Prediction of evaporation in tropical climate using artificial neural network and climate based models

Benzaghta, Mostafa Ali

doi:10.5897/sre11.1311

Cited by 10 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The classifiers with 8 features (i.e. feature 5,7,8,4,9,1,6, and 3) and 9 features gave the highest accuracy for both ANN and LR cases. Fig.…”

Section: Scenario 3: Selection Of Fe Aturesmentioning

confidence: 91%

“…However, only a single hidden layer ANN is enough to mimic the model together with six inputs which are minimum and maximum temperature, minimum and maximum relative humidity, wind speed, and solar radiation [4] . ANN was also successfully applied to estimate evaporation rate with air temperature, humidity, wind velocity and solar radiation [5].…”

Section: Ek Thamwiwatthanamentioning

confidence: 99%

“…Moreover, the computational time is reduced. There is an evidence that using inputs of air temperature, wind speed, humidity and solar radiation in Malaysia gives the highest accuracy of the prediction [5]. However, the selection of variables depends on the area where the experiment is conducted such as USA [4] Malaysia [5], Brazil [6], and Burkina Faso [7].…”

Section: Ek Thamwiwatthanamentioning

confidence: 99%

“…artificial neural network [4] , [5], [6], [7] . Artificial neural networks (ANNs) are trained from data collected by sensors which are installed in the crop fields.…”

Section: Ek Thamwiwatthanamentioning

confidence: 99%

See 3 more Smart Citations

Prediction of reference evapotranspiration with missing data in Thailand

Pasupa

Thamwiwatthana

2013

2013 International Conference on Information Technology and Electrical Engineering (ICITEE)

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) has been used in prediction of reference evapotranspiration for a recent decade. Its performance is competitive to a widely used method the so-called "Penman-Monteith" method. In this study, we aim to estimate the crop evapotranspiration by ANNs from climatic data in Thailand and compare the performance with the Penman Monteith method. As missing data is inevitable, we also included the missing data situation into the study. This can be solved by expectation-maximization algorithm. The accuracy of the prediction decreases when the amount of missing values increases. Furthermore, we exploit the feature selection in the study. It shows that sunshine duration is the most important feature followed by temperature and wide speed, respectively.

show abstract

“…The classifiers with 8 features (i.e. feature 5,7,8,4,9,1,6, and 3) and 9 features gave the highest accuracy for both ANN and LR cases. Fig.…”

Section: Scenario 3: Selection Of Fe Aturesmentioning

confidence: 91%

Section: Ek Thamwiwatthanamentioning

confidence: 99%

Section: Ek Thamwiwatthanamentioning

confidence: 99%

“…artificial neural network [4] , [5], [6], [7] . Artificial neural networks (ANNs) are trained from data collected by sensors which are installed in the crop fields.…”

Section: Ek Thamwiwatthanamentioning

confidence: 99%

See 2 more Smart Citations

Prediction of reference evapotranspiration with missing data in Thailand

Pasupa

Thamwiwatthana

2013

2013 International Conference on Information Technology and Electrical Engineering (ICITEE)

View full text Add to dashboard Cite

show abstract

“…The situation in Libya is typical of semi-arid climate, with average annual rainfall of less than (100 mm )and average annual evaporation is estimated to be (2500 mm )which is much higher than the rainfall [7]. This highlights the seriousness of water losses problem from open water bodies.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Three Evaporation Estimation Techniques In A Semi-Arid Region (Omar El Mukhtar Reservoir Sluge, Libya- As a case Study)

Taher¹

2017

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

In many semi-arid countries in the world like Libya, drinking water supply is dependent on reservoirs water storage. Since the evaporation rate is very high in semi-arid countries, estimates and forecasts of reservoir evaporation rate can be useful in the management of major water source. Many researchers have been investigating the suitability of estimates evaporation rates methods in many climatic settings, infrequently of which were in an arid setting. This paper presents the modeling results of evaporation from Omar El Mukhtar Reservoir, Libya. Three techniques namely (artificial neural networks (ANN), Multiple linear regression (MLR) and response surface methods (RSM)) were developed, to assess the estimation of monthly evaporation records from 2001 to 2009; their relative performance were compared using the coefficient of determination(E), mean absolute percentage error (MAPE%), and 95% confidence interval. The key variables used to develop and validate the models were: monthly (precipitation Rf., average temperature Temp., relative humidity Rh., sunshine hours Sh., atmospheric pressure Pa. and wind speed Ws.). The encouraging results approved that the models with more inputs generally had better accuracies and the ANN model performed superior to the other models in predicting monthly Evp with high E=0.86 and low MAPE%= 13.9 and the predicted mean within the range of observed 95CI%. In summary, it is revealed in this study that the ANN and RSM models are appropriate for predicting Evp using climatic inputs in semi-arid climate.

show abstract

Artificial neural networks and empirical equations to estimate daily evaporation: application to Lake Vegoritis, Greece

Antonopoulos

Gianniou

Antonopoulos

2016

Hydrological Sciences Journal

View full text Add to dashboard Cite

Evaporation is one of the most important components in the energy and water budgets of lakes and is a primary process of water loss from their surfaces. An artificial neural network (ANN) technique is used in this study to estimate daily evaporation from Lake Vegoritis in northern Greece and is compared with the classical empirical methods of Penman, Priestley-Taylor and the mass transfer method. Estimation of the evaporation over the lake is based on the energy budget method in combination with a mathematical model of water temperature distribution in the lake. Daily datasets of air temperature, relative humidity, wind velocity, sunshine hours and evaporation are used for training and testing of ANN models. Several input combinations and different ANN architectures are tested to detect the most suitable model for predicting lake evaporation. The best structure obtained for the ANN evaporation model is 4-4-1, with root mean square error (RMSE) from 0.69 to 1.35 mm d −1 and correlation coefficient from 0.79 to 0.92.

show abstract

Prediction of evaporation in tropical climate using artificial neural network and climate based models

Cited by 10 publications

References 41 publications

Prediction of reference evapotranspiration with missing data in Thailand

Prediction of reference evapotranspiration with missing data in Thailand

Evaluation of Three Evaporation Estimation Techniques In A Semi-Arid Region (Omar El Mukhtar Reservoir Sluge, Libya- As a case Study)

Artificial neural networks and empirical equations to estimate daily evaporation: application to Lake Vegoritis, Greece

Contact Info

Product

Resources

About