Pan evaporation modeling using six different heuristic computing methods in different climates of China

Wang, Lunche; Kisi, Özgür; Zounemat‐Kermani, Mohammad; Li, Hui

doi:10.1016/j.jhydrol.2016.11.059

Cited by 105 publications

(44 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Inspired by a biological neural network, the neural network receives its independent neurons in its input. The variables are passed to subsequent layers of neurons, where, passing through a transfer function, the weighted sum of input values are calculated, providing an output for the neuron in analysis (Wang et al, 2017a). The bayesian regularized neural networks (BRNN) are more robust than the networks that use the back propagation of the errors, besides avoiding the overfitting of the model (Ticknor, 2013).…”

Section: Bayesian Regularized Neural Networkmentioning

confidence: 99%

“…Support vector machines (SVMs) are considered as supervised learning methods, which can be used both to classify a set of samples and to regress them. When a dataset is submitted to SVM analysis, they separate the data by constructing hyperplanes, aiming at the implantation of surfaces with the greatest possible margin between the datasets considered as different (Wang et al, 2017a). The larger the margin of the hyperplane, the greater is the generalization capacity of the model created to predict or classify the data set.…”

Section: Support Vector Machinesmentioning

confidence: 99%

See 1 more Smart Citation

Heuristic methods applied in reference evapotranspiration modeling

et al. 2018

View full text Add to dashboard Cite

The importance of the precise estimation of evapotranspiration is directly related to sustainable water usage. Since agriculture represents 70% of Brazil’s water consumption, adequate and efficient application of water may reduce the conflicts over the use of water among the multiple users. Considering the importance of accurate estimation of evapotranspiration, the objective of the present study was to model and compare the reference evapotranspiration from different heuristic methodologies. The standard Penman-Monteith method was used as reference for evapotranspiration, however, to evaluate the heuristic methodologies with scarce data, two widely known methods had their performances assessed in relation to Penman-Monteith. The methods used to estimate evapotranspiration from scarce data were Priestley-Taylor and Thornthwaite. The computational techniques Stepwise Regression (SWR), Random Forest (RF), Cubist (CB), Bayesian Regularized Neural Network (BRNN) and Support Vector Machines (SVM) were used to estimate evapotranspiration with scarce and full meteorological data. The results show the robustness of the heuristic methods in the prediction of the evapotranspiration. The performance criteria of machine learning methods for full weather data varied from 0.14 to 0.22 mm d-1 for mean absolute error (MAE), from 0.21 to 0.29 mm d-1 for root mean squared error (RMSE) and from 0.95 to 0.99 coefficient of determination (r²). The computational techniques proved superior performance to established methods in literature, even in scenarios of scarce variables. The BRNN presented the best performance overall.

show abstract

Section: Bayesian Regularized Neural Networkmentioning

confidence: 99%

Section: Support Vector Machinesmentioning

confidence: 99%

Heuristic methods applied in reference evapotranspiration modeling

et al. 2018

View full text Add to dashboard Cite

show abstract

“…As previously reported in the literature, Rg decreased from 1961 to 1990 and then increased from the 1990s for most stations in China ( Figure 6). A more detailed account of these change rates is presented in Wang et al (2017). Monthly statistical parameters regarding the climatic data are shown in Table 1 and Figure 6, where x mean , S x , C v , C x , x min and x max denote the mean, standard deviation, variation coefficient, skewness, minimum and maximum values, respectively.…”

Section: Case Study and Datamentioning

confidence: 99%

“…In recent decades, both direct and indirect methods have been employed to estimate Ep values around the world (Priestley and Taylor, 1972;Shirsath and Singh, 2010;Shiri et al, 2014c;Wang et al, 2017). The U.S.…”

Section: Introductionmentioning

confidence: 99%

Evaporation modelling using different machine learning techniques

Wang

Kisi

et al. 2017

Intl Journal of Climatology

Self Cite

View full text Add to dashboard Cite

Accurate prediction of pan evaporation (Ep) is critical for water resource management. This article investigates the capabilities of three different soft computing methods at estimating monthly Ep at six stations in the Yangtze River Basin using climatic factors, including the air temperature (Ta), solar radiation (Rg), air pressure (Pa) and wind speed (Ws) for the period of 1961–2000. The first part of the study focused on testing and comparing model accuracy levels at each station using local input combinations. The results indicate that the fuzzy genetic (FG) model generally produces better results than adaptive neuro‐fuzzy inference systems with grid partition (ANFIS‐GP) and M5 model tree (M5Tree) specifications in terms of the root mean square error , mean absolute error and coefficient of determination values. The performance of the above models was also examined using cross‐station applications (estimating Ep without local input or output data) in the second part of the study. The third part focused on estimating Ep using generalized FG, ANFIS‐GP and M5Tree models. Collectively, the results demonstrate that the FG model can be successfully used to estimate Ep without any local inputs and outputs and that a single generalized FG model can also be used at six different locations.

show abstract

“…The physical basis of Class A pan's E p was investigated among others by Roderick et al (2007) and Jacobs et al (1998). E p has also been applied as an index of lake and reservoir E (Wang et al, 2017;Kim et al, 2015;Allen et al, 1998) beyond traditional E p uses in water budget estimation, plant-weather interactions, etc. Spatial and temporal limitations of pan application due to instrumental and practical issues were also integrated (Martí et al, 2015;Shiri et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

Estimation of natural water body’s evaporation based on Class A pan measurements in comparison to reference evapotranspiration

Anda¹,

Simón²,

Soós³

et al. 2018

Időjárás

View full text Add to dashboard Cite

Abstract⎯ A Class A pan (C) evaporation (E p ) study was conducted at the Agrometeorological Research Station of Keszthely, in the growing season of 2016. Some of the evaporation pans were implemented with freshwater aquatic macrophytes (Myriophyllum sp., Potamogeton sp., and Najas sp.) (P s ) and sediment covered bottom (S). The applied macrophytes were the predominant species of Keszthely Bay (Balaton Lake). Reference (E o ) after Shuttleworth and reference evapotranspiration (ET o ) after PenmanMonteith (FAO-56 formula) were also included for the E study. Of pre-selected four investigated variables, air temperature and air humidity impacted E p of treated Class A pans the most. Cumulative E p values for 2016 were 363.1, 427.7, and 461.5 mm in C, S, and Ps, respectively. There was no difference in measured cumulative E p of P s (461.5 mm) and computed ET o (472.1 mm) during the studied season.On the basis of a simplified water budget, E rate of Keszthely Bay increased with 16.9%, when macrophytes and sediment cover were accounted. It is equivalent to 264,000,000 m 3 water in Keszthely Bay's E estimation. Simple E approach -when lake's components, such as submerged macrophytes and sediment cover were also accounted -could extend the accuracy of natural lake's E estimation in a broader circle than earlier.

show abstract

Pan evaporation modeling using six different heuristic computing methods in different climates of China

Cited by 105 publications

References 35 publications

Heuristic methods applied in reference evapotranspiration modeling

Heuristic methods applied in reference evapotranspiration modeling

Evaporation modelling using different machine learning techniques

Estimation of natural water body’s evaporation based on Class A pan measurements in comparison to reference evapotranspiration

Contact Info

Product

Resources

About