Estimation Of Reference Evapotranspiration Research Articles

A novel kernel extreme learning machine model coupled with K-means clustering and firefly algorithm for estimating monthly reference evapotranspiration in parallel computation

Accurate and fast estimation of reference evapotranspiration (ET0) is important in determining crop water requirements, designing irrigation schedule, planning and managing agricultural water resources, especially when limited meteorological data are available. This study proposed a novel kernel extreme learning machine model coupled with the K-means clustering and firefly algorithms (Kmeans-FFA-KELM) with 5, 10, 15, 20, 25, 30 and 40 data subsets for estimating monthly mean daily ET0 in parallel computation in the Poyang Lake basin of South China with pooled temperature data from 26 weather stations. Two input combinations, i.e. (1) mean temperature (Tavg) and extraterrestrial radiation (Ra), (2) maximum and minimum temperatures (Tmax and Tmin) and Ra, were considered. Meteorological data during 1966–2000 were used to train the models, while those for the period 2001–2015 were used for model testing. The results showed that the prediction accuracy of selected machine learning models with Tmax, Tmin and Ra was improved by 7.0–15.5% in terms of RMSE compared to that with Tavg and Ra during testing. The FFA-KELM model slightly outperformed the adaptive network based fuzzy inference system (ANFIS) model, both of which were superior to the random forest (RF) and M5 prime model tree (M5P) models, followed by the Hargreaves and Thornthwaite models. The RMSE values of Kmeans-FFA-KELM models with more than 20 subsets were decreased by 0.7–3.5% compared with those of the FFA-KELM models. The Kmeans-FFA-KELM model with 25 subsets (FFA-KELM-25) outperformed the FFA-KELM model in summer and in the count of absolute errors greater than 0.9 mm d−1. The computational time of Kmeans-FFA-KELM models first decreased and then increased with the increase of the subset number. The parallel FFA-KELM-25 model (0.5–0.7 s) significantly reduced the computational time, which was 10–13 times faster than the sequential Kmeans-FFA-KELM model (7.0–7.4 s), and 1185–1603 times faster than the FFA-KELM model (802.2–830.0 s). This study provides a new and fast modeling method for processing large datasets in agricultural and water resources studies on a regional scale.

Application of an artificial intelligence technique enhanced with intelligent water drops for monthly reference evapotranspiration estimation

Reference evapotranspiration (ET0) is one of the most important parameters, which is required in many fields such as hydrological, agricultural, and climatological studies. Therefore, its estimation via reliable and accurate techniques is a necessity. The present study aims to estimate the monthly ET0 time series of six stations located in Iran. To achieve this objective, gene expression programming (GEP) and support vector regression (SVR) were used as standalone models. A novel hybrid model was then introduced through coupling the classical SVR with an optimization algorithm, namely intelligent water drops (IWD) (i.e., SVR−IWD). Two various types of scenarios were considered, including the climatic data- and antecedent ET0 data-based patterns. In the climatic data-based models, the effective climatic parameters were recognized by using two pre-processing techniques consisting of τ Kendall and entropy. It is worthy to mention that developing the hybrid SVR-IWD model as well as utilizing the τ Kendall and entropy approaches to discern the most influential weather parameters on ET0 are the innovations of current research. The results illustrated that the applied pre-processing methods introduced different climatic inputs to feed the models. The overall results of present study revealed that the proposed hybrid SVR-IWD model outperformed the standalone SVR one under both the considered scenarios when estimating the monthly ET0. In addition to the mentioned models, two types of empirical equations were also used including the Hargreaves−Samani (H−S) and Priestley−Taylor (P−T) in their original and calibrated versions. It was concluded that the calibrated versions showed superior performances compared to their original ones.

Forecasting of Long-term Sugar Beet Water Requirement in the Middle Anatolia, Turkey

Turkey’s highest sugar beet (Beta vulgaris L.) cultivation area is the Konya basin where is located in Middle Anatolia region. Therefore, this area has socio-economic importance in this region. However, the area faces water scarcity due to less amount of precipitation and high evapotranspiration. Moreover, irrigation is a prerequisite for sugar beet cultivation. Therefore, irrigation management is a vital topic for the area. The Food and Agricultural Organization of the United Nations Penman-Monteith (FAO 56 PM) equation for estimating reference evapotranspiration (ETo) requires various meteorological data. Unfortunately, it is not possible to ease to reach all these input data. Hence, FAO56 proposes another method called Hargreaves – Samani (HS). Due to limited meteorological data, the HS method is employed for estimating ETo in the Konya basin. For this area, there is big ambiguity about crop evapotranspiration (ETc) and the net irrigation requirement (NIR) for sugar beet crop. This study estimates long-term (1986-2015) sugar beet evapotranspiration and net irrigation requirement to give a better idea for sugar beet irrigation management in the Konya basin. Results show that long-term annual sugar beet ETc reaches between 657 mm and 917 mm in the growing season. NIR ranges from 614 mm to 886 mm in the aforesaid basin.

