Artificial neural network models for reference evapotranspiration in an arid area of northwest China

Huo, Zailin; Feng, Shuyi; Kang, Shaozhong; Dai, Xiaoqin

doi:10.1016/j.jaridenv.2012.01.016

Cited by 80 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The increase of MLT performance by increasing the number of input variables has been reported in other papers (Huo et al, 2012;Wen et al, 2015;Traore et al, 2016), confirming the results here presented. Although AB method had been more accurate for A1 and S1, MBE value was the highest.…”

Section: Comparison Of the Performance Of Mlt Against Hs And Ab Methodssupporting

confidence: 92%

See 1 more Smart Citation

Reference evapotranspiration in So Paulo State: Empirical methods and machine learning techniques

Tangune¹,

Escobedo²

2018

Int. J. Water Res. Environ. Eng.

View full text Add to dashboard Cite

show abstract

Section: Comparison Of the Performance Of Mlt Against Hs And Ab Methodssupporting

confidence: 92%

“…For Huo et al (2012), in BP algorithm, an activation function of neurons is used to generate the output data. In WEKA the sigmoidal function (Equation (2)) was used considering learning rate = 0.3; momentum = 0.2 and training time = 500.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Reference evapotranspiration in So Paulo State: Empirical methods and machine learning techniques

Tangune¹,

Escobedo²

2018

Int. J. Water Res. Environ. Eng.

View full text Add to dashboard Cite

show abstract

“…10−12 M5MT is an extension of a regression tree and provides the user with multiple linear functions. [1][2][3][4][5][6][7][8][9][10][11][12][13] This approach is capable of handling high dimensional datasets and the resulting model tree is significantly smaller and more precise than regression trees. 14 Moreover, the M5MT is not a black-box and provides a relationship between the independent and dependent variables.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Reference Evapotranspiration from Climatic Data

Lum

Bateni

Shiri

et al. 2017

IJH

View full text Add to dashboard Cite

This study investigated the capability of M5 Model Tree (M5MT) to predict reference evapotranspiration (ET 0 ). M5MT was trained and tested with climatic data from eight weather stations located in coastal areas of Iran for the years 2000-2008. It was validated with climatic data from seven California Irrigation Management Information System (CIMIS) weather stations for the year 2015. Four different data combinations were utilized to train, test, and validate the M5MT model. These were: daily mean air temperature, wind speed, relative humidity, and solar radiation (configuration 1); daily mean air temperature and solar radiation (configuration 2); daily mean air temperature and relative humidity (configuration 3); and daily maximum, minimum, and mean air temperature, and extraterrestrial radiation (configuration 4). The Penman-Monteith (PM) equation was used as a standard method to provide target ET 0 values. Mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R 2 ) were used to evaluate the performance of the M5MT models developed with different input configurations. Results indicated that M5MT was able to successfully estimate ET 0 . Configuration 1 provided the most accurate results. Configuration 2 showed to have the variables that have a greater influence on ET 0 than configuration 3. Configuration 4 performed the worst. MAE of ET 0 estimates from M5MT 1 was respectively 29%, 55%, and 91% lower than that of M5MT 2 , M5MT 3 , and M5MT 4 , when the model is validated in California. Also, RMSE from M5MT 1 was 29%, 59%, and 125% smaller than that of M5MT 2 , M5MT 3 , and M5MT 4 , respectively.

show abstract

“…This method employs a variety of complex equations, which are based on weather data, including air temperature, humidity, radiation, and wind speed [9]. The requirement of various weather data, which are not mainly 2 Journal of Climatology available in many regions, is the major limitation of this method [10]; in addition, it seems that the reordered data are not accurate enough, especially in developing countries [11].…”

Section: Introductionmentioning

confidence: 99%

“…The substantial benefit of ANN methods, compared to conventional methods, is the ability of solving problems that are difficult to formalize [30]. Hou et al [10] studied ANNs in simulating ET values and demonstrated that the models reflected a noticeable efficiency. Landeras et al [21] compared calculated ET by ANN to the ET values of radiation and thermal models and declared that ANN can provide more accurate results than empirical models.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of M5 Model Tree and Artificial Neural Network in Estimating Reference Evapotranspiration Using MODIS Products

Alipour

Yarahmadi

Mahdavi

2014

Journal of Climatology

View full text Add to dashboard Cite

Reference evapotranspiration (ET ) is one of the major parameters affecting hydrological cycle. Use of satellite images can be very helpful to compensate for lack of reliable weather data. This study aimed to determine ET using land surface temperature (LST) data acquired from MODIS sensor. LST data were considered as inputs of two data-driven models including artificial neural network (ANN) and M5 model tree to estimate ET values and their results were compared with calculated ET by FAO-Penman-Monteith (FAO-PM) equation. Climatic data of five weather stations in Khuzestan province, which is located in the southeastern Iran, were employed in order to calculate ET . LST data extracted from corresponding points of MODIS images were used in training of ANN and M5 model tree. Among study stations, three stations (Amirkabir, Farabi, and Gazali) were selected for creating the models and two stations (Khazaei and Shoeybie) for testing. In Khazaei station, the coefficient of determination (2 ) values for comparison between calculated ET by FAO-PM and estimated ET by ANN and M5 tree model were 0.79 and 0.80, respectively. In a similar manner, 2 values for Shoeybie station were 0.86 and 0.85. In general, the results showed that both models can properly estimate ET by means of LST data derived from MODIS sensor.

show abstract

Artificial neural network models for reference evapotranspiration in an arid area of northwest China

Cited by 80 publications

References 28 publications

Reference evapotranspiration in So Paulo State: Empirical methods and machine learning techniques

Reference evapotranspiration in So Paulo State: Empirical methods and machine learning techniques

Estimation of Reference Evapotranspiration from Climatic Data

Comparative Study of M5 Model Tree and Artificial Neural Network in Estimating Reference Evapotranspiration Using MODIS Products

Contact Info

Product

Resources

About