltration Mohd Khairul Nizar Shamsuddin 1,*, Faradiella Mohd Kusin 2, Wan Nor Azmin Sulaiman

More information

Research Review and Modeling of Concrete Compressive Strength Using Artificial Neural Networks

Research Review and Modeling of Concrete Compressive Strength Using Artificial Neural Networks Research Review and Modeling of Concrete Compressive Strength Using Artificial Neural Networks Geet Kalra Undergraduate Student, Department of Civil Engineering 6021, New Academic Block, Birla Institute

More information

Research Article An Inventory Controlled Supply Chain Model Based on Improved BP Neural Network

Research Article An Inventory Controlled Supply Chain Model Based on Improved BP Neural Network Discrete Dynamics in Nature and Society Volume 2013, Article ID 537675, 7 pages http://dx.doi.org/10.1155/2013/537675 Research Article An Inventory Controlled Supply Chain Model Based on Improved BP Neural

More information

The prediction of electric energy consumption using an artificial neural network

The prediction of electric energy consumption using an artificial neural network Energy Production and Management in the 21st Century, Vol. 1 109 The prediction of electric energy consumption using an artificial neural network I. Chernykh 1, D. Chechushkov 1 & T. Panikovskaya 2 1 Department

More information

RAINFALL - RUNOFF MODELING IN AN EXPERIMENTAL WATERSHED IN GREECE

RAINFALL - RUNOFF MODELING IN AN EXPERIMENTAL WATERSHED IN GREECE Proceedings of the 14 th International Conference on Environmental Science and Technology Rhodes, Greece, 3-5 September 2015 RAINFALL - RUNOFF MODELING IN AN EXPERIMENTAL WATERSHED IN GREECE KOTSIFAKIS

More information

SHORT-TERM FORECASTING OF ELECTRICITY CONSUMPTION IN PALESTINE USING ARTIFICIAL NEURAL NETWORKS

SHORT-TERM FORECASTING OF ELECTRICITY CONSUMPTION IN PALESTINE USING ARTIFICIAL NEURAL NETWORKS SHORT-TERM FORECASTING OF ELECTRICITY CONSUMPTION IN PALESTINE USING ARTIFICIAL NEURAL NETWORKS Shorouq Salahat 1 and Mohammad Awad 2 1 Master Students in Faculty of Engineering and Information Technology,

More information

Comparison of Artificial Neural Networks ANN and Statistica in Daily Flow Forecasting

Comparison of Artificial Neural Networks ANN and Statistica in Daily Flow Forecasting Advances in Environmental Biology, 6(2): 863-868, 2012 ISSN 1995-0756 863 This is a refereed journal and all articles are professionally screened and reviewed ORIGINAL ARTICLE Comparison of Artificial

More information

Artificial Neural Networks Modelling for Monitoring and Performance Analysis of a Heat and Power Plant

Artificial Neural Networks Modelling for Monitoring and Performance Analysis of a Heat and Power Plant ISRN LUTMDN/TMHP 06/5084 SE ISSN 0282-1990 Artificial Neural Networks Modelling for Monitoring and Performance Analysis of a Heat and Power Plant Mehrzad Kaiadi Thesis for the Degree of Master of Science

More information

Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN)

Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN) Publication date: 18 October 2009, http://www.biosciences.elewa.org/; ISSN 2071-7024 Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN) Özbek F. Ş.

More information

CHAPTER 5 IMPROVING ON TIME, IN FULL DELIVERY

CHAPTER 5 IMPROVING ON TIME, IN FULL DELIVERY 70 CHAPTER 5 IMPROVING ON TIME, IN FULL DELIVERY 5.1 INTRODUCTION The orders which are not yet shipped or invoiced to customer are called backlog orders. The various reasons for accumulation of stock,

More information

Effect of Conjunctive Use of Water for Paddy Field Irrigation on Groundwater Budget in an Alluvial Fan ABSTRACT

Effect of Conjunctive Use of Water for Paddy Field Irrigation on Groundwater Budget in an Alluvial Fan ABSTRACT 1 Effect of Conjunctive Use of Water for Paddy Field Irrigation on Groundwater Budget in an Alluvial Fan Ali M. Elhassan (1), A. Goto (2), M. Mizutani (2) (1) New Mexico Interstate Stream Commission, P.

More information

Research on the Improved Back Propagation Neural Network for the Aquaculture Water Quality Prediction

Research on the Improved Back Propagation Neural Network for the Aquaculture Water Quality Prediction Journal of Advanced Agricultural Technologies Vol. 3, No. 4, December 2016 Research on the Improved Back Propagation Neural Network for the Aquaculture Water Quality Prediction Ding Jin-ting and Zang Ze-lin

More information

Genetic Programming: Efficient Modeling Tool in Hydrology and Groundwater Management

Genetic Programming: Efficient Modeling Tool in Hydrology and Groundwater Management Chapter 10 Genetic Programming: Efficient Modeling Tool in Hydrology and Groundwater Management J. Sreekanth and Bithin Datta Additional information is available at the end of the chapter http://dx.doi.org/10.5772/52102

More information

Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform

Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform Electrical and Electronic Engineering 2018, 8(2): 37-52 DOI: 10.5923/j.eee.20180802.02 Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform Kamran Rahimimoghadam

More information

PCA and SOM based Dimension Reduction Techniques for Quaternary Protein Structure Prediction

PCA and SOM based Dimension Reduction Techniques for Quaternary Protein Structure Prediction PCA and SOM based Dimension Reduction Techniques for Quaternary Protein Structure Prediction Sanyukta Chetia Department of Electronics and Communication Engineering, Gauhati University-781014, Guwahati,