New machine learning approaches to improve reference evapotranspiration estimates using intra-daily temperature-based variables in a semi-arid region of Spain

The estimation of Reference Evapotranspiration (ET0) is crucial to estimate crop water requirements, especially in developing countries and areas with scarce water resources. In these regions, the impossibility of collecting all the required data to compute FAO-56 Penman–Monteith equation (FAO56-PM) makes scientists search new methodologies to accurately estimate ET0 with the minimum number of climatic parameters. In this work, several neural network approaches have been evaluated for estimating ET0 using datasets from five weather stations located in Southern Spain (semiarid region of Andalusia). The assessment of statistical performance (Root Mean Square Error -RMSE-, Mean Bias Error -MBE-, coefficient of determination -R2- and Nash-Sutcliffe model efficiency coefficient -NSE-) of models namely Multilayer perceptron (MLP), Generalized Regression Neural Network (GRNN), Extreme Learning Machine (ELM), Support Vector Machines (SVM), Random Forest (RF) and XGBoost were carried out using different input variables configurations. Only temperature-based data were used as inputs; the calculation of new variables called EnergyT (the integral of the half hourly temperature values of a day) and Hourmin (the difference in hours between time sunset and the time when the maximum temperature occurs) had promising results for the most humid stations. The good results obtained with EnergyT when it is used as an input of the system demonstrated that the information contained on it gives detailed characterization of the daily thermic behavior at each location, resulting in a more efficient model than those using only daily maximum, minimum temperature and extraterrestrial radiation values. In general, the modeling results showed that no model firmly outperformed the others, although MLP and ELM were commonly the models that gave the best performances for all sites: mean values of R2 > 0.89, mean values of NSE > 0.88, mean values of RMSE < 0.67 mm/day and mean values of MBE ranging from −0.17 to 0.30 mm/day. Therefore, EnergyT and Hourmin can be used to estimate ET0 more accurately in stations where data acquisition is limited, like in developing countries or at low-cost weather stations that cannot collect all the required meteorological variables used in FAO56-PM. Overall, the use of ELM is recommended due to its high performance in terms of efficiency (NSE) for all the configurations and for all locations, especially using EnergyT as an input variable.

Monthly evapotranspiration estimation using optimal climatic parameters: efficacy of hybrid support vector regression integrated with whale optimization algorithm.

For effective planning of irrigation scheduling, water budgeting, crop simulation, and water resources management, the accurate estimation of reference evapotranspiration (ETo) is essential. In the current study, the hybrid support vector regression (SVR) coupled with Whale Optimization Algorithm (SVR-WOA) was employed to estimate the monthly ETo at Algiers and Tlemcen meteorological stations positioned in the north of Algeria under three different optimal input scenarios. Monthly climatic parameters, i.e., solar radiation (Rs), wind speed (Us), relative humidity (RH), and maximum and minimum air temperatures (Tmax and Tmin) of 14years (2000-2013), were obtained from both stations. The accuracy of the hybrid SVR-WOA model was appraised against hybrid SVR-MVO (Multi-Verse Optimizer), and SVR-ALO (Ant Lion Optimizer) models through performance measures, i.e., mean absolute error (MAE), root-mean-square error (RMSE), index of scattering (IOS), index of agreement (IOA), Pearson correlation coefficient (PCC), Nash-Sutcliffe efficiency (NSE), and graphical interpretation (time-variation and scatter plots, radar chart, and Taylor diagram). The results showed that the SVR-WOA model performed superior to the SVR-MVO and SVR-ALO models at both stations in all scenarios. The SVR-WOA-1 model with five inputs (i.e., Tmin, Tmax, RH, Us, Rs: scenario-1) had the lowest value of MAE = 0.0658/0.0489mm/month, RMSE = 0.0808/0.0617mm/month, IOS = 0.0259/0.0165, and the highest value of NSE = 0.9949/0.9989, PCC = 0.9975/0.9995, and IOA = 0.9987/0.9997 for testing period at both stations, respectively. The proposed hybrid SVR-WOA model was found to be more appropriate and efficient in comparison to SVR-MVO and SVR-ALO models for estimating monthly ETo in the study region.

