SlideShare ist ein Scribd-Unternehmen logo
1 von 5
Downloaden Sie, um offline zu lesen
ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011
© 2011 ACEE 31
DOI:01.IJCEE.01.01.517
EstimationofWeeklyReferenceEvapotranspiration
using
LinearRegressionandANN Models
K.Chandra Sekhar Reddy1
, S.Aruna Jyothy2
, and P.Mallikarjuna3
1
N.B.K.R.I.S.T., Department of Civil Engineering, Vidyanagar,Andhra Pradesh, India.
Email: vinod_harsha@yahoo.co.in
2
Sri Venkateswara University, Department of Civil Engineering, Tirupati, India
Email: aruna_jyothy@yahoo.co.in
3
Sri Venkateswara University, Department of Civil Engineering, Tirupati, India
Email : mallikarjuna_perugu@yahoo.co.in
Abstract— The study investigates the applicability of linear
regression and ANN models for estimating weekly reference
evapotranspiration (ET0
) at Tirupati, Nellore, Rajahmundry,
Anakapalli and Rajendranagar regions of Andhra Pradesh.
The climatic parameters influencing ET0
were identified
through multiple and partial correlation analysis. The
sunshine, temperature, wind velocity and relative humidity
mostly influenced the study area in the weekly ET0
estimation.
Linear regression models in terms of the climatic parameters
influencing the regions and, optimal neural network
architectures considering these climatic parameters as inputs
were developed. The models’ performance was evaluated with
respect to ET0
estimated by FAO-56 Penman-Monteith method.
The linear regression models showed a satisfactory
performance in the weekly ET0
estimation in the regions
selected for the present study. The ANN (4,4,1) models,
however, consistently showed a slightly improved performance
over linear regression models.
Index Terms—Reference evapotranspiration, multiple linear
regression, artificial neural network, performance evaluation
I. INTRODUCTION
An accurate estimation of reference crop
evapotranspiration (ET0
) is of paramount importance for
designing irrigation systems and managing natural water
resources. Numerous ET0
equations have been developed
and used according to the availabilityof historical and current
weather data. These equations range in sophistication from
empirical to complex equations. The FAO-56 Penman-
Monteith (PM) equation [1] is widelyused in recent times for
ET0
estimation. However, the difficultyin using this equation,
in general, is the lack of accurate and complete data. In
addition, the parameters in the equation potentiallyintroduce
certain amount of measurement and/or computational errors,
resulting in cumulative errors in ET0
estimates. Under these
conditions, a simple empirical equation that requires as few
parameters as possible and, results comparable with Penman-
Monteith method is preferable. Owing to the difficulties
associated with model structure identification and parameter
estimation of the nonlinear complex evapotranspiration
process, most of the models that have been developed may
not yield satisfactoryresults. ANNs are capable of modelling
complex nonlinear processeseffectivelyextracting the relation
between the inputs and outputs of a process without the
physics being explicitly provided to them and also, they
identify the underlying rule even if the data is noisy and
contaminated with errors [2] and [3]. “Reference [4]”
investigated the utility of ANNs for the estimation of daily
ET0
andcompared theperformanceofANNs with PMmethod.
It was concluded that ANNs can predict ET0
better than the
conventional methods. “Reference [5]” examined thepotential
of artificial neural networks in estimating the actual
evapotranspiration from limited climatic data and suggested
that the crop evapotranspiration could be computed from air
temperature using theANN approach. “Reference [6]” showed
thatANNs can be used for forecasting ET0
with high reliability.
“Reference [7]” derived solar radiation and net radiation
based ET0
equations using multi- linear regression technique
and concluded that the equations performed better than the
simplified temperature and/or radiation based methods for
humid climates. “Reference [8]” tested the ANNs for
estimating ET0
as a function of maximum and minimum air
temperatures and concluded that when taking into account
just themaximum andminimum air temperatures, it ispossible
toestimate ET0
. “Reference [9]” tested theANNs, to estimate
ET0
as a function of the maximum and minimum air
temperatures in semiarid climate. While comparing with PM
method, it was concluded that ANN methods are better for
ET0
estimates than the conventional methods. “Reference
[10]” evaluated ANN models for daily ET0
estimation under
situations of presence of only temperature and relative
humiditydata. ANNs showed an improved performance over
traditional ET0
equations. “Reference [11]” developed
generalized artificial neural network (GANN) basedreference
crop evapotranspiration models corresponding to FAO-56
PM, FAO-24 Radiation, Turc and FAO-24 Blaney-Criddle
methodsusing the data from California Irrigation Management
and Information System stations. It was concluded that the
GANN models can be used directlyto predict ET0
under the
arid conditions since they performed better than the
conventional ET0
estimation methods. “Reference [12]”
compared weekly evapotranspiration ANN based forecasts
with regard to a model based on weeklyaverages and found
an improved performance of one week in advance weekly
ET0
predictions compared tothe model based on means (mean
year model).
ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011
© 2011 ACEE 32
DOI:01.IJCEE.01.01.517
II. MATERIALSANDMETHODS
The climatic data at Tirupati, Nellore, Rajahmundry,
Anakapalli and Rajendranagar meteorological centers
collected from the India Meteorological Department (IMD),
Pune, India were used in the data analysis and model
development. A part of the data was used for the purpose of
development ofmodels and the rest for validating the models
developed. The resemblance of the statistical structure in
terms of mean, variance and skewness of the calibration and
validation data sets was ensured while making the division
of the data into training and testing data sets. A brief
description ofthe meteorological centers along with the data
period is shown in TABLE I. In the present study, an attempt
is made to develop simple linear and optimal neural network
models considering the climatic parameters influencing the
regions selected for the studyfor weeklyET0
estimation. The
study also compares the performance of proposed linear
regression and ANN models.
III.MODELDEVELOPMENT
The weekly reference evapotranspiration model at a
meteorological center is developed using the climatic data at
the center. The steps in the modelling include i) identification
of meteorological parameters influencing the region, ii)
development of the model and iii) performance evaluation of
the model developed. The identification of meteorological
parameters influencing the region is based on multiple and
partial correlation analysis. The linear regression and ANN
models are developed for the present study. The performance
of the models is verified through selected performance
evaluation criteria.
A. Linear Regression (LR) model
The objective of the model is the transfer of information
among several variables observed simultaneously and the
estimation of the dependent variable from the several other
observed independent variables.
The weekly reference evapotranspiration (ET0
) at a
meteorological center is expressed as a simple linear model
as
ET0
=C + a1
X1
+ a2
X2
+… (1)
where a1
,a2
,…… and C are empirical constants and X1
,X2
,….
are the meteorological parameters influencing the region. The
multiplecorrelation analysis was carried out usingSTASTICA
package.
B. Artificial Neural Network model (ANN)
A standard multilayer feed-forward ANN with logistic
sigmoid function was adopted for the present study. A
constant value of0.1 for learning rate and a constant value of
0.9 for momentum factor were considered. The data were
normalized in the range of (0.1, 0.9) to avoid anysaturation
effect. Error back propagation which is an iterative nonlinear
optimization approach based on the gradient descent search
method [13] was used during calibration. The calibration set
was used to minimize the error and validation set was used to
ensure proper training of the neural network employed such
that it does not get overtrained. The performance of the model
was checked for its improvement on each iteration to avoid
overlearning. The optimal network corresponding tominimum
mean squared error was obtained through trail and error
process. Care was taken to avoid too few and too many
neurons which can respectivelycause difficulties in mapping
each input and output in the training set and increase training
time unnecessarily, in the process ofdetermination ofoptimal
number of hidden layers and nodes in each hidden layer. The
process was carried out using MATLAB routines.
IV.PERFORMANCE EVALUATIONCRITERIA
The performance evaluation criteria used in the present
study are the coefficient of determination (R2
), root mean
square error (RMSE) and efficiency coefficient (EC).
TABLE I.
BRIEF DESCRIPTION OF METEOROLOGICAL CENTERS
A. Coefficient of Determination (R2
)
It is the square of the correlation coefficient (R) and the
correlation coefficient is expressed as
where yi
and iyˆ are the observed and estimated values
respectively and, y and iyˆ are the means of observed and
estimated values and n is the number of observations. It
measures the degree of association between the observed
and estimated values and indicates the relative assessment
of the model performance in dimensionless measure.
ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011
© 2011 ACEE 33
DOI:01.IJCEE.01.01.517
B. Root Mean Square Error (RMSE)
It yields the residual error in terms ofthe mean square error
and is expressed as [14].
RMSE=
n
yy ii
n
i
2
1
)ˆ(  (3)
C. Efficiency Coefficient (EC)
It is used to assess the performance of different models [15].
It is a better choice than RMSE statistic when the calibration
and verification periods have different lengths [16]. It
measures directly the ability of the model to reproduce the
observed values and is expressed as
EC = 1001
0







