Explore the vast range of titles available.

Affordable and efficient agricultural methods enhance crop yield and water management by optimizing resources. Precise irrigation relies on accurate estimation of reference evapotranspiration ( ET o ). Numerous analytical and empirical methods exist to compute ET o but these methods are costlier, requires time and perform poorly under limited availability of meteorological data. This study first evaluated the performances of three deep learning sequential models—Long short-term memory (LSTM), Neural Basis Expansion Analysis for Time Series (N-BEATS) and, Temporal Convolutional Network model (TCN), for predicting daily ET o possessing temporal characteristics. In this TCN is considered as baseline model to be compared with other models. In the results, TCN performed better, so it is further utilized to evaluate two strategies of ET o prediction that makes the second objective of the paper. In the first approach, historic data is used to predict future ET o using TCN which is standard method. And, in recursive approach, TCN predicted climatological data and, ET o is computed. This is required for better irrigation planning in data-scarce situations. The results demonstrate that the TCN model provided satisfactory performance with the Nash–Sutcliffe Efficiency (NSE) = 0.99, Theil U2 = 0.005, RMSE = 0.092 and, MAE = 0.048. Also, with the recursive strategy, ET o values computed found more accurate than using standard approach. Thus, comparative study among sequential architecture revealed TCN outperformed LSTM and N-BEATS models and, is an efficient method for predicting ET o time-series and, could also assist in the precise management of water resources in data scarcity.

Estimating daily evapotranspiration is challenging when ground observation data are not available or scarce. Remote sensing can be used to estimate the meteorological data necessary for calculating reference evapotranspiration ETₒ. Here, we assessed the accuracy of daily ETₒ estimates derived from remote sensing (ETₒ-RS) compared with those derived from four ground-based stations (ETₒ-G) in Kurdistan (Iraq) over the period 2010–2014. Near surface air temperature, relative humidity and cloud cover fraction were derived from the Atmospheric Infrared Sounder/Advanced Microwave Sounding Unit (AIRS/AMSU), and wind speed at 10 m height from MERRA (Modern-Era Retrospective Analysis for Research and Application). Four methods were used to estimate ETₒ: Hargreaves–Samani (HS), Jensen–Haise (JH), McGuinness–Bordne (MB) and the FAO Penman Monteith equation (PM). ETₒ-G (PM) was adopted as the main benchmark. HS underestimated ETₒ by 2%–3% (R2 = 0.86 to 0.90; RMSE = 0.95 to 1.2 mm day−1 at different stations). JH and MB overestimated ETₒ by 8% to 40% (R2= 0.85 to 0.92; RMSE from 1.18 to 2.18 mm day−1). The annual average values of ETₒ estimated using RS data and ground-based data were similar to one another reflecting low bias in daily estimates. They ranged between 1153 and 1893 mm year−1 for ETₒ-G and between 1176 and 1859 mm year−1 for ETₒ-RS for the different stations. Our results suggest that ETₒ-RS (HS) can yield accurate and unbiased ETₒ estimates for semi-arid regions which can be usefully employed in water resources management.

The crop coefficient (Kc) values given in FAO-56 report need to corrected for local conditions due to differences in climate, soil types, and water management practices. Therefore, present study was undertaken to develop growth-stage-specific Kc values of wheat grown under drip irrigated conditions for two years (2022-23 and 2023-24) at Jalandhar, Punjab. The developed Kc values are 0.36, 0.77, 1.05, 0.69, and 0.25 during initial, development, mid, late, and end growth stages, respectively. These average Kc values can be effectively utilized to schedule irrigation for drip-irrigated wheat crops in the Jalandhar region of Punjab. Irrigating wheat crop under drip irrigation with developed Kc values not only enhances grain yield by 36% but also improves IWUE by three times and saves 61% use of irrigation water as compared to conventional irrigation practices (flood irrigation).

