Global cross-station assessment of neuro-fuzzy models for estimating daily reference evapotranspiration

Shiri, Jalal; Nazemi, Amir Hossein; Sadraddini, Ali Ashraf; Landeras, Gorka; Kisi, Özgür; Fard, Ahmad Fakheri; Martí, Pau

doi:10.1016/j.jhydrol.2012.12.006

Cited by 56 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the same region, Shiri et al () reported RMSE averages from 0.53 to 0.78 mm day −1 when using gene expressing programming with only T max and T min , and from 0.49 to 0.65 mm day −1 when estimations were performed with a neuro‐fuzzy model, also with T max and T min only. In a later study, Shiri et al () reported a wider range for non‐humid locations than for humid ones. In this study, RMSE ranging 0.22–0.38 mm day −1 were obtained for the same region.…”

Section: Resultsmentioning

confidence: 99%

Assessing reference evapotranspiration estimation from reanalysis weather products. An application to the Iberian Peninsula

Martins

Paredes

Raziei

et al. 2016

Intl Journal of Climatology

View full text Add to dashboard Cite

Computing crop reference evapotranspiration (ETo) with the FAO Penman–Monteith method (PM‐ETo) requires maximum and minimum air temperature, shortwave radiation, relative air humidity and wind speed. These data are often not available, thus requiring alternative computation procedures. Although some proposed approximations may provide ETo values with small estimation errors, the physics of the ET processes may then not be well described. The use of reanalysis data, which is common in climate studies, represents an alternative to observation data for the weather variables referred above, when these are not available. This study focuses on the use of the National Center for Environmental Prediction/National Center for Atmospheric Research (NCEP/NCAR) blended reanalysis products with gridded data sets for the computation of PM‐ETo in the Iberian Peninsula. A monthly time step was adopted. The PM‐ETo time series computed with the blended reanalysis data sets were compared with those obtained using observations for 130 weather stations in the Iberian Peninsula. Results show that the PM‐ETo computed with blended reanalysis compares well with the series computed from observation data (average root mean square error, RMSE = 0.49 mm day−1). The weather variables derived from reanalysis were also compared with observation data. Results supported the quality of ETo computations because, overall, there was a good match between solar radiation (average RMSE = 1.76 MJm−2 day−1) and maximum temperature (average RMSE = 1.48 °C) derived from reanalysis and in situ observations. By contrast, the wind speed from reanalysis highly overestimated observations and this is likely a reason for the slight overestimation of ETo computed from reanalysis (percentage bias, PBIAS>20% in 89% of cases). In addition, the reanalysis products are apparently influenced by modelled warming, which contributes to overestimation of the minimum temperature and, to a lesser extent, of the relative humidity. The spatial pattern of accuracy indicators reveals that poorer results correspond to the southern and south‐eastern coastal areas of Iberia, where climate is semi‐arid. The compatibility of the PM‐ETo computed with monthly inputs and of the daily ETo cumulated to the month using the PM‐ETo equation was confirmed, thus allowing to extend conclusions of this study to daily computations. Alternative reanalysis products were also assessed. Tests for ERA‐Interim reanalysis products revealed overestimation of ETo and those for NCEP/NCAR Reanalysis II have shown large underestimation. Results suggest that the blended reanalysis products are suitable for the estimation of ETo in Iberia since they integrate an appropriate correction of radiation and temperature, which proved essential for the good estimation results obtained.

show abstract

Section: Resultsmentioning

confidence: 99%

Assessing reference evapotranspiration estimation from reanalysis weather products. An application to the Iberian Peninsula

Martins

Paredes

Raziei

et al. 2016

Intl Journal of Climatology

View full text Add to dashboard Cite

show abstract

“…In relation to the limitations of the approaches in terms of reduced data requirements, previous studies (Landeras et al , ; Shiri et al , , ) showed a better performance of approaches including wind speed and/or humidity compared with simpler approaches such as Makkink or Hargreaves. However these limitations could be reduced by carrying out an efficient calibration process, as Cruz‐Blanco et al () did with the MAK‐Adv approach, or Cristea et al () considering relative humidity and wind speed.…”

Section: Resultsmentioning

confidence: 99%

“…MAK-Adv approach uses only temperature and solar radiation as input), by the failure to meet the reference surface requirements (see Section 2.3) and by errors in the input data provided by LSA SAF and ECMWF. In relation to the limitations of the approaches in terms of reduced data requirements, previous studies (Landeras et al, 2008;Shiri et al, 2012Shiri et al, , 2013 showed a better performance of approaches including wind speed and/or humidity compared with simpler approaches such as Makkink or Hargreaves. However these limitations could be reduced by carrying out an efficient calibration process, as Cruz-Blanco et al (2014a) did with the MAK-Adv approach, or Cristea et al (2013b) considering relative humidity and wind speed.…”