Comparing the use of past and forecast weather data for estimating reference evapotranspiration

The reliability of short-term weather forecast provided by COSMO model in simulating reference evapotranspiration (ET0) was evaluated in 7 study sites distributed in 4 countries (Italy, Norway, Romania and Spain). The main objective of the study was to assess the optimal scenario for calculating ET0, using the FAO-56 Penman-Monteith (PM) equation, by separately considering the accuracy in the use of “past” and “forecast” data input. Firstly, each forecasted variable (air temperature, Tair; relative humidity, RH; wind speed, u2; solar radiation, Rs) and ET0 were compared with in situ observations at hourly and daily scales. Moreover the seasonality effect in the forecast performance was evaluated. Secondly, simulated ET0 were computed every three days with: (i) a “past scenario” that used the observed data input measured in situ during the previous three days, (ii) a “forecast scenario” that used the forecasted input variables for the next three days; and compared with (iii) actual ET0 obtained from the in situ measured data.A general good agreement was found between observed and forecasted agro-meteorological parameters at the different explored time-scales. The best performance was obtained for Tair and Rs, followed by RH and u2. Globally, the comparison between ET0 from the measured and forecasted data input showed high performance, with R2 and RMSE of 0.90 and 0.68 mm d−1. ET0 simulations resulted more accurate using the “forecast scenario” (1.7% overestimation), rather than using the “past scenario” (2.6% underestimation). These results open promising perspectives in the use of forecast for ET0 assessment for different agriculture practices and particularly for irrigation scheduling under water scarcity conditions.

Comparison of Performance of GLM, RF and DL Models in Estimation of Reference Evapotranspiration in Zabol Synoptic Station

Comparison of Performance of GLM, RF and DL Models in Estimation of Reference Evapotranspiration in Zabol Synoptic Station

Método de Penman-Monteith e Hargreaves-Samani para obtenção da ETo em ano chuvoso e seco

O planejamento e aproveitamento da água na produção agrícola, bem como o desenvolvimento de metodologias que permitam estimar o correto volume de água são fundamentais para o estabelecimento de planos eficientes de irrigação, evitando o desperdício. A evapotranspiração está diretamente relacionada ao consumo de água das plantas, desta forma, foram desenvolvidos diversos métodos para a determinação da evapotranspiração utilizando para isso, as variáveis meteorológicas. Dessa forma objetivou-se avaliar umas das metodologias mais utilizadas, que é o conhecida como método de Hargreaves-Samani para estimar a evapotranspiração de referência (ETo) em condições de baixa e elevada pluviosidade, utilizando como referência o método de Penman-Monteith-FAO56. Foram empregados dados de uma estação meteorológica automática pertencente à Universidade Federal Rural do Semi-Árido, em Mossoró (RN), os dados mencionados são referentes ao período de janeiro de 2011 a dezembro de 2012. A ETo foi estimada sendo considerada de uso prático, o modelo de Hargreaves-Samani que utiliza elementos meteorológicos de fácil obtenção como a temperatura, umidade relativa do are velocidade do vento, permitindo a estimativa da ETo é considerado de uso prático. Verificou-se que, as estimativas a partir do método de Hargreaves-Samani superestimaram os valores de ETo quando comparado com o método padrão em condições de elevada umidade para o ano de 2011, além de apresentar significância quanto a variável velocidade do vento, desta forma podendo ser fortemente influenciada por ela. Diante disso verifica-se a necessidade de calibração ou parametrização dos coeficientes da equação de Hargreaves-Samani como alternativa para uma melhor estimativa, principalmente para cidades com influência litorânea.

Generalized gene expression programming models for estimating reference evapotranspiration through cross-station assessment and exogenous data supply.