F
F
(4)
where F0
=
2
1
)( yyi
n
i

and F =
2
1
)ˆ( ii
n
i
yy 
A value of EC of 90% generally indicates a verysatisfactory
model performance while a value in therange80-90%, a fairly
good model. Values ofEC in the range 60-80% would indicate
an unsatisfactorymodel fit.
V.RESULTSANDDISCUSSION
The multiple correlation analysis has been carried out to
identifythe climatic parameters influencing weeklyET0
in the
regions selected for the study. It may be observed from
multiple and partial correlation coefficients presented in
TABLE II that the sunshine hours, temperature, wind velocity
and relative humidity mostly influence the regions in the
weeklyET0
estimation. Linear weeklyET0
regression models
at the centers have been developed as presented in TABLE
III. The weeklyET0
estimation at the meteorological centers
has also been carried out using different artificial neural
network architectures with input nodes ranging from one to
four and, varying the number of nodes in the hidden layer.
The ANNs with four input nodes and a hidden layer with
four nodes i.e. ANN (4,4,1) have been identified as optimal
architectures. The performance indices of linear regression
(LR) and ANN (4,4,1) models on comparison of the results
with those ofFAO-56 Penman-Montieth method arepresented
in TABLE IV. It maybe observed from the results presented
inTABLE IVthat thevaluesofR2
andECofLRmodelsindicate
a very satisfactory performance. However, the performance
hasimproved marginallywith optimal artificial neural network
architectures.
TABLE II
MULTIPLE AND PARTIAL CORRELATION COEFFICIENTS
TABLE III
LINEAR REGRESSION MODELS
ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011
© 2011 ACEE 34
DOI:01.IJCEE.01.01.517
TABLE IV
PERFORMANCE INDICES OF LR AND ANN (4,4.1) MODELS
The values ofRMSE ofANN(4,4,1) models have alsoreduced
slightly. This maybe due to the fact that weekly average ET0
values do not exhibit much of nonlinearity. The scatter plots
(not shown in the paper) of ET0
values estimated using
Penman-Montieth method against those estimated using LR
and ANN (4,4,1) models respectively. The nearly unit slope
and zero intercept of scatter plots (TABLE IV) indicate the
closeness of ET0
values with those of PM method. “Fig. 1”
presents the comparison of performance of LR and ANN
(4,4,1) models against PM method during testing period. The
study reveals that the simple linear regression models
proposed may be adopted satisfactorily in the weekly ET0
estimation at the centers selected for the present study and,
the accuracy in the ET0
estimation may further be improved
usingANN (4,4,1) models.
VI.CONCLUSIONS
The climatic parameters such as sunshine hours,
temperature, wind velocity and relative humidity mostly
influenced weekly ET0
estimation at Tirupati, Nellore,
Rajahmundry, Anakapalli and Rajendranagar regions of
Andhra Pradesh. The linear regression models proposed in
terms of the climatic parameters influencing the regions
performed satisfactorily in the weekly ET0
estimation. The
optimal ANN models proposed showed a marginal
improvement over linear regression models. The linear
regression models may therefore be adopted for weekly ET0
estimation in the regions with reasonable degree of accuracy
and, the accuracy may slightly be improved with ANN
architectures.
Figure 1. Comparison of average weekly ETO
values estimated using LR and ANN models with those estimated by
Penman-Monteith method during testing period
ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011
© 2011 ACEE 35
DOI:01.IJCEE.01.01.517
REFERENCES
[1] R. G. Allen, L. S Pereira, D. Raes, and M.Smith, “Crop
Evapotranspiration Guidelines for Computing Crop Water
Requirements.” FAO Irrigation and Drainage Paper 56, FAO,
Rome, 1998.
[2] ASCE Task Committee on Application of Artificial Neural
Networks in Hydrology. “Artificial Neural Networks in
Hydrology. I: Preliminary concepts.” J. Hydrol. Eng., 5(2),
pp. 115-123, 2000a.
[3] ASCE Task Committee on Application of Artificial Neural
Networks in Hydrology.”Artificial Neural Networks in
Hydrology. II: Hydrologic applications.” J. Hydrol. Eng.,
5(2), pp. 124-137, 2000b.
[4] M. Kumar, N. S. Raghuwanshi, R. Singh, W. W.Wallender, and
W. O. Pruitt. “Estimating Evapotranspiration using Artificial
Neural Network.” J. Irrig. Drain. Eng., 128(4), pp. 224-233,
2002.
[5] K. P. Sudheer, A. K. Gosain, and K. S. Ramasastri, “Estimating
Actual Evapotranspiration from Limited Climatic Data using
Neural Computing Technique.” J. Irrig. Drain. Eng., 129(3),
pp. 214-218, 2003.
[6] S. Trajkovic, B.Todorovic, and M. Stankovic, “Forecasting of
Reference Evapotranspiration by Artificial Neural Networks.”
J. Irrig. Drain. Eng., 129(6), pp.454-457, 2003.
[7] S. Irmak, A. Irmak, R. G. Allen, and J. W. Jones, “Solar and Net
Radiation-Based Equations to Estimate Reference
Evapotranspiration in Humid Climates.” J. Irrig. Drain. Eng.
129(5), pp.336-347, 2003.
[8] S. S.Zanetti, E. F. Sousa, V. P. S.Oliveira, F. T.Almeida, and S.
Bernardo,”Estimating Evapotranspiration using Artificial
Neural Network and Minimum Climatological Data.” J. Irrig.
Drain. Eng., 133(2), 83-89, 2007.
[9]A.R. Khoob, “ArtificialNeural Network Estimation of Reference
Evapotranspiration from Pan Evaporation in a Semi-Arid
Environment.” J. Irrig. Sci., 27(1), pp.35-39, 2008.
[10] G. Landeras, A. O. Barredo, and J. J. Lopez, “Comparison of
Artificial Neural Network Models and Empirical and Semi-
Empirical Equations for Daily Reference Evapotranspiration
Estimation in the Basque Country (Northern
Spain).”Agricultural Water Management, 95(5), pp. 553-565,
2008.
[11] M. Kumar, N. S. Raghuwanshi and R. Singh, “Development
and Validation of GANN model for Evapotranspiration
Estimation.” J. Hydrol. Eng., 14(2), pp.131- 140, 2009.
[12] G. Landeras, A. O. Barredo, and J. J. Lopez. “Forecasting
Weekly Evapotranspiration with
ARIMA and Artificial Neural Network Models.” J. Irrig.
Drain. Eng., 135(3), pp.323-334, 2009..
[13] D. E. Rumelhart, G. E.Hinton, and R. J. Williams. “Learning
Internal Representations by Error Propagation.” Parallel
Distributed Processing, MIT press, Cambridge, MA, 1, pp.
318-362, 1986.
[14] P. S Yu., C. L Liu and T. Y. Lee, “Application of Transfer
Function Model to a Storage Runoff Process.” Stochastic and
Statistical Methods in Hydrology and Environmental
Engineering, 3, pp. 87 – 97, 1994.
[15] J. E. Nash, and J.V. Sutcliffe, “River Flow Forecasting Through
Conceptual Models- I: A Discussion of Principles.” J. Hydrol.,
10(3), pp. 282-290, 1970.
[16] G. C. Liang, O. Connor, and R. K. Kachroo, “A Multiple-
Input Single-Output Varia R. K. Ble gain Model.” J. Hydrol.,
155(1-2), pp. 185-198, 1994.

