Penman-Monteith Research Articles

Estimation of Reference Evapotranspiration in a Semi-Arid Region of Mexico.

Reference evapotranspiration (ET0) is the first step in calculating crop irrigation demand, and numerous methods have been proposed to estimate this parameter. FAO-56 Penman-Monteith (PM) is the only standard method for defining and calculating ET0. However, it requires radiation, air temperature, atmospheric humidity, and wind speed data, limiting its application in regions where these data are unavailable; therefore, new alternatives are required. This study compared the accuracy of ET0 calculated with the Blaney-Criddle (BC) and Hargreaves-Samani (HS) methods versus PM using information from an automated weather station (AWS) and the NASA-POWER platform (NP) for different periods. The information collected corresponds to Module XII of the Lagunera Region Irrigation District 017, a semi-arid region in the North of Mexico. The HS method underestimated the reference evapotranspiration (ET0) by 5.5% compared to the PM method considering the total ET0 of the study period (26 February to 9 August 2021) and yielded the best fit in the different evaluation periods (daily, 5-day mean, and 5-day cumulative); the latter showed the best values of inferential parameters. The information about maximum and minimum temperatures from the NP platform was suitable for estimating ET0 using the HS equation. This data source is a suitable alternative, particularly in semi-arid regions with limited climatological data from weather stations.

Advanced machine learning-based kharif maize evapotranspiration estimation in semi-arid climate.

Accurate Crop Evapotranspiration (ETc) estimation is crucial for understanding hydrological and agrometeorological processes, yet it's challenged by multiple parameters, data variations, and lack of continuity. These limitations restrict numerical methods application. To address this, the study aims to develop and assess ML models for daily maize ETc in semi-arid areas, utilizing varied weather inputs. Five ML models viz., Category Boosting (CB), Linear Regression (LR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Stochastic Gradient Descent (SGD) were developed and validated for the ICAR-IARI, New Delhi, Research Station. Penman-Monteith (PM) model estimated ETc values are used as the standard for comparing the performance of the ML model values. Results revealed that the SVM model achieved the highest coefficient of determination (R2) among all models, with a value of 0.987. Furthermore, the SVM model exhibited the lowest model errors (MAE = 0.121 mm day-1, RMSE = 0.172 mm day-1, and MAPE = 4.37%) compared to other models. The ANN model also demonstrated promising results, comparable to the SVM model. Notably, the wind speed parameter was found most influential input parameter. In conclusion, SVM or ANN could be considered reliable alternative methods for the accurate estimation of kharif maize crop ETc in the semi-arid climate.

Comparison of surface resistance‐based models for estimating maize evapotranspiration in a humid region of China

AbstractAccurate simulation of evapotranspiration (ET) is essential to enhance efficient irrigation management in the maize field. Here, we evaluated the performance of four mathematical models for estimating the ET of maize. The four models based on surface resistance calculate ET from different vapor sources, which are Penman‐Monteith (PM) through the “big leaf” model, the Shuttleworth‐Wallace (SW) model for distinguishing between soil and canopy, the clumping (C) model for distinguishing between canopy, soils under the canopy and bare soil, and the seasonal clumping (Cj) model for dividing ET into transpiration of sunlit leaves and shaded leaves, evaporation of bare soil surface, sunlit soil surface of canopy gap fraction, and canopy shaded soil surfaces. The models were calibrated by ET measured from a weighing lysimeter, transpiration by the sap flux method, and soil evaporation by micro‐lysimeters in 2014, 2015, and 2017. Results showed that the measured daily transpiration was 3.32 mm/day during the full‐grown stage of maize, and the mean measured daily soil evaporation was 1.46 mm/day. The performance of the sap flow for transpiration plus micro‐lysimeter for soil evaporation method was consistent with the large‐weighted lysimeter method in measuring daily ET. For simulating versus measuring hourly transpiration, the Cj model performed better than the C model with a slope of 0.94, determination coefficient (R2) of 0.85, mean absolute error (MAE) of 0.08 mm/h, and modified agreement index (d) of 0.81. In simulating daily soil evaporation, the Cj model also had a higher slope and less MAE than the C and SW models. Nevertheless, the Cj model yielded increased slope and d and decreased MAE between simulated and measured daily ET. The most sensitive environmental factor in the Cj model is temperature. With a 50% increase in temperature, ET, transpiration, and evaporation increase by 45%, 36%, and 69%, respectively. In summary, the Cj model improved the accuracy for hourly and daily ET of maize and helped separate plant transpiration and soil evaporation, thus giving an available approach for precision irrigation in water management of maize planting systems.

Assessing water stress in a high-density apple orchard using trunk circumference variation, sap flow index and stem water potential.