Adopting methodologies utilizing exogenous data from ancillary stations for determining crop water requirement is a suitable approach to exempt local shortcomings due to the lack of meteorological data/stations. Meanwhile, soft computing techniques might be suitable tools to be used with such data management scenarios. The present paper aimed at evaluating the generalizability of the gene expression programming (GEP) technique for estimating reference evapotranspiration (ET0) through cross-station assessment and exogenous data supply, using data from Turkey and Iran. The GEP-based models were established and learnt using data from 10 stations in Turkey, and then the developed models were tested (validated) in 18 stations of Iran with considerable latitude differences. Different time periods (beginning and the end of time series) were selected for the training and testing stations so that there was no overlap among the dates of the events in both the groups. A comparison was also performed between the GEP models and the corresponding commonly used empirical equations. The obtained results revealed that the generalized GEP models presented promising outcomes in simulating daily ET0 values when they were trained and tested in quite distant stations with different chronological periods of the applied parameters. The performance accuracy of the empirical equations calibrated using exogenous data was reduced in comparison with their original (non-calibrated) versions. Further, although the generalization ability of the GEP models was reduced when the climatic context of the training-testing stations was different, the overall performance accuracy of those models was higher than those of the commonly used classic empirical equations.

Comparative assessment of different reference evapotranspiration models towards a fit calibration for arid and semi-arid areas

The enhancement of water efficiency requires controlling the high demand for irrigated agriculture which depends on improving the capabilities to accurately simulate the water cycle and its components. Among these, evapotranspiration is widely studied to estimate reference evapotranspiration (ET0) but the performance and accuracy of the estimates vary. Moreover, these estimates require some hardly available or misrepresentative meteorological data which lead, mainly in arid and semi-arid areas, to errors and inaccuracies. Here, ET0 of five empirical temperature-based estimates are compared to the standard FAO Penman–Monteith estimate (ET0-PM) under the representative and wide-ranging settings of 22 weather stations of Morocco. We found a significant positive correlation between ET0-PM and solar radiation, average and maximum air temperatures. We have determined that the Dorji estimate shows relatively better precision and stability while it requires advanced calibration to accommodate arid and semi-arid conditions. After hundreds of calibration repetitions, we concluded a new estimate (ET0-Hadria) which demonstrates an overall improvement in the quality and precision of ET0 assessment, mainly in flat areas. This estimate improved the precision and enhanced the precision in almost 68% of the stations. This simple calibrated estimate is an accurate, improved, and transferable tool achieved through a precise methodical process of selection and configuration.

Efficiency of small pan evaporimeter in monitoring evapotranspiration under poly-covered house and open-field conditions in a hot, tropical region of Nigeria

Study RegionThis study was carried out in a hot, tropical region of southwest Nigeria. Study FocusThe study aimed to evaluate the efficiency of small pan evaporimeter in estimating evapotranspiration (ET) and compare with five reference evapotranspiration (ETo) estimation models of FAO56 Penman Monteith; Modified Penman; Thornthwaite; Blaney-Criddle, and Hargreaves under poly-covered house and open-field conditions grown to maize and tomato in two contrasting seasons. Small pan evaporimeters with diameter 24.5 cm and 11 cm high were constructed and installed to measure evaporation. The ETo from the empirical models was estimated using weather data downloaded from NASA website and a mini-weather station installed in the poly-covered house. A rain gauge was also installed to measure rainfall during the growing period. New hydrological insights for the regionThe small pan evaporation significantly (p < 0.05) correlated with the reference evapotranspiration obtained from the empirical ET models. Canopy cover was the driving force responsible for the reduced pan evaporation within the crop canopy. Temperature and relative humidity are the driving forces controlling evapotranspiration in the poly-house. The inexpensive small pan could complement conventional pans, empirical ETo models, remote sensing and others for quantifying evapotranspiration, which is essential not only for irrigation but also hydrologic studies and modelling of watersheds, catchments areas, agricultural fields and landscapes in this region and similar tropical and sub-tropical environments.

Performance evaluation of numerical and machine learning methods in estimating reference evapotranspiration in a Brazilian agricultural frontier

The reference evapotranspiration (ET0) estimates is important for water resources and irrigation management. The Penman-Monteith equation is known for its accuracy but requires a high number of climatic parameters that are not always available. Thus, this study aimed to evaluate the performance of machine learning techniques (cubist regression, artificial neural network with Bayesian regularization, support vector machine with linear kernel function) and stepwise multiple linear regression method to estimate daily ET0 with limited weather data in a Brazilian agricultural frontier (MATOPIBA). Climatic data from 2000 to 2016 obtained from 23 weather stations were used. Five data scenarios were evaluated: (i) all variables, (ii) radiation and temperature, (iii) temperature and relative humidity, (iv) wind speed and temperature, and (v) temperature. The results showed that the machine learning methods are robust in estimating ET0, even in the absence of some variables. Among the methods evaluated using only temperature data, the cubist regression showed better performance. When estimating water demand for soybean and maize crops using only temperature, the cubist regression and calibrated Hargreaves-Samani equation showed the smallest errors.