Accurate estimation of daily reference evapotranspiration (ETo) is crucial for sustainable water resource management and irrigation scheduling, especially in water-scarce regions like Arizona. The standardized Penman–Monteith (PM) method is costly and requires specialized instruments and expertise, making it generally impractical for commercial growers. This study developed 35 ETo models to predict daily ETo across Coolidge, Maricopa, and Queen Creek in Pinal County, Arizona. Seven input combinations of daily meteorological variables were used for training and testing five machine learning (ML) models: Artificial Neural Network (ANN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Support Vector Machine (SVM). Four statistical indicators, coefficient of determination (R2), the normalized root-mean-squared error (RMSEn), mean absolute error (MAE), and simulation error (Se), were used to evaluate the ML models’ performance in comparison with the FAO-56 PM standardized method. The SHapley Additive exPlanations (SHAP) method was used to interpret each meteorological variable’s contribution to the model predictions. Overall, the 35 ETo-developed models showed an excellent to fair performance in predicting daily ETo over the three weather stations. Employing ANN10, RF10, XGBoost10, CatBoost10, and SVM10, incorporating all ten meteorological variables, yielded the highest accuracies during training and testing periods (0.994 ≤ R2 ≤ 1.0, 0.729 ≤ RMSEn ≤ 3.662, 0.030 ≤ MAE ≤ 0.181 mm·day−1, and 0.833 ≤ Se ≤ 2.295). Excluding meteorological variables caused a gradual decline in ET-developed models’ performance across the stations. However, 3-variable models using only maximum, minimum, and average temperatures (Tmax, Tmin, and Tave) predicted ETo well across the three stations during testing (17.655 ≤ RMSEn ≤ 13.469 and Se ≤ 15.45%). Results highlighted that Tmax, solar radiation (Rs), and wind speed at 2 m height (U2) are the most influential factors affecting ETo at the central Arizona sites, followed by extraterrestrial solar radiation (Ra) and Tave. In contrast, humidity-related variables (RHmin, RHmax, and RHave), along with Tmin and precipitation (Pr), had minimal impact on the model’s predictions. The results are informative for assisting growers and policymakers in developing effective water management strategies, especially for arid regions like central Arizona.

Accurate estimation of evapotranspiration of rapeseed is essentially required for irrigation scheduling and water management. The present study was undertaken during 2015-16 and 2017-18 in ICR Farm, Assam Agricultural University, Jorhat to determine the crop coefficients (Kc) and estimate evapotranspiration of rapeseed using lysimeter and eight reference evapotranspiration models viz. Penman-Monteith, Advection-Aridity (Bruitsaert-Strickler), Granger-Gray, Makkink, Blaney-Criddle, Turc (1961), Hargreaves-Somani and Priestly-Tailor models. During 2015-16, the crop coefficients were developed by these models. Actual evapotranspiration was determined by three weighing type lysimeters. During 2017-18, evapotranspiration was estimated by multiplying reference evapotranspiration with Kc derived by different models and compared with actual evapotranspiration estimated by lysimeter during similar growing periods. All the models except Turc (1961) showed less than 10% deviation between actual and estimated ET. The estimated evapotranspiration using Penman-Monteith and Priestly-Tailor reference evapotranspiration recorded the lowest MAE and RMSE. The study revealed that estimated evapotranspiration using Penman-Monteith reference evapotranspiration gave the best estimate of evapotranspiration of rapeseed followed by Priestly-Tailor. The crop coefficients for initial, mid and end stages were 0.83, 1.20 and 0.65, respectively for Penman-Monteith and 0.70, 1.05 and 0.55, respectively for Priestly-Tailor.These results can be used for efficient management of irrigation water for rapeseed.

Reference Evapotranspiration (ET0) is an essential factor in irrigation scheduling, climate change studies, and drought assessment. The study's main objective was to identify the influences of detrending input climatic parameters (CPs) on ET0 using linear and nonlinear approaches throughout 1980–2015 in Gangtok, East Sikkim, India. The benchmark values of ET0 were calculated using the global standard FAO56 Penman–Montieth equation. The ET0-related CPs included for the analysis are maximum temperature (Tmax), minimum temperature (Tmin), maximum relative humidity (RHmax), minimum relative humidity (RHmin), and sunshine duration (SSH). The linear and nonlinear trends in various CPs affect ET0 change. Linearly detrended series was obtained by linear regression method whereas, nonlinearly detrended series was obtained using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method. Twenty-three scenarios, including the original scenario, 11 scenarios in Group 1 (CPs de-trended linearly), and 11 scenarios in Group 2 (CPs de-trended nonlinearly) were generated. Influences of Tmax and SSH were more substantial than the influences of other CPs for both Group 1 and Group 2. The SSH masked the weak influence of other CPs. The effects of the trends in CPs, especially of SSH and Tmax, were clearly shown. The ET0 values decreased significantly during 1980–2015; however, no significant decreasing trend was observed in the case of SSH, during the same period. The nonlinear detrending gave closer results to the benchmark values as compared to linear detrending because of non-monotone variations of the ET0 and CPs. Therefore, the results from nonlinear detrending were more plausible as compared to linear detrending. The diminishing trend of ET0 prompted an overall alleviation of the dry spell, hence there would be a somewhat lower risk of water use in the study region.