Automated plant-based measurements of water stress have the potential to advance precision irrigation in orchard crops. Previous studies have shown correlations between sap flow, line variable differential transform (LVDT) dendrometers and fruit tree drought response. Here we report season-long automated measurement of maximum daily change in trunk diameter using band dendrometers and heated needles to measure a simplified sap flow index (SFI). Measurements were made on two apple cultivars that were stressed at 7 to 12 day intervals by withholding irrigation until the average stem water potential (ΨStem) dropped below -1.5 MPa, after which irrigation was restored and the drought cycle repeated. Dendrometer measurements of maximum daily trunk shrinkage (MDS) were highly correlated (r² = 0.85) with pressure chamber measurements of stem water potential. The SFI measurements were less correlated with stem water potential but were highly correlated with evaporative demand (r² = 0.82) as determined by the Penman-Monteith equation (ETr). The high correlation of SFI to ETr suggests that high-density orchards resemble a continuous surface, unlike orchards with widely spaced trees. The correlations of MDS and SFI to ΨStem were higher during the early season than the late season growth. Band dendrometers are less labor intensive to install than LVDT dendrometers and are non-invasive so are well suited to commercialization.

Assessment of the Correction of the Reference Evapotranspiration at Nonirrigated Weather Stations Affected by Aridity and Delimitation of the Meteorological Conditions that Limit its Implementation

As most reference crop evapotranspiration (ETref) estimates are computed from weather stations located outside irrigated plots, the site aridity can produce ETref overestimation. To obtain more reliable ETref estimates, the potential of using the methodology that corrects the observed air and dew point temperatures was first analyzed in this study, and the meteorological conditions that limit this methodology implementation were subsequently assessed. A statistical analysis was conducted of pairwise comparisons between a station under reference conditions (Montañana) and four nearby stations affected by aridity in Spain for 2020. The daily reference evapotranspiration was calculated with the FAO56 Penman–Monteith equation (ETo PM), and afterward, the corrected daily reference evapotranspiration (ETo PMcor) was obtained using the previously mentioned correction methodology. The statistical analysis showed a greater connection between ETref and ETo PMcor in all pairwise comparisons, with the strongest connection reached between ETref Montañana station and ETo PMcor Pastríz station (coefficient of determination r2 = 0.98 and root mean square error RMSE = 0.34 mm/day.). This ETo PM correction methodology was established considering a difference between the minimum temperature (Tmin) and the dew point temperature (Tdew) greater than 2 °C, as this value is considered the benchmark of aridity, but this research found that high aridity (P/ETo < 0.5) inland locations and high aridity coastal locations with high relative humidity (RH), markedly as of 61.5% and 68%, respectively, could exhibit days where Tmin-Tdew < 2 °C does not reflect well-watered soil and healthy grass but rather high RH levels (r2 = 0.77 and 0.57, respectively). As this correction methodology was not established considering Tmin-Tdew values smaller than 2 °C, the application scope of this methodology is limited under the above scenarios.

Estimating evapotranspiration from soil moisture using the improved soil water balance method in cold mountainous areas

Evapotranspiration (ET) is critical for ecosystem protection and water services, especially in the mountainous areas of arid and semi-arid watersheds. The lysimeter and Eddy Covariance (EC) methods are widely used for directly measuring ET, but are difficult to install and apply in mountainous areas with complex topography. The commonly used indirect methods for estimating ET, such as the Penman-Monteith (PM) method, present significant challenges in mountainous areas with scarce data. The simple soil water balance (SWB) method, which estimates ET from soil moisture dynamics, is another reliable and simple method for estimating ET. However, a drawback of the original SWB method is that it assumes soil moisture depletion only occurs through ET, ignoring the process of deep percolation. This restriction limits the applicability of the SWB method. In this study, we improve the SWB method (ISWB) by incorporating a deep percolation module into the soil water balance equation. Subsequently, we compare the estimated ET obtained from the ISWB, the Food and Agriculture Organization (FAO)-56 PM, and the Hargreaves-Samani (HS) methods with the observed ET. Results show that the ISWB method for estimating ET performs better when using the soil moisture of the 0–25 cm and below layers, compared to the 0–20 cm and above layers. Meanwhile, there is no significant difference in performance between using the soil moisture of the 0–25 cm layer and the soil layers below 25 cm. In addition, ignoring interception evaporation has an obvious influence on ET estimation using the ISWB. Furthermore, the comparison indicated that the performance of the ISWB method is superior to that of the FAO-56 PM and HS methods in the study areas. Our study shows that the ISWB method has significant potential for ET estimation in data-scarce and topographic-complex mountainous areas.