Assessing forecasting performance of daily reference evapotranspiration using public weather forecast and numerical weather prediction

Accurate estimation of reference evapotranspiration (ET0) is important for water resource management and irrigation scheduling design. Limited by data availability of the numerical weather prediction (NWP), the public weather forecasting (PWF) has been widely used to forecast daily ET0 in China. Recently, two Chinese independently developed NWP products have been open to the public, namely, the Global/Regional Assimilation and Prediction System (GRAPES) and the T639 Global Medium-term Numerical Forecast Model (T639L60). In this paper, the forecast of ET0 is evaluated based on the recently released NWP outputs and the PWF using the FAO-56 PM equation. The daily ET0 forecast of the two datasets was compared against the ET0 that was calculated using weather variables observed from 31 automatic weather stations across a wide range of climate zones in China, including the temperate continental zone (TC), temperate monsoon zone (TM), mountain plateau zone (MP) and subtropical monsoon zone (SM). The results showed that the forecast performance of NWP for maximum and minimum air temperature (Tmax, Tmin) was worse due to the large errors in the altitude estimation process. The forecast performance of NWP for net radiation (Rnet) forecasted was better than that of PWF in the MP, TC and TM, while slightly worse in the SM. The VPD from the NWP was more accurate in TC and TM, while showed little difference with that from PWF in MP and SM. For the wind speed (u2), the NWP showed better forecast accuracy than PWF in all climate zones. Furthermore, the better forecast performance of ET0 was obtained by the NWP in the MP and TC. In the TM and SM, the PWF can provide a more accurate ET0 forecast compared to the NWP. Overall, the NWP can serve as a promising data source to generate acceptable ET0 forecasts across China. The high spatial resolution of the NWP provides the ability to capture the high resolution of the spatial variability in ET0, especially in the MP and TC where weather stations are sparse.

INFLUENCE OF THE ESTIMATED GLOBAL SOLAR RADIATION ON THE REFERENCE EVAPOTRANSPIRATION OBTAINED THROUGH THE PENMAN-MONTEITH FAO 56 METHOD

Agriculture accounts for a significant portion of the state of Minas Gerais' GDP, which is one of the most productive Brazilian states in the agricultural sector. Given this scenario, it is essential to know the elements that affect agricultural productivity. The data manipulated in this work were obtained from the Network of Automatic Meteorological Stations (EMA's) from the National Institute of Meteorology (INMET) located in 51 cities from the State of Minas Gerais. There is a lack of studies to determine the most appropriate model to estimate evapotranspiration with less error in the state of Minas Gerais. Such studies are necessary because the state in question has different climatic and hydrological conditions. The objective of this paper was to evaluate whether the estimation of global solar radiation can influence the daily reference evapotranspiration by the Penman-Monteith FAO 56 method, for the state of Minas Gerais, Brazil. The estimated radiation data were applied to the Penman-Monteith FAO equation for reference evapotranspiration estimation, and these results were compared to the reference evapotranspiration data obtained by the Penman-Monteith FAO equation with radiation data measured at the stations. The performance indexes used were: Mean Relative Error (MRE), Root Mean Square Error (RMSE) and Willmott's d index. The solar radiation values used, when calibrated for the study site, tended to overestimate the evapotranspiration values, presented dispersion of 0.76 mm d-1 on average and the degree of precision of the calibrated models had an average of 0.65 mm d-1. The best solar radiation estimation model for the cities studied was the Thorton and Running model.