Weitere ähnliche Inhalte

Was ist angesagt?

Bulk power system availability assessment with multiple wind power plants
Bulk power system availability assessment with multiple wind power plants Bulk power system availability assessment with multiple wind power plants
Bulk power system availability assessment with multiple wind power plants IJECEIAES
 
Power system transient stability margin estimation using artificial neural ne...
Power system transient stability margin estimation using artificial neural ne...Power system transient stability margin estimation using artificial neural ne...
Power system transient stability margin estimation using artificial neural ne...elelijjournal
 
Optimum capacity allocation of distributed generation units using parallel ps...
Optimum capacity allocation of distributed generation units using parallel ps...Optimum capacity allocation of distributed generation units using parallel ps...
Optimum capacity allocation of distributed generation units using parallel ps...eSAT Journals
 
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural NetworksSolar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural NetworksIJECEIAES
 
Performance comparison of distributed generation installation arrangement in ...
Performance comparison of distributed generation installation arrangement in ...Performance comparison of distributed generation installation arrangement in ...
Performance comparison of distributed generation installation arrangement in ...journalBEEI
 
Short Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural NetworkShort Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural NetworkIJERA Editor
 
Power System State Estimation - A Review
Power System State Estimation - A ReviewPower System State Estimation - A Review
Power System State Estimation - A ReviewIDES Editor
 
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET Journal
 
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET Journal
 
Optimum capacity allocation of distributed generation
Optimum capacity allocation of distributed generationOptimum capacity allocation of distributed generation
Optimum capacity allocation of distributed generationeSAT Publishing House
 
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...journalBEEI
 
Learning from data for wind–wave forecasting
Learning from data for wind–wave forecastingLearning from data for wind–wave forecasting
Learning from data for wind–wave forecastingJonathan D'Cruz
 
Study on the application of genetic algorithms in the optimization of wireles...
Study on the application of genetic algorithms in the optimization of wireles...Study on the application of genetic algorithms in the optimization of wireles...
Study on the application of genetic algorithms in the optimization of wireles...Amir Shokri
 
2018 solar energy forecasting based on hybrid neural network and improved met...
2018 solar energy forecasting based on hybrid neural network and improved met...2018 solar energy forecasting based on hybrid neural network and improved met...
2018 solar energy forecasting based on hybrid neural network and improved met...Souvik Ganguli
 
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkPresentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkArzam Muzaffar Kotriwala
 
SAIP2015 presentation_v5
SAIP2015 presentation_v5SAIP2015 presentation_v5
SAIP2015 presentation_v5Thembelani Gina
 
Optimal Siting of Distributed Generators in a Distribution Network using Arti...
Optimal Siting of Distributed Generators in a Distribution Network using Arti...Optimal Siting of Distributed Generators in a Distribution Network using Arti...
Optimal Siting of Distributed Generators in a Distribution Network using Arti...IJECEIAES
 
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...IJERA Editor
 
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...IOSRJEEE
 

Was ist angesagt? (20)

Bulk power system availability assessment with multiple wind power plants
Bulk power system availability assessment with multiple wind power plants Bulk power system availability assessment with multiple wind power plants
Bulk power system availability assessment with multiple wind power plants
 
Power system transient stability margin estimation using artificial neural ne...
Power system transient stability margin estimation using artificial neural ne...Power system transient stability margin estimation using artificial neural ne...
Power system transient stability margin estimation using artificial neural ne...
 
Optimum capacity allocation of distributed generation units using parallel ps...
Optimum capacity allocation of distributed generation units using parallel ps...Optimum capacity allocation of distributed generation units using parallel ps...
Optimum capacity allocation of distributed generation units using parallel ps...
 
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural NetworksSolar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
Solar Photovoltaic Power Forecasting in Jordan using Artificial Neural Networks
 
Performance comparison of distributed generation installation arrangement in ...
Performance comparison of distributed generation installation arrangement in ...Performance comparison of distributed generation installation arrangement in ...
Performance comparison of distributed generation installation arrangement in ...
 
