Comparative analysis of reference evapotranspiration equations modelling by extreme learning machine

Gocić, Milan; Petković, Dalibor; Shamshirband, Shahaboddin; Kamsin, Amirrudin

doi:10.1016/j.compag.2016.05.017

Cited by 86 publications

(32 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the equation is relatively complex and requires many meteorological data including maximum and minimum air temperature, maximum and minimum relative humidity, wind speed at 2 m height and solar radiation. A serious problem is that the numerous required data may lack accuracy or may not even be available at many stations (Allen et al, 1998;Feng et al, 2016;Feng et al, 2017;Gocic et al, 2016;Landeras et al, 2008;Shiri et al, 2012;Tabari and Talaee, 2011). To simplify the process of estimating ET 0 , many empirical temperature-or radiationbased methods, such as the McCloud, Priestley-Taylor, Blaney-Criddle and Hargreaves-Samani (HS) methods, can be applied for ET 0 calculation (Hargreaves and Allen, 2003).…”

Section: Introductionmentioning

confidence: 99%

Calibration and Validation of the Hargreaves‐Samani Model for Reference Evapotranspiration Estimation in China

Zhu

Luo

et al. 2019

Irrigation and Drainage

View full text Add to dashboard Cite

Daily meteorological data of 12 years from 838 stations over China were collected and applied to calibrate the HS model by comparison between the values of ET0 calculated from the original HS and those from the PM model. The calibrated HS model was evaluated by the distribution and values of statistical indices. After calibration, the mean values of the mean absolute error (MAE) and the root mean square error (RMSE) decreased by 24.6 and 23.9%, respectively. The correlation coefficients (R) for most areas were greater than 0.9, and the minimum R increased by 2% compared with the values of the original. The minimum and maximum slope of the zero‐intercept regression lines changed from 0.839 to 0.898 and from 1.46 to 1.04 during the validation period, respectively. The distribution of the statistical indices also showed better performance in most areas. The calibrated HS model produced the greatest ET0 estimation in the subtropical monsoon climate zone and the south‐western part of the temperate monsoon climate zone. Although the performance of the HS model improved after calibration in the plateau and mountain climate and temperate monsoon climate zones, the original HS model had high enough accuracy. However, for the tropical climate regions, the HS model failed to give reliable results even in calibrated form. Overall, the study illustrated that the calibrated HS model has higher accuracy for most climate zones. © 2019 John Wiley & Sons, Ltd.

show abstract

Section: Introductionmentioning

confidence: 99%

Calibration and Validation of the Hargreaves‐Samani Model for Reference Evapotranspiration Estimation in China

Zhu

Luo

et al. 2019

Irrigation and Drainage

View full text Add to dashboard Cite

show abstract

“…There are three layers in the ELM model, including the input layer, hidden layer, and output layer, and one of the significant factors is that the hidden layer does not need to be tuned. ELM randomly selects the input weights and then analytically determines the output weights of the SLFNs [40][41][42][43].…”

Section: Extreme Learning Machinementioning

confidence: 99%

Hydrological Responses to the Future Climate Change in a Data Scarce Region, Northwest China: Application of Machine Learning Models

Zhu

Yang

Liu

et al. 2019

Water

View full text Add to dashboard Cite

Forecasting the potential hydrological response to future climate change is an effective way of assessing the adverse effects of future climate change on water resources. Data-driven models based on machine learning algorithms have great application prospects for hydrological response forecasting as they require less developmental time, minimal input, and are relatively simple compared to dynamic or physical models, especially for data scarce regions. In this study, we employed an ensemble of eight General Circulation Models (GCMs) and two artificial intelligence-based methods (Support Vector Regression, SVR, and Extreme Learning Machine, ELM) to establish the historical streamflow response to climate change and to forecast the future response under Representative Concentration Pathway (RCP) scenarios 4.5 and 8.5 in a mountainous watershed in northwest China. We found that the artificial-intelligence-based SVR and ELM methods showed very good performances in the projection of future hydrological responses. The ensemble of GCM outputs derived very close historical hydrological hindcasts but had great uncertainty in future hydrological projections. Using the variables of GCM outputs as inputs to SVR can reduce intermediate downscaling links between variables and decrease the cumulative effect of bias in projecting future hydrological responses. Future precipitation in the study area will increase in the future under both scenarios, and this increasing trend is more significant under RCP 8.5 than under scenario 4.5. The results also indicate the streamflow change will be more sensitive to temperature (precipitation) under the RCP 8.5 (4.5) scenario. The findings and approach have important implications for hydrological response studies and the evaluation of impacts on localized regions similar to the mountainous watershed in this study.

show abstract

“…Hence, the ELM model is able randomly to screen the input weights, and then analytically determine the output weights (e.g., feature-analyzed property) of the SLFNNs. Detailed descriptions of the ELM can be found in Huang et al [74], Gocic et al [49], Abdullah et al [5], and Patil and Deka [33].…”

Section: Extreme-learning Machinementioning

confidence: 99%

Future Projection with an Extreme-Learning Machine and Support Vector Regression of Reference Evapotranspiration in a Mountainous Inland Watershed in North-West China

Yin

Feng

Yang

et al. 2017

Water

View full text Add to dashboard Cite

This study aims to project future variability of reference evapotranspiration (ET 0 ) using artificial intelligence methods, constructed with an extreme-learning machine (ELM) and support vector regression (SVR) in a mountainous inland watershed in north-west China. under the RCP4.5 (RCP8.5) scenario. Compared to the historical period, the relative changes in ET 0 were found to be approximately 2%, 5% and 6% (2%, 7% and 13%), during the near, mid-and long-term periods, respectively, under the RCP4.5 (RCP8.5) warming scenarios. In accordance with the analyses, we aver that the opportunity to downscale monthly ET 0 with artificial intelligence is useful in practice for water-management policies.

show abstract

Comparative analysis of reference evapotranspiration equations modelling by extreme learning machine

Cited by 86 publications

References 51 publications

Calibration and Validation of the Hargreaves‐Samani Model for Reference Evapotranspiration Estimation in China

Calibration and Validation of the Hargreaves‐Samani Model for Reference Evapotranspiration Estimation in China

Hydrological Responses to the Future Climate Change in a Data Scarce Region, Northwest China: Application of Machine Learning Models

Future Projection with an Extreme-Learning Machine and Support Vector Regression of Reference Evapotranspiration in a Mountainous Inland Watershed in North-West China

Contact Info

Product

Resources

About