Swarm-based optimization as stochastic training strategy for estimation of reference evapotranspiration using extreme learning machine

Reference evapotranspiration (ET0) is usually calculated as a pre-requisite to obtain the actual evapotranspiration (ET). Estimation of ET0 using extreme learning machine (ELM) is a new norm due to its excellent computation efficiency and its lower data dependency. However, the lack of stochastic tuning often results in the convergence to the local optima instead of the global optimum. This study attempts to address this issue by hybridizing the ELM with three swarm-based optimization algorithms, namely the particle swarm optimization (PSO), the moth-flame optimization (MFO) and the whale optimization algorithm (WOA) with different fitness functions. This study was conducted with three stations in Sabah and Sarawak (states in East Malaysia) as this region is to a very large extent covered with oil palm plantation. The water resources management is thus rather crucial for the area. The results showed that the WOA-ELM achieved a higher average rank score relative to the PSO-ELM and MFO-ELM, especially when the simple Taylor skill score was used as the fitness function. The application of different fitness functions did not show any significant effect. The reported standard deviations of the mean absolute error (MAE), root mean square error (RMSE) and coefficient of determination (R2) for the three variations of the hybridized ELM were close to 0; thus reflecting their similarity in accuracy. However, in terms of computational efficiency, the simple Taylor skill score exhibited better stability where it could effectively reduce the number of required hidden neurons when the input meteorological parameters were decreased. The WOA was suggested as the best optimization algorithm for this study. For the three stations, respectively it achieved an average MAE, RMSE and R2 of 0.0007 to 0.1443, 0.0011 to 0.1927 and 1.0000 to 0.9486, from cases C1 to C6 with minimum time cost.

Modeling of reference evapotranspiration for temperate Kashmir Valley using linear regression

Reference evapotranspiration (ETO) estimation is a prerequisite for the estimation of evapotranspiration rates of different crops. There is global consensus on the consistency of the FAO-56 Penman–Monteith (FAO-56 PM) method, and it has lately become the first-choice for the estimation of ETO, but despite its consistent performance, other methods continue to be popular for their simple structure and data requirement, more so in field practice. In this study, regression models were developed for predicting monthly ETO using monthly averages of minimum temperature (Tmin), relative humidity (RH), wind speed (WS), and sunshine hours (SSH) for three stations in the temperate Kashmir Valley. The models are based on the ETO data generated using the FAO-56 PM method. The weather data required for the analysis were for a period of 20 years. The models were evaluated using the coefficient of determination (R2) and residual analysis. R2 values for the developed models were greater than 0.96. In addition to the ETO estimation, the developed models may also be used for trend evaluation in the ETO data in climatologically similar regions. In this study, for the cases of very limited data availability where the FAO-56 PM equation cannot be used, the Hargreaves and Samani (HAR) equation, which only uses temperature as an input, was calibrated for each station using linear regression between FAO-56 PM ETO and HAR ETO.

Uncertainty analysis of artificial intelligence modeling daily reference evapotranspiration in the northwest end of China

Accurate estimation of reference evapotranspiration (ET0) is of utmost importance for hydrological balance, global change and water resource management. However, caused by the insufficient meteorological data and indefinite input combination, uncertainties may exist in the simplified artificial intelligence (AI) models. Thus, determination the uncertainty is significant for accurate ET0 results. In this study, the validity of 29 combination scenarios of maximum and minimum temperature, wind speed, relative humidity, solar radiation, sunshine duration, and atmospheric pressure was examined by applying the artificial neural network (ANN), support vector regression (SVR), and extreme learning machine (ELM) models for the arid Altay Prefecture. Performances of the models were evaluated against the Penman-Monteith equation by coefficient of correlation (R), root mean squared error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NS) in testing period. The Monte Carlo (MC) technique was firstly performed to analyze the sensitivity of the meteorological parameters and the uncertainty of the AI models. The results confirmed the indispensable role of temperature and the predominant function of the aerodynamic part in evapotranspiration process. An input pattern, which is able to reveal the physical mechanism of AI models in ET0 estimation, was proposed innovatively. Both the SVR and ELM models are highly recommended for ET0 estimation due to the comparable simulating ability and lower uncertainty. The findings help to understand the implied intrinsic mechanism of evapotranspiration in AI models and can be regarded as a breakthrough in ET0 modeling.