Short Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural NetworkShort Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural Network
 
Power System State Estimation - A Review
Power System State Estimation - A ReviewPower System State Estimation - A Review
Power System State Estimation - A Review
 
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
 
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
IRJET- Optimal Placement and Size of DG and DER for Minimizing Power Loss and...
 
Optimum capacity allocation of distributed generation
Optimum capacity allocation of distributed generationOptimum capacity allocation of distributed generation
Optimum capacity allocation of distributed generation
 
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...
Oscillatory Stability Prediction Using PSO Based Synchronizing and Damping To...
 
Learning from data for wind–wave forecasting
Learning from data for wind–wave forecastingLearning from data for wind–wave forecasting
Learning from data for wind–wave forecasting
 
Study on the application of genetic algorithms in the optimization of wireles...
Study on the application of genetic algorithms in the optimization of wireles...Study on the application of genetic algorithms in the optimization of wireles...
Study on the application of genetic algorithms in the optimization of wireles...
 
I02095257
I02095257I02095257
I02095257
 
2018 solar energy forecasting based on hybrid neural network and improved met...
2018 solar energy forecasting based on hybrid neural network and improved met...2018 solar energy forecasting based on hybrid neural network and improved met...
2018 solar energy forecasting based on hybrid neural network and improved met...
 
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural NetworkPresentation: Wind Speed Prediction using Radial Basis Function Neural Network
Presentation: Wind Speed Prediction using Radial Basis Function Neural Network
 
SAIP2015 presentation_v5
SAIP2015 presentation_v5SAIP2015 presentation_v5
SAIP2015 presentation_v5
 
Optimal Siting of Distributed Generators in a Distribution Network using Arti...
Optimal Siting of Distributed Generators in a Distribution Network using Arti...Optimal Siting of Distributed Generators in a Distribution Network using Arti...
Optimal Siting of Distributed Generators in a Distribution Network using Arti...
 
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...
Cost Aware Expansion Planning with Renewable DGs using Particle Swarm Optimiz...
 
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...
A Comparative study on Different ANN Techniques in Wind Speed Forecasting for...
 

Andere mochten auch

Study and Development of an Energy Saving Mechanical System
Study and Development of an Energy Saving Mechanical SystemStudy and Development of an Energy Saving Mechanical System
Study and Development of an Energy Saving Mechanical SystemIDES Editor
 
Simulative study of cause-effect interdependencies in tool logistics
Simulative study of cause-effect interdependencies in tool logisticsSimulative study of cause-effect interdependencies in tool logistics
Simulative study of cause-effect interdependencies in tool logisticsIDES Editor
 
Geographic Information Systems Based Quantity Takeoffs in Buildings Construction
Geographic Information Systems Based Quantity Takeoffs in Buildings ConstructionGeographic Information Systems Based Quantity Takeoffs in Buildings Construction
Geographic Information Systems Based Quantity Takeoffs in Buildings ConstructionIDES Editor
 
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...IDES Editor
 
Overbank Flow Condition in a River Section
Overbank Flow Condition in a River SectionOverbank Flow Condition in a River Section
Overbank Flow Condition in a River SectionIDES Editor
 
FACT Aquatic biofuels for local development
FACT Aquatic biofuels for local developmentFACT Aquatic biofuels for local development
FACT Aquatic biofuels for local developmentRik Hoevers
 
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...IDES Editor
 

Andere mochten auch (7)

Study and Development of an Energy Saving Mechanical System
Study and Development of an Energy Saving Mechanical SystemStudy and Development of an Energy Saving Mechanical System
Study and Development of an Energy Saving Mechanical System
 
Simulative study of cause-effect interdependencies in tool logistics
Simulative study of cause-effect interdependencies in tool logisticsSimulative study of cause-effect interdependencies in tool logistics
Simulative study of cause-effect interdependencies in tool logistics
 
Geographic Information Systems Based Quantity Takeoffs in Buildings Construction
Geographic Information Systems Based Quantity Takeoffs in Buildings ConstructionGeographic Information Systems Based Quantity Takeoffs in Buildings Construction
Geographic Information Systems Based Quantity Takeoffs in Buildings Construction
 
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...
Environment Protection of Reserved areas – A Study of Gulf of Mannar (GOM) Bi...
 
Overbank Flow Condition in a River Section
Overbank Flow Condition in a River SectionOverbank Flow Condition in a River Section
Overbank Flow Condition in a River Section
 
FACT Aquatic biofuels for local development
FACT Aquatic biofuels for local developmentFACT Aquatic biofuels for local development
FACT Aquatic biofuels for local development
 
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...
Urban Air Quality Modelling and Simulation: A Case Study of Kolhapur (M.S.), ...
 

Ähnlich wie Estimation of Weekly Reference Evapotranspiration using Linear Regression and ANN Models

Applications of Artificial Neural Networks in Civil Engineering
Applications of Artificial Neural Networks in Civil EngineeringApplications of Artificial Neural Networks in Civil Engineering
Applications of Artificial Neural Networks in Civil EngineeringPramey Zode
 
Application Of Artificial Neural Networks In Civil Engineering
Application Of Artificial Neural Networks In Civil EngineeringApplication Of Artificial Neural Networks In Civil Engineering
Application Of Artificial Neural Networks In Civil EngineeringJanelle Martinez
 
IEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinIEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinMinchao Lin
 
The prediction of moisture through the use of neural networks MLP type
The prediction of moisture through the use of neural networks MLP typeThe prediction of moisture through the use of neural networks MLP type
The prediction of moisture through the use of neural networks MLP typeIOSR Journals
 
IRJET - Intelligent Weather Forecasting using Machine Learning Techniques
IRJET -  	  Intelligent Weather Forecasting using Machine Learning TechniquesIRJET -  	  Intelligent Weather Forecasting using Machine Learning Techniques
IRJET - Intelligent Weather Forecasting using Machine Learning TechniquesIRJET Journal
 
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...IAEME Publication
 
Sugarcane yield forecasting using
Sugarcane yield forecasting usingSugarcane yield forecasting using
Sugarcane yield forecasting usingijaia
 
Estimation of global solar radiation by using machine learning methods
Estimation of global solar radiation by using machine learning methodsEstimation of global solar radiation by using machine learning methods
Estimation of global solar radiation by using machine learning methodsmehmet şahin
 
Application of the extreme learning machine algorithm for the
Application of the extreme learning machine algorithm for theApplication of the extreme learning machine algorithm for the
Application of the extreme learning machine algorithm for themehmet şahin
 
710201911
710201911710201911
710201911IJRAT
 
Overview of soft intelligent computing technique for supercritical fluid extr...
Overview of soft intelligent computing technique for supercritical fluid extr...Overview of soft intelligent computing technique for supercritical fluid extr...
Overview of soft intelligent computing technique for supercritical fluid extr...IJAAS Team
 