Section: Mak-adv Approach For Et O Estimationmentioning

confidence: 99%

Uncertainty in estimating reference evapotranspiration using remotely sensed and forecasted weather data under the climatic conditions of Southern Spain

Cruz-Blanco

Santos

Jiménez-Gavilán

et al. 2014

Intl Journal of Climatology

View full text Add to dashboard Cite

In this study, a detailed spatial analysis of the reference evapotranspiration (ETo) estimates provided by the MAK‐Adv approach and the well‐known Penman‐Monteith equation (PM‐FAO56) has been carried out. MAK‐Adv approach considers a regionally calibrated Makkink equation based on a combination of remotely sensed solar radiation, Rs, provided by the Land Surface Analysis Satellite Applications Facility (LSA SAF), and numerical weather forecasts of near‐surface air temperature, T2m, provided by the European Centre for Medium‐range Weather Forecasts (ECMWF). This analysis evaluated the performance of these approaches with data measured by 57 weather stations under different weather conditions within a semi‐arid region, Andalusia, located at Southern Spain, and determined the role of certain physical and climate variables, such as wind speed and sensible heat advection, on the quality of the ETo estimation. For three years (2007–2009), daily Rs and T2m provided by LSA SAF and ECMWF were compared with measured data showing very good estimates, with RMSD equal to 1.47 W m−2 and 1.53 °C, respectively. Equally, ETo using MAK‐Adv approach with data provided by LSA SAF and ECMWF was compared with ETo provided by the PM‐FAO56 approach with measured data, obtaining RMSD = 0.69 mm, linear regression slope = 0.94, and R2 = 0.92. Although ETo estimates using both approaches were similar between them, the small differences in terms of estimation ETo were mainly correlated with the wind speed (u) and the advection index (Ia), depicting the critical role of these factors in the ETo estimations under semi‐arid conditions, and increasing the uncertainty in ETo estimation when wind speed and/or Ia are high. The comparison of MAK‐Adv and PM‐FAO56 approaches has proved the usefulness in providing ETo values at a regional scale and detecting those areas where the ETo estimation had higher uncertainty, contributing to an improvement in water management.

show abstract

“…According to the results, it was concluded that the ANFIS method was successful in pan evaporation modelling using climate data (Kisi, ). Global generalized neuro‐fuzzy models provided a more appropriate estimation of ET 0 than empirical models in humid and non‐humid regions of Iran (Shiri et al ., ). The ANFIS and ANN techniques and empirical equations were used to estimate evaporation, and it was concluded that the ANFIS and ANN methods were much better than the empirical equations.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of several soft computing methods in monthly evapotranspiration modelling

Gavili

Hadi

Kişi

et al. 2017

Meteorological Applications

Self Cite

View full text Add to dashboard Cite

Evapotranspiration assessment is one of the most substantial issues in hydrology. The methods used in modelling reference evapotranspiration (ET 0 ) consist of empirical equations or complex methods based on physical processes. In arid and semi-arid climates, determining the amount of evapotranspiration has a major role in the design of irrigation systems, irrigation network management, planning and management of water resources and water management issues in the agricultural sector. This paper presents a case study of five meteorological stations located in Kurdistan province in the west of Iran. The ability of three different soft computing methods, an artificial neural network (ANN), an adaptive neuro-fuzzy inference system (ANFIS) and gene expression programming (GEP), were compared for modelling ET 0 in this study. The FAO56 Penman−Monteith model was considered as a reference model and soft computing models were compared using the Priestley−Taylor, Hargreaves, Hargreaves−Samani, Makkink and Makkink−Hansen empirical methods, with respect to the determination co-efficient, the root mean square error, the mean absolute error and the Nash-Sutcliffe model efficiency co-efficient. Soft computing models were superior to the empirical methods in modelling ET 0 . Among the soft computing methods, the ANN was found to be better than the ANFIS and GEP.

show abstract

Global cross-station assessment of neuro-fuzzy models for estimating daily reference evapotranspiration

Cited by 56 publications

References 37 publications

Assessing reference evapotranspiration estimation from reanalysis weather products. An application to the Iberian Peninsula

Assessing reference evapotranspiration estimation from reanalysis weather products. An application to the Iberian Peninsula

Uncertainty in estimating reference evapotranspiration using remotely sensed and forecasted weather data under the climatic conditions of Southern Spain

Evaluation of several soft computing methods in monthly evapotranspiration modelling

Contact Info

Product

Resources

About