An evaluation of gridded weather data sets for the purpose of estimating reference evapotranspiration in the United States

This study assessed the quality of gridded weather data for calculating reference evapotranspiration (ETref), which, by definition, represents a near maximum ET occurring in a well-watered agricultural environment. Six gridded weather data sets – GLDAS-1, NLDAS-2, the CFSv2 operational analysis, gridMET, RTMA, and NDFD – were compared to weather data collected from 103 weather stations located in well-watered settings across the conterminous United States. ETref along with the weather variables used to compute it – near-surface air temperature, vapor pressure, wind speed, and shortwave solar radiation – were compared.The gridded weather data sets generally overestimated the standardized Penman-Monteith ETref produced from weather station data, with median biases ranging from 12 to 31 %. The overestimation was mainly due to chronic overstatement of air temperature, shortwave radiation, and wind speed and understatement of humidity. These results indicate that gridded data should be carefully evaluated before being substituted for agricultural weather station data. Bias correction procedures may make these gridded data more suitable for generating ETref.RTMA was generally the best performing gridded data set for all variables and NLDAS was the worst for all variables except vapor pressure. NDFD one-day forecasts outperformed most of the analysis products, likely due to its initialization with RTMA. gridMET temperature agreed relatively well with the station data due to its dependence on the PRISM station-interpolated data set. However, its performance was similar to its other parent product, NLDAS, for the remaining variables which reduced its ETref performance. The low-resolution products GLDAS and CFSv2 performed better than the finer resolution NLDAS product suggesting that spatial resolution is not a primary factor determining correspondence to station data. The excellent performance of gridMET temperature and RTMA indicates that the degree to which gridded data depend on station data is a primary factor determining correspondence.

Supplanting missing climatic inputs in classical and random forest models for estimating reference evapotranspiration in humid coastal areas of Iran

Although evapotranspiration might not be a limiting factor for water consumption in humid regions, it is a very important parameter in irrigation scheduling and agricultural water management in those regions, and should be estimated with high accuracy. The reference evapotranspiration (ETo) concept is a way for retrieving the actual crop water requirements using a crop coefficient. The standard procedure for determining ETo values in literature is the Penman-FAO-Monteith (PFM) equation, which needs considerable meteorological inputs. In practice, when all necessary data of PFM are not available, the consideration of estimated meteorological inputs for this equation might be a suitable approach for deriving accurate ETo values. Further, the empirical ETo equations and machine learning techniques relying on fewer meteorological variables are usually employed as alternatives to the PFM equation. The present paper aimed at assessing the effect of considering calculated missing meteorological variables on the performance accuracy of the standard PFM and some commonly used empirical equations using daily data from six humid coastal locations in Iran covering a period of 10 years. Moreover, the machine learning bootstrap aggregating-based random forest (RF) technique was applied under the same conditions. Based on the obtained results, when replacing missing inputs by calculated ones, the combination-based models (relying on estimated wind speed values) provided the most accurate results, while using estimated solar radiation values reduced the model’s performance accuracy.

Spatio‐temporal calibration of Hargreaves‐Samani model to estimate reference evapotranspiration across U.S. High Plains

AbstractTemperature‐based grass‐reference evapotranspiration (ETo) estimation methods (e.g., Hargreaves−Samani [HS] model) present advantages over combination‐based methods that require full‐suite weather data. The U.S. High Plains region has scarce and short‐term full‐suite weather sites. This data scarcity presents challenges for combination‐based ETo estimation. The performance of HS model against the American Society of Civil Engineers (ASCE) standardized Penman−Monteith (PM) model was assessed using long‐term data at 124 full‐suite weather sites across nine states in the U.S. High Plains. The HS model underestimated ETo at arid (mean bias error [MBE] = −1.68 mm d−1), semi‐arid (MBE = −0.34 mm d−1), and dry subhumid sites (MBE = −0.16 mm d−1) and overestimated ETo at humid sites (MBE = 0.14 mm d−1). There was a significant relationship (p &lt; .01) between HS model performance and aridity index. The HS model performed better (27% lower root mean squared difference [RMSD]) in summer months than the rest of the year at semi‐arid and dry subhumid sites. The model performance was non‐ideal during the summer months in subhumid climates. Spatio‐temporal annual zonal (climate division), monthly zonal, annual site‐specific, and monthly site‐specific calibration resulted in 12, 16, 20, and 26% reduction in RMSD and 11, 16, 17, and 23% reduction in relative error, respectively. Monthly site‐specific calibration performed the best and was used to quantify annual and growing season ETo across the region. The research characterized performance patterns of the HS model over an important agroecosystem‐dominated region. Practical data‐driven strategies were proposed to better estimate PM ETo using limited weather data at any given site (with similar aridity) and time of the year.