710201911
710201911710201911
710201911IJRAT
 
Multi-task learning using non-linear autoregressive models and recurrent neur...
Multi-task learning using non-linear autoregressive models and recurrent neur...Multi-task learning using non-linear autoregressive models and recurrent neur...
Multi-task learning using non-linear autoregressive models and recurrent neur...IJECEIAES
 
2005年EI收录浙江财经学院论文7篇
2005年EI收录浙江财经学院论文7篇2005年EI收录浙江财经学院论文7篇
2005年EI收录浙江财经学院论文7篇butest
 
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)IRJET Journal
 

Ähnlich wie Estimation of Weekly Reference Evapotranspiration using Linear Regression and ANN Models (20)

20320140503021
2032014050302120320140503021
20320140503021
 
Applications of Artificial Neural Networks in Civil Engineering
Applications of Artificial Neural Networks in Civil EngineeringApplications of Artificial Neural Networks in Civil Engineering
Applications of Artificial Neural Networks in Civil Engineering
 
Application Of Artificial Neural Networks In Civil Engineering
Application Of Artificial Neural Networks In Civil EngineeringApplication Of Artificial Neural Networks In Civil Engineering
Application Of Artificial Neural Networks In Civil Engineering
 
20320140501002
2032014050100220320140501002
20320140501002
 
IEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao LinIEOR 265 Final Paper_Minchao Lin
IEOR 265 Final Paper_Minchao Lin
 
The prediction of moisture through the use of neural networks MLP type
The prediction of moisture through the use of neural networks MLP typeThe prediction of moisture through the use of neural networks MLP type
The prediction of moisture through the use of neural networks MLP type
 
IRJET - Intelligent Weather Forecasting using Machine Learning Techniques
IRJET -  	  Intelligent Weather Forecasting using Machine Learning TechniquesIRJET -  	  Intelligent Weather Forecasting using Machine Learning Techniques
IRJET - Intelligent Weather Forecasting using Machine Learning Techniques
 
Ae4102224236
Ae4102224236Ae4102224236
Ae4102224236
 
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...
EVALUATION OF REFERENCE EVAPOTRANSPIRATION ESTIMATION METHODS AND DEVELOPMENT...
 
Sugarcane yield forecasting using
Sugarcane yield forecasting usingSugarcane yield forecasting using
Sugarcane yield forecasting using
 
Estimation of global solar radiation by using machine learning methods
Estimation of global solar radiation by using machine learning methodsEstimation of global solar radiation by using machine learning methods
Estimation of global solar radiation by using machine learning methods
 
A1802050102
A1802050102A1802050102
A1802050102
 
Application of the extreme learning machine algorithm for the
Application of the extreme learning machine algorithm for theApplication of the extreme learning machine algorithm for the
Application of the extreme learning machine algorithm for the
 
20320140502008
2032014050200820320140502008
20320140502008
 
710201911
710201911710201911
710201911
 
Overview of soft intelligent computing technique for supercritical fluid extr...
Overview of soft intelligent computing technique for supercritical fluid extr...Overview of soft intelligent computing technique for supercritical fluid extr...
Overview of soft intelligent computing technique for supercritical fluid extr...
 
710201911
710201911710201911
710201911
 
Multi-task learning using non-linear autoregressive models and recurrent neur...
Multi-task learning using non-linear autoregressive models and recurrent neur...Multi-task learning using non-linear autoregressive models and recurrent neur...
Multi-task learning using non-linear autoregressive models and recurrent neur...
 
2005年EI收录浙江财经学院论文7篇
2005年EI收录浙江财经学院论文7篇2005年EI收录浙江财经学院论文7篇
2005年EI收录浙江财经学院论文7篇
 
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)
IRJET- Estimation the Bod of Wastewater by using the Neural Networks (ANN)
 

Mehr von IDES Editor

Artificial Intelligence Technique based Reactive Power Planning Incorporating...
Artificial Intelligence Technique based Reactive Power Planning Incorporating...Artificial Intelligence Technique based Reactive Power Planning Incorporating...
Artificial Intelligence Technique based Reactive Power Planning Incorporating...IDES Editor
 
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...IDES Editor
 
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...IDES Editor
 
Line Losses in the 14-Bus Power System Network using UPFC
Line Losses in the 14-Bus Power System Network using UPFCLine Losses in the 14-Bus Power System Network using UPFC
Line Losses in the 14-Bus Power System Network using UPFCIDES Editor
 
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...IDES Editor
 
Assessing Uncertainty of Pushover Analysis to Geometric Modeling
Assessing Uncertainty of Pushover Analysis to Geometric ModelingAssessing Uncertainty of Pushover Analysis to Geometric Modeling
Assessing Uncertainty of Pushover Analysis to Geometric ModelingIDES Editor
 
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...IDES Editor
 
Selfish Node Isolation & Incentivation using Progressive Thresholds
Selfish Node Isolation & Incentivation using Progressive ThresholdsSelfish Node Isolation & Incentivation using Progressive Thresholds
Selfish Node Isolation & Incentivation using Progressive ThresholdsIDES Editor
 
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...IDES Editor
 
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...IDES Editor
 
Cloud Security and Data Integrity with Client Accountability Framework
Cloud Security and Data Integrity with Client Accountability FrameworkCloud Security and Data Integrity with Client Accountability Framework
Cloud Security and Data Integrity with Client Accountability FrameworkIDES Editor
 
Genetic Algorithm based Layered Detection and Defense of HTTP Botnet
Genetic Algorithm based Layered Detection and Defense of HTTP BotnetGenetic Algorithm based Layered Detection and Defense of HTTP Botnet
Genetic Algorithm based Layered Detection and Defense of HTTP BotnetIDES Editor
 
Enhancing Data Storage Security in Cloud Computing Through Steganography
Enhancing Data Storage Security in Cloud Computing Through SteganographyEnhancing Data Storage Security in Cloud Computing Through Steganography
Enhancing Data Storage Security in Cloud Computing Through SteganographyIDES Editor
 
Low Energy Routing for WSN’s
Low Energy Routing for WSN’sLow Energy Routing for WSN’s
Low Energy Routing for WSN’sIDES Editor
 
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...IDES Editor
 
Rotman Lens Performance Analysis
Rotman Lens Performance AnalysisRotman Lens Performance Analysis
Rotman Lens Performance AnalysisIDES Editor
 
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral Images
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral ImagesBand Clustering for the Lossless Compression of AVIRIS Hyperspectral Images
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral ImagesIDES Editor
 
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...IDES Editor
 
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...Texture Unit based Monocular Real-world Scene Classification using SOM and KN...
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...IDES Editor
 
Mental Stress Evaluation using an Adaptive Model
Mental Stress Evaluation using an Adaptive ModelMental Stress Evaluation using an Adaptive Model
Mental Stress Evaluation using an Adaptive ModelIDES Editor
 

Mehr von IDES Editor (20)

Artificial Intelligence Technique based Reactive Power Planning Incorporating...
Artificial Intelligence Technique based Reactive Power Planning Incorporating...Artificial Intelligence Technique based Reactive Power Planning Incorporating...
Artificial Intelligence Technique based Reactive Power Planning Incorporating...
 
