Fuzzy-Probabilistic Calculations of Evapotranspiration

Faybishenko, Boris

doi:10.5772/18087

Cited by 2 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques were more popular than direct and indirect methods due to their capacity to tolerate incomplete or imprecise information. At an early stage, as a popular AI technique, several fuzzy inference systems (FIS) were attempted for modeling, those included ( Odhiambo, Yoder & Yoder, 2001 ; Patel, Patel & Bhatt, 2014 ; Faybishenko, 2012 ), etc . However, these models did not survive due to severe drawbacks, such as domain experts’ scarcity, rule ambiguity, and the improper design of the membership functions ( Wang, 2015 ).…”

Section: Introductionmentioning

confidence: 99%

EvatCrop: a novel hybrid quasi-fuzzy artificial neural network (ANN) model for estimation of reference evapotranspiration

Banerjee,

Sarkar,

Sarkar

et al. 2024

PeerJ

View full text Add to dashboard Cite

Reference evapotranspiration (ET0 ) is a significant parameter for efficient irrigation scheduling and groundwater conservation. Different machine learning models have been designed for ET0 estimation for specific combinations of available meteorological parameters. However, no single model has been suggested so far that can handle diverse combinations of available meteorological parameters for the estimation of ET0. This article suggests a novel architecture of an improved hybrid quasi-fuzzy artificial neural network (ANN) model (EvatCrop) for this purpose. EvatCrop yielded superior results when compared with the other three popular models, decision trees, artificial neural networks, and adaptive neuro-fuzzy inference systems, irrespective of study locations and the combinations of input parameters. For real-field case studies, it was applied in the groundwater-stressed area of the Terai agro-climatic region of North Bengal, India, and trained and tested with the daily meteorological data available from the National Centres for Environmental Prediction from 2000 to 2014. The precision of the model was compared with the standard Penman-Monteith model (FAO56PM). Empirical results depicted that the model performances remarkably varied under different data-limited situations. When the complete set of input parameters was available, EvatCrop resulted in the best values of coefficient of determination (R2 = 0.988), degree of agreement (d = 0.997), root mean square error (RMSE = 0.183), and root mean square relative error (RMSRE = 0.034).

show abstract

Section: Introductionmentioning

confidence: 99%

EvatCrop: a novel hybrid quasi-fuzzy artificial neural network (ANN) model for estimation of reference evapotranspiration

Banerjee,

Sarkar,

Sarkar

et al. 2024

PeerJ

View full text Add to dashboard Cite

show abstract

Comparison of calculation methods for determining evapotranspiration under drip irrigation

Zhuravlov

Shatkovskyi

Vasyuta

et al. 2022

LRaWM

View full text Add to dashboard Cite

The accuracy of calculation methods for determining the evapotranspiration (ET) of corn for grain under drip irrigation in the steppe of Ukraine was established. A comprehensive assessment of calculation methods for soil optimal water regime formation during different growth phases of maize plants was carried out. The accuracy of the estimated value of evapotranspiration was determined by the mean absolute percentage error (MAPE). It has been proven that the use of calculation methods without taking into account the climatic conditions of Southern Ukraine leads to a significant error in determining the actual evapotranspiration. By the Penman-Monteith method, the MAPE of 16.3-26.9% corresponds to the good and satisfactory accuracy of the chosen calculation model. Using the methods of A.M. and S.M. Alpatyev as well as D.A. Stoyko the MAPE increased to 22.2-39.7% and 20.8-29.1%, respectively, which proved their satisfactory accuracy. The calculation method of M.M. Ivanov ensured the MAPE of 48,7-76,8%; that is unsatisfactory calculation accuracy. Adapted crop coefficients Kc for the conditions of the South of Ukraine increased the accuracy of calculating ET by the Penman-Monteith method by an average of 2,2 times, D.A. Shtoyko and A.M. and S.M. Alpatiev by 1,9 and 2,2 times, and M.M. Ivanov by 4,4 times. An analysis of the MAPE using various calculation methods for determining the evapotranspiration of corn for grain under drip irrigation showed that the Penman-Monteith method provides the smallest error (MAPE = 9.1%), which corresponds to high prediction accuracy. In a wet year, the accuracy of ET determination decreases by all methods, which indicates an increase in the MAPE: by Penman-Monteith and D.A. Shtoyko - up to 11.9% and 18.7%, respectively, and the determination accuracy decreases to category “good”. When calculating using the methods of A.M. and S.M. Alpatiev and M.M. Ivanov the MAPE increased to 23,3% and 21,5%, respectively, and the accuracy of ET determination was satisfactory.

show abstract

Fuzzy-Probabilistic Calculations of Evapotranspiration

Cited by 2 publications

References 40 publications

EvatCrop: a novel hybrid quasi-fuzzy artificial neural network (ANN) model for estimation of reference evapotranspiration

EvatCrop: a novel hybrid quasi-fuzzy artificial neural network (ANN) model for estimation of reference evapotranspiration

Comparison of calculation methods for determining evapotranspiration under drip irrigation

Contact Info

Product

Resources

About