For irrigation scheduling and better management of the water, estimation of irrigation water requirement of the crop is essentially required. The study was conducted for estimation of daily reference evapotranspiration (ETo) by FAO Penman-Monteith method using 30 years (1985-2015) mean meteorological data of two locations Sabour (zone III A) and Patna (zone III B) in Bihar. The crop evapotranspiration was estimated using crop coefficients of different crops like rice,kharif maize, wheat, rabi maize, green gram and summer maize at Sabour and Patna locations. Irrigation water requirement for different crops was estimated based on crop evapotranspiration and effective rainfall during the growing period of the crop. The mean annual reference evapotranspiration (ETo) was found 3.6 mmday-1 at Sabour and 4.1 mmday-1 at Patna. The total crop evapotranspiration was maximum for rice crop in kharif season 546.0 and 607.3 mm at Sabour and Patna respectively and lowest for wheat crop in rabi season 212.9 mm and 243.3 mm at Sabour and Patna respectively. Net irrigation water requirement was maximum for summer maize366.3at Sabour and 508.2 mm at Patna for rice crop whereas lowest in kharif maize 67.5 and 161.4 mm at Sabour and Patna respectively.

The reference evapotranspiration (ETo) is an important agrometeorological parameter which has been used in a number of applications. In present study daily ETo was determined for 16 stations of Gujarat having long period (10-20 years) weather data following P-M approach. The Kc values for maize and wheat as given in FAO-56 was used in which Kcmid and Kcend were corrected for climatic conditions of stations. The corrected Kc values were used to calculate the daily crop water requirement (ETc) for wheat and rabi maize crops grown at different locations of Gujarat. The results revealed that during winter season (Nov. 15 to March 13) the mean daily (ETo) varies from 4.2 to 7.6 mm day-1. However the large variation in ETo across the locations (2.9 to 9.8 mm day-1) was observed, the lowest being at Khedbrahma and highest being at Targadia. The correction applied in Kcmid and Kcend suggested that at most of the stations Kcmid and Kcend for wheat crop were higher than that of FAO values while the corrected Kc values for maize were found to be less than that given by FAO. The mean water requirement (ETc) of wheat during its initial stage was found to be lower and almost constant and it increased continuously during developmental stage (from 1.9 to 5.2 mm day-1) and during the mid season stage (from 5.6 to 7.5 mm day-1) and decreased during the late-season stage (from 7.3 to 3.6 mm day-1). The seasonal water requirement across the locations varies between 400.5 mm (Khedbrahma) to 684.0 mm (Arnej). The mean water requirement of maize during initial stage is 1.3 mm day-1, during developmental stage 1.4 to 5.0 mm day-1, during the mid season stage ETc varies between 5.0 to 6.6 mm day-1 and during lateseason stage it decreases from 6.4 to 2.5 mm day-1 . The seasonal water requirement of rabi maize varies between 330.7 mm (Khedbrahma) to 520.5 mm (Bharuch). 

The need for accurate estimates of reference crop evapotranspiration (ETo) is important in irrigation planning and design, irrigation scheduling, reservoir management among other applications. ETo can be accurately determined using the internationally accepted FAO Penman–Monteith (FAO-56 PM) equation. However, this requires numerous observed data, including solar radiation, air temperature, relative humidity, and wind speed, which in most cases are unavailable, particularly in developing countries such as the Philippines. This study developed models based on Support Vector Machines (SVMs) and Extreme Learning Machines (ELMs) for the estimation of daily ETo using different input combinations of meteorological data in Region IV-A, Philippines. The performance of machine learning models was compared with the different established alternative empirical models for ETo. The results show that the SVM and ELM models, with at least Tmax, Tmin, and Rs as inputs, provide the best daily ETo estimates. The accuracy of machine learning models was also found to be superior compared to the empirical models given with same input requirements. In general, SVM and ELM models showed similar modeling performance, although the former showed lower run time than the latter.

In this study, the predictive power of three different machine learning (ML)-based approaches, namely, multi-gene genetic programming (MGGP), M5 model trees (M5Tree), and K-nearest neighbor algorithm (KNN), for long-term monthly reference evapotranspiration ( ET 0 ) prediction were investigated. The input data consist of monthly solar radiation ( R s ), maximum air temperature ( T max ), and wind speed ( W s ) derived from 163 meteorological stations in Turkey. Different input combinations were created and analyzed. The model’s performance was evaluated using criteria such as Nash–Sutcliffe efficiency, Kling-Gupta efficiency, relative root mean squared error, mean absolute percentage error, and determination coefficient. Moreover, Taylor, radar, and boxplot diagrams were created. It was determined that the MGGP model outperformed both the M5Tree and the KNN models. The equation obtained from the MGGP model, for the best-performed combination of R s - T max - W s , was presented. The best weather conditions were obtained as 0.029 to 31.814 MJ/m 2 , − 5.8 to 45.7 °C, and 0.140 to 5.086 m/s for R s , T max , and W s , respectively. It was also found that the R s was the most potent input variable for ET 0 estimation while W s was the weakest.