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...
Design and Performance Analysis of Genetic based PID-PSS with SVC in a Multi-...
 
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...
Optimal Placement of DG for Loss Reduction and Voltage Sag Mitigation in Radi...
 
Line Losses in the 14-Bus Power System Network using UPFC
Line Losses in the 14-Bus Power System Network using UPFCLine Losses in the 14-Bus Power System Network using UPFC
Line Losses in the 14-Bus Power System Network using UPFC
 
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...
Study of Structural Behaviour of Gravity Dam with Various Features of Gallery...
 
Assessing Uncertainty of Pushover Analysis to Geometric Modeling
Assessing Uncertainty of Pushover Analysis to Geometric ModelingAssessing Uncertainty of Pushover Analysis to Geometric Modeling
Assessing Uncertainty of Pushover Analysis to Geometric Modeling
 
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...
Secure Multi-Party Negotiation: An Analysis for Electronic Payments in Mobile...
 
Selfish Node Isolation & Incentivation using Progressive Thresholds
Selfish Node Isolation & Incentivation using Progressive ThresholdsSelfish Node Isolation & Incentivation using Progressive Thresholds
Selfish Node Isolation & Incentivation using Progressive Thresholds
 
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...
Various OSI Layer Attacks and Countermeasure to Enhance the Performance of WS...
 
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...
Responsive Parameter based an AntiWorm Approach to Prevent Wormhole Attack in...
 
Cloud Security and Data Integrity with Client Accountability Framework
Cloud Security and Data Integrity with Client Accountability FrameworkCloud Security and Data Integrity with Client Accountability Framework
Cloud Security and Data Integrity with Client Accountability Framework
 
Genetic Algorithm based Layered Detection and Defense of HTTP Botnet
Genetic Algorithm based Layered Detection and Defense of HTTP BotnetGenetic Algorithm based Layered Detection and Defense of HTTP Botnet
Genetic Algorithm based Layered Detection and Defense of HTTP Botnet
 
Enhancing Data Storage Security in Cloud Computing Through Steganography
Enhancing Data Storage Security in Cloud Computing Through SteganographyEnhancing Data Storage Security in Cloud Computing Through Steganography
Enhancing Data Storage Security in Cloud Computing Through Steganography
 
Low Energy Routing for WSN’s
Low Energy Routing for WSN’sLow Energy Routing for WSN’s
Low Energy Routing for WSN’s
 
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...
Permutation of Pixels within the Shares of Visual Cryptography using KBRP for...
 
Rotman Lens Performance Analysis
Rotman Lens Performance AnalysisRotman Lens Performance Analysis
Rotman Lens Performance Analysis
 
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral Images
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral ImagesBand Clustering for the Lossless Compression of AVIRIS Hyperspectral Images
Band Clustering for the Lossless Compression of AVIRIS Hyperspectral Images
 
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...
Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site ...
 
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...Texture Unit based Monocular Real-world Scene Classification using SOM and KN...
Texture Unit based Monocular Real-world Scene Classification using SOM and KN...
 
Mental Stress Evaluation using an Adaptive Model
Mental Stress Evaluation using an Adaptive ModelMental Stress Evaluation using an Adaptive Model
Mental Stress Evaluation using an Adaptive Model
 

Kürzlich hochgeladen

2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptxMaritesTamaniVerdade
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docxPoojaSen20
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
Magic bus Group work1and 2 (Team 3).pptx
Magic bus Group work1and 2 (Team 3).pptxMagic bus Group work1and 2 (Team 3).pptx
Magic bus Group work1and 2 (Team 3).pptxdhanalakshmis0310
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfagholdier
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and ModificationsMJDuyan
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...Poonam Aher Patil
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Association for Project Management
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdfQucHHunhnh
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxnegromaestrong
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...pradhanghanshyam7136
 
ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701bronxfugly43
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfSherif Taha
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 

Kürzlich hochgeladen (20)

2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Magic bus Group work1and 2 (Team 3).pptx
Magic bus Group work1and 2 (Team 3).pptxMagic bus Group work1and 2 (Team 3).pptx
Magic bus Group work1and 2 (Team 3).pptx
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...Making communications land - Are they received and understood as intended? we...
Making communications land - Are they received and understood as intended? we...
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 

Estimation of Weekly Reference Evapotranspiration using Linear Regression and ANN Models