More information

The Use of a Neural Network Technique for the Prediction of Water Quality Parameters of Axios River in Northern Greece

The Use of a Neural Network Technique for the Prediction of Water Quality Parameters of Axios River in Northern Greece European Water 11/12: 55-62, 2005. 2005 E.W. Publications The Use of a Neural Network Technique for the Prediction of Water Quality Parameters of Axios River in Northern Greece M. J. Diamantopoulou 1,

More information

MULTI-LAYER MESH APPROXIMATION OF INTEGRATED HYDROLOGICAL MODELING FOR WATERSHEDS: THE CASE OF THE YASU RIVER BASIN

MULTI-LAYER MESH APPROXIMATION OF INTEGRATED HYDROLOGICAL MODELING FOR WATERSHEDS: THE CASE OF THE YASU RIVER BASIN MULTI-LAYER MESH APPROXIMATION OF INTEGRATED HYDROLOGICAL MODELING FOR WATERSHEDS: THE CASE OF THE YASU RIVER BASIN Toshiharu KOJIRI and Amin NAWAHDA 1 ABSTRACT A method for applying the multi-layer mesh

More information

COMPARISON BETWEEN NEURAL NETWORKS AND MULTIPLE REGRESSION METHODS IN METALLURGICAL PERFORMANCE MODELING OF FLOTATION COLUMN

COMPARISON BETWEEN NEURAL NETWORKS AND MULTIPLE REGRESSION METHODS IN METALLURGICAL PERFORMANCE MODELING OF FLOTATION COLUMN Physicochem. Probl. Miner. Process. 49(1), 2013, 255 266 www.minproc.pwr.wroc.pl/journal/ Physicochemical Problems of Mineral Processing ISSN 1643-1049 (print) ISSN 2084-4735 (online) Received May 15,

More information

The Bankruptcy Prediction by Neural Networks and Logistic Regression

The Bankruptcy Prediction by Neural Networks and Logistic Regression Vol. 3, No. 4, October 2013, pp. 146 152 E-ISSN: 2225-8329, P-ISSN: 2308-0337 2013 HRMARS www.hrmars.com The Bankruptcy Prediction by Neural Networks and Logistic Regression Ahmad Ahmadpour KASGARI 1 Seyyed

More information

Groundwater Level Forecasting in a Shallow Aquifer Using Artificial Neural Network Approach

Groundwater Level Forecasting in a Shallow Aquifer Using Artificial Neural Network Approach Water Resources Management (2006) 20: 77 90 DOI: 10.1007/s11269-006-4007-z C Springer 2006 Groundwater Level Forecasting in a Shallow Aquifer Using Artificial Neural Network Approach PURNA C. NAYAK 1,,Y.R.SATYAJIRAO

More information

Neural networks application in an AISI 304L intergranular corrosion resistance analysis

Neural networks application in an AISI 304L intergranular corrosion resistance analysis T3-025 1 Neural networks application in an AISI 304L intergranular corrosion resistance analysis D. IACOVIELLO, F. IACOVIELLO and M. MACARIO Abstract Multi-Layer-Perceptron (MLP) neural network is here

More information

Modeling of Steam Turbine Combined Cycle Power Plant Based on Soft Computing

Modeling of Steam Turbine Combined Cycle Power Plant Based on Soft Computing Modeling of Steam Turbine Combined Cycle Power Plant Based on Soft Computing ALI GHAFFARI, ALI CHAIBAKHSH, ALI MOSTAFAVI MANESH Department of Mechanical Engineering, department of Mechanical Engineering,

More information

Inflow forecasting using Artificial Neural Networks for reservoir operation

Inflow forecasting using Artificial Neural Networks for reservoir operation Proc IAHS, 373, 29 214, 216 proc-iahsnet/373/29/216/ doi:15194/piahs-373-29-216 Author(s) 216 CC Attribution 3 License Inflow forecasting using Artificial Neural Networks for reservoir operation Chuthamat

More information

Short-term electricity price forecasting in deregulated markets using artificial neural network

Short-term electricity price forecasting in deregulated markets using artificial neural network Proceedings of the 2011 International Conference on Industrial Engineering and Operations Management Kuala Lumpur, Malaysia, January 22 24, 2011 Short-term electricity price forecasting in deregulated

More information

Numerical Groundwater Model for the Kaweah Delta Water Conservation District

Numerical Groundwater Model for the Kaweah Delta Water Conservation District Numerical Groundwater Model for the Kaweah Delta Water Conservation District Nels Ruud and Peter Leffler Fugro West, Inc. Larry Dotson Kaweah Delta Water Conservation District Presentation Outline Background

More information

ADAPTIVE NEURO FUZZY INFERENCE SYSTEM FOR MONTHLY GROUNDWATER LEVEL PREDICTION IN AMARAVATHI RIVER MINOR BASIN

ADAPTIVE NEURO FUZZY INFERENCE SYSTEM FOR MONTHLY GROUNDWATER LEVEL PREDICTION IN AMARAVATHI RIVER MINOR BASIN 3 st October 24. Vol. 68 No.3 25-24 JATIT & LLS. All rights reserved. ADAPTIVE NEURO FUZZY INFEREN SYSTEM FOR MONTHLY GROUNDWATER LEVEL PREDICTION IN AMARAVATHI RIVER MINOR BASIN G. R. UMAMAHESWARI, 2

More information