  • 1. ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011 © 2011 ACEE 31 DOI:01.IJCEE.01.01.517 EstimationofWeeklyReferenceEvapotranspiration using LinearRegressionandANN Models K.Chandra Sekhar Reddy1 , S.Aruna Jyothy2 , and P.Mallikarjuna3 1 N.B.K.R.I.S.T., Department of Civil Engineering, Vidyanagar,Andhra Pradesh, India. Email: vinod_harsha@yahoo.co.in 2 Sri Venkateswara University, Department of Civil Engineering, Tirupati, India Email: aruna_jyothy@yahoo.co.in 3 Sri Venkateswara University, Department of Civil Engineering, Tirupati, India Email : mallikarjuna_perugu@yahoo.co.in Abstract— The study investigates the applicability of linear regression and ANN models for estimating weekly reference evapotranspiration (ET0 ) at Tirupati, Nellore, Rajahmundry, Anakapalli and Rajendranagar regions of Andhra Pradesh. The climatic parameters influencing ET0 were identified through multiple and partial correlation analysis. The sunshine, temperature, wind velocity and relative humidity mostly influenced the study area in the weekly ET0 estimation. Linear regression models in terms of the climatic parameters influencing the regions and, optimal neural network architectures considering these climatic parameters as inputs were developed. The models’ performance was evaluated with respect to ET0 estimated by FAO-56 Penman-Monteith method. The linear regression models showed a satisfactory performance in the weekly ET0 estimation in the regions selected for the present study. The ANN (4,4,1) models, however, consistently showed a slightly improved performance over linear regression models. Index Terms—Reference evapotranspiration, multiple linear regression, artificial neural network, performance evaluation I. INTRODUCTION An accurate estimation of reference crop evapotranspiration (ET0 ) is of paramount importance for designing irrigation systems and managing natural water resources. Numerous ET0 equations have been developed and used according to the availabilityof historical and current weather data. These equations range in sophistication from empirical to complex equations. The FAO-56 Penman- Monteith (PM) equation [1] is widelyused in recent times for ET0 estimation. However, the difficultyin using this equation, in general, is the lack of accurate and complete data. In addition, the parameters in the equation potentiallyintroduce certain amount of measurement and/or computational errors, resulting in cumulative errors in ET0 estimates. Under these conditions, a simple empirical equation that requires as few parameters as possible and, results comparable with Penman- Monteith method is preferable. Owing to the difficulties associated with model structure identification and parameter estimation of the nonlinear complex evapotranspiration process, most of the models that have been developed may not yield satisfactoryresults. ANNs are capable of modelling complex nonlinear processeseffectivelyextracting the relation between the inputs and outputs of a process without the physics being explicitly provided to them and also, they identify the underlying rule even if the data is noisy and contaminated with errors [2] and [3]. “Reference [4]” investigated the utility of ANNs for the estimation of daily ET0 andcompared theperformanceofANNs with PMmethod. It was concluded that ANNs can predict ET0 better than the conventional methods. “Reference [5]” examined thepotential of artificial neural networks in estimating the actual evapotranspiration from limited climatic data and suggested that the crop evapotranspiration could be computed from air temperature using theANN approach. “Reference [6]” showed thatANNs can be used for forecasting ET0 with high reliability. “Reference [7]” derived solar radiation and net radiation based ET0 equations using multi- linear regression technique and concluded that the equations performed better than the simplified temperature and/or radiation based methods for humid climates. “Reference [8]” tested the ANNs for estimating ET0 as a function of maximum and minimum air temperatures and concluded that when taking into account just themaximum andminimum air temperatures, it ispossible toestimate ET0 . “Reference [9]” tested theANNs, to estimate ET0 as a function of the maximum and minimum air temperatures in semiarid climate. While comparing with PM method, it was concluded that ANN methods are better for ET0 estimates than the conventional methods. “Reference [10]” evaluated ANN models for daily ET0 estimation under situations of presence of only temperature and relative humiditydata. ANNs showed an improved performance over traditional ET0 equations. “Reference [11]” developed generalized artificial neural network (GANN) basedreference crop evapotranspiration models corresponding to FAO-56 PM, FAO-24 Radiation, Turc and FAO-24 Blaney-Criddle methodsusing the data from California Irrigation Management and Information System stations. It was concluded that the GANN models can be used directlyto predict ET0 under the arid conditions since they performed better than the conventional ET0 estimation methods. “Reference [12]” compared weekly evapotranspiration ANN based forecasts with regard to a model based on weeklyaverages and found an improved performance of one week in advance weekly ET0 predictions compared tothe model based on means (mean year model).
  • 2. ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011 © 2011 ACEE 32 DOI:01.IJCEE.01.01.517 II. MATERIALSANDMETHODS The climatic data at Tirupati, Nellore, Rajahmundry, Anakapalli and Rajendranagar meteorological centers collected from the India Meteorological Department (IMD), Pune, India were used in the data analysis and model development. A part of the data was used for the purpose of development ofmodels and the rest for validating the models developed. The resemblance of the statistical structure in terms of mean, variance and skewness of the calibration and validation data sets was ensured while making the division of the data into training and testing data sets. A brief description ofthe meteorological centers along with the data period is shown in TABLE I. In the present study, an attempt is made to develop simple linear and optimal neural network models considering the climatic parameters influencing the regions selected for the studyfor weeklyET0 estimation. The study also compares the performance of proposed linear regression and ANN models. III.MODELDEVELOPMENT The weekly reference evapotranspiration model at a meteorological center is developed using the climatic data at the center. The steps in the modelling include i) identification of meteorological parameters influencing the region, ii) development of the model and iii) performance evaluation of the model developed. The identification of meteorological parameters influencing the region is based on multiple and partial correlation analysis. The linear regression and ANN models are developed for the present study. The performance of the models is verified through selected performance evaluation criteria. A. Linear Regression (LR) model The objective of the model is the transfer of information among several variables observed simultaneously and the estimation of the dependent variable from the several other observed independent variables. The weekly reference evapotranspiration (ET0 ) at a meteorological center is expressed as a simple linear model as ET0 =C + a1 X1 + a2 X2 +… (1) where a1 ,a2 ,…… and C are empirical constants and X1 ,X2 ,…. are the meteorological parameters influencing the region. The multiplecorrelation analysis was carried out usingSTASTICA package. B. Artificial Neural Network model (ANN) A standard multilayer feed-forward ANN with logistic sigmoid function was adopted for the present study. A constant value of0.1 for learning rate and a constant value of 0.9 for momentum factor were considered. The data were normalized in the range of (0.1, 0.9) to avoid anysaturation effect. Error back propagation which is an iterative nonlinear optimization approach based on the gradient descent search method [13] was used during calibration. The calibration set was used to minimize the error and validation set was used to ensure proper training of the neural network employed such that it does not get overtrained. The performance of the model was checked for its improvement on each iteration to avoid overlearning. The optimal network corresponding tominimum mean squared error was obtained through trail and error process. Care was taken to avoid too few and too many neurons which can respectivelycause difficulties in mapping each input and output in the training set and increase training time unnecessarily, in the process ofdetermination ofoptimal number of hidden layers and nodes in each hidden layer. The process was carried out using MATLAB routines. IV.PERFORMANCE EVALUATIONCRITERIA The performance evaluation criteria used in the present study are the coefficient of determination (R2 ), root mean square error (RMSE) and efficiency coefficient (EC). TABLE I. BRIEF DESCRIPTION OF METEOROLOGICAL CENTERS A. Coefficient of Determination (R2 ) It is the square of the correlation coefficient (R) and the correlation coefficient is expressed as where yi and iyˆ are the observed and estimated values respectively and, y and iyˆ are the means of observed and estimated values and n is the number of observations. It measures the degree of association between the observed and estimated values and indicates the relative assessment of the model performance in dimensionless measure.
  • 3. ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011 © 2011 ACEE 33 DOI:01.IJCEE.01.01.517 B. Root Mean Square Error (RMSE) It yields the residual error in terms ofthe mean square error and is expressed as [14]. RMSE= n yy ii n i 2 1 )ˆ(  (3) C. Efficiency Coefficient (EC) It is used to assess the performance of different models [15]. It is a better choice than RMSE statistic when the calibration and verification periods have different lengths [16]. It measures directly the ability of the model to reproduce the observed values and is expressed as EC = 1001 0        F F (4) where F0 = 2 1 )( yyi n i  and F = 2 1 )ˆ( ii n i yy  A value of EC of 90% generally indicates a verysatisfactory model performance while a value in therange80-90%, a fairly good model. Values ofEC in the range 60-80% would indicate an unsatisfactorymodel fit. V.RESULTSANDDISCUSSION The multiple correlation analysis has been carried out to identifythe climatic parameters influencing weeklyET0 in the regions selected for the study. It may be observed from multiple and partial correlation coefficients presented in TABLE II that the sunshine hours, temperature, wind velocity and relative humidity mostly influence the regions in the weeklyET0 estimation. Linear weeklyET0 regression models at the centers have been developed as presented in TABLE III. The weeklyET0 estimation at the meteorological centers has also been carried out using different artificial neural network architectures with input nodes ranging from one to four and, varying the number of nodes in the hidden layer. The ANNs with four input nodes and a hidden layer with four nodes i.e. ANN (4,4,1) have been identified as optimal architectures. The performance indices of linear regression (LR) and ANN (4,4,1) models on comparison of the results with those ofFAO-56 Penman-Montieth method arepresented in TABLE IV. It maybe observed from the results presented inTABLE IVthat thevaluesofR2 andECofLRmodelsindicate a very satisfactory performance. However, the performance hasimproved marginallywith optimal artificial neural network architectures. TABLE II MULTIPLE AND PARTIAL CORRELATION COEFFICIENTS TABLE III LINEAR REGRESSION MODELS
  • 4. ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011 © 2011 ACEE 34 DOI:01.IJCEE.01.01.517 TABLE IV PERFORMANCE INDICES OF LR AND ANN (4,4.1) MODELS The values ofRMSE ofANN(4,4,1) models have alsoreduced slightly. This maybe due to the fact that weekly average ET0 values do not exhibit much of nonlinearity. The scatter plots (not shown in the paper) of ET0 values estimated using Penman-Montieth method against those estimated using LR and ANN (4,4,1) models respectively. The nearly unit slope and zero intercept of scatter plots (TABLE IV) indicate the closeness of ET0 values with those of PM method. “Fig. 1” presents the comparison of performance of LR and ANN (4,4,1) models against PM method during testing period. The study reveals that the simple linear regression models proposed may be adopted satisfactorily in the weekly ET0 estimation at the centers selected for the present study and, the accuracy in the ET0 estimation may further be improved usingANN (4,4,1) models. VI.CONCLUSIONS The climatic parameters such as sunshine hours, temperature, wind velocity and relative humidity mostly influenced weekly ET0 estimation at Tirupati, Nellore, Rajahmundry, Anakapalli and Rajendranagar regions of Andhra Pradesh. The linear regression models proposed in terms of the climatic parameters influencing the regions performed satisfactorily in the weekly ET0 estimation. The optimal ANN models proposed showed a marginal improvement over linear regression models. The linear regression models may therefore be adopted for weekly ET0 estimation in the regions with reasonable degree of accuracy and, the accuracy may slightly be improved with ANN architectures. Figure 1. Comparison of average weekly ETO values estimated using LR and ANN models with those estimated by Penman-Monteith method during testing period
  • 5. ACEE Int. J. on Civil and Environmental Engineering, Vol. 01, No. 01, Feb2011 © 2011 ACEE 35 DOI:01.IJCEE.01.01.517 REFERENCES [1] R. G. Allen, L. S Pereira, D. Raes, and M.Smith, “Crop Evapotranspiration Guidelines for Computing Crop Water Requirements.” FAO Irrigation and Drainage Paper 56, FAO, Rome, 1998. [2] ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. “Artificial Neural Networks in Hydrology. I: Preliminary concepts.” J. Hydrol. Eng., 5(2), pp. 115-123, 2000a. [3] ASCE Task Committee on Application of Artificial Neural Networks in Hydrology.”Artificial Neural Networks in Hydrology. II: Hydrologic applications.” J. Hydrol. Eng., 5(2), pp. 124-137, 2000b. [4] M. Kumar, N. S. Raghuwanshi, R. Singh, W. W.Wallender, and W. O. Pruitt. “Estimating Evapotranspiration using Artificial Neural Network.” J. Irrig. Drain. Eng., 128(4), pp. 224-233, 2002. [5] K. P. Sudheer, A. K. Gosain, and K. S. Ramasastri, “Estimating Actual Evapotranspiration from Limited Climatic Data using Neural Computing Technique.” J. Irrig. Drain. Eng., 129(3), pp. 214-218, 2003. [6] S. Trajkovic, B.Todorovic, and M. Stankovic, “Forecasting of Reference Evapotranspiration by Artificial Neural Networks.” J. Irrig. Drain. Eng., 129(6), pp.454-457, 2003. [7] S. Irmak, A. Irmak, R. G. Allen, and J. W. Jones, “Solar and Net Radiation-Based Equations to Estimate Reference Evapotranspiration in Humid Climates.” J. Irrig. Drain. Eng. 129(5), pp.336-347, 2003. [8] S. S.Zanetti, E. F. Sousa, V. P. S.Oliveira, F. T.Almeida, and S. Bernardo,”Estimating Evapotranspiration using Artificial Neural Network and Minimum Climatological Data.” J. Irrig. Drain. Eng., 133(2), 83-89, 2007. [9]A.R. Khoob, “ArtificialNeural Network Estimation of Reference Evapotranspiration from Pan Evaporation in a Semi-Arid Environment.” J. Irrig. Sci., 27(1), pp.35-39, 2008. [10] G. Landeras, A. O. Barredo, and J. J. Lopez, “Comparison of Artificial Neural Network Models and Empirical and Semi- Empirical Equations for Daily Reference Evapotranspiration Estimation in the Basque Country (Northern Spain).”Agricultural Water Management, 95(5), pp. 553-565, 2008. [11] M. Kumar, N. S. Raghuwanshi and R. Singh, “Development and Validation of GANN model for Evapotranspiration Estimation.” J. Hydrol. Eng., 14(2), pp.131- 140, 2009. [12] G. Landeras, A. O. Barredo, and J. J. Lopez. “Forecasting Weekly Evapotranspiration with ARIMA and Artificial Neural Network Models.” J. Irrig. Drain. Eng., 135(3), pp.323-334, 2009.. [13] D. E. Rumelhart, G. E.Hinton, and R. J. Williams. “Learning Internal Representations by Error Propagation.” Parallel Distributed Processing, MIT press, Cambridge, MA, 1, pp. 318-362, 1986. [14] P. S Yu., C. L Liu and T. Y. Lee, “Application of Transfer Function Model to a Storage Runoff Process.” Stochastic and Statistical Methods in Hydrology and Environmental Engineering, 3, pp. 87 – 97, 1994. [15] J. E. Nash, and J.V. Sutcliffe, “River Flow Forecasting Through Conceptual Models- I: A Discussion of Principles.” J. Hydrol., 10(3), pp. 282-290, 1970. [16] G. C. Liang, O. Connor, and R. K. Kachroo, “A Multiple- Input Single-Output Varia R. K. Ble gain Model.” J. Hydrol., 155(1-2), pp. 185-198, 1994.