Empirical insights on the use of sun-induced chlorophyll fluorescence to estimate short-term changes in crop transpiration under controlled water limitation

Knowledge of actual crop transpiration (T) is important for advanced crop management but challenging to obtain due to the large spatial and temporal variation of T. Remote sensing offers various possibilities to assess T dynamics, while particularly sun-induced chlorophyll fluorescence (SIF) has been demonstrated as a sensitive empirical proxy for T. Despite this success, the advancement of the mechanistic understanding of how SIF relates to T dynamics is key for the future development and implementation of robust and reliable SIF-based T products. This study aims to contribute insights by experimentally assessing the sensitivity of several SIF-based T estimation strategies for evolving soil water limitation. We investigated extensive in situ and airborne data acquired during a water limitation experiment in a maize canopy in northern Italy. We evaluated five empirical strategies to integrate SIF in a T modelling framework based on the Penman-Monteith (PM) and the Ball-Berry-Leuning (BBL) concepts. Our results indicate that replacing model parameters sensitive to canopy conductance with SIF results in the best agreement between modelled and measured T under evolving water limitation. Our study contributes expanding existing knowledge with empirical insights on the sensitivity of SIF based T approaches under increasing soil water limitation at short time scales.

Evaluating the Impact of Future Seasonal Climate Extremes on Crop Evapotranspiration of Maize in Western Kansas Using a Machine Learning Approach

Data-driven technologies are employed in agriculture to optimize the use of limited resources. Crop evapotranspiration (ET) estimates the actual amount of water that crops require at different growth stages, thereby proving to be the essential information needed for precision irrigation. Crop ET is essential in areas like the US High Plains, where farmers rely on groundwater for irrigation. The sustainability of irrigated agriculture in the region is threatened by diminishing groundwater levels, and the increasing frequency of extreme events caused by climate change further exacerbates the situation. These conditions can significantly affect crop ET rates, leading to water stress, which adversely affects crop yields. In this study, we analyze historical climate data using a machine learning model to determine which of the climate extreme indices most influences crop ET. Crop ET is estimated using reference ET derived from the FAO Penman–Monteith equation, which is multiplied with the crop coefficient data estimated from the remotely sensed normalized difference vegetation index (NDVI). We found that the climate extreme indices of consecutive dry days and the mean weekly maximum temperatures most influenced crop ET. It was found that temperature-derived indices influenced crop ET more than precipitation-derived indices. Under the future climate scenarios, we predict that crop ET will increase by 0.4% and 1.7% in the near term, by 3.1% and 5.9% in the middle term, and by 3.8% and 9.6% at the end of the century under low greenhouse gas emission and high greenhouse gas emission scenarios, respectively. These predicted changes in seasonal crop ET can help agricultural producers to make well-informed decisions to optimize groundwater resources.

Management of irrigation water in Al-Baha, Saudi Arabia, using a simple alternative to the Penman–Monteith equation

Estimating reference crop evapotranspiration (ETo) is very important in the planning and scheduling of irrigation water. A simple method for the estimation of ETo is needed, with fewer meteorological factors that are required for estimation using the Penmen–Monteith equation (PME). The aim of this study was to manage irrigation water in the Al-Baha region of Saudi Arabia using a simple equation to estimate ETo based on air temperature as an effective alternative to the PME. Four simple temperature-dependent equations proposed by Thornthwaite, Blaney-Criddle, Hamon and Linacre were selected for analysis. Of these four equations, the Linacre equation (LE) was found to be best for estimating ETo. Although the ETo rate was overestimated when using the LE compared with the PME, it had the lowest error percentage (9.55%) and the highest R2 (0.97). After deducing a new and accurate equation based on the LE with the ability to estimate the ETo rate, the modified LE produced values closest to the results obtained using the PME for the Al-Baha region. It can thus be relied upon for estimating irrigation needs in the Al-Baha region with the irrigation systems used in the region.

Estimation of daily evapotranspiration in gully area scrub ecosystems on Loess Plateau of China based on multisource observation data

Evapotranspiration is an important process in the hydrologic cycle. In this study, different types of daily evapotranspiration were accurately estimated and comparatively analyzed for 2020–2021 in the gully area of Loess Plateau, China with multisource observation data. The daily actual evapotranspiration was directly observed by the eddy covariance system and then compared with the daily evapotranspiration simulated by HYDRUS-1D, and they showed reasonable agreement and similar variability characteristics it with a correlation coefficient of 0.71. The FAO-56 Penman-Monteith equation was used to calculate the reference evapotranspiration and compared with the pan evaporation in the study area. The reference evapotranspiration has a single-peak pattern and seasonal variation, similar to the actual evapotranspiration process during the annual period. The crop coefficient had seasonal-variation characteristics and remained 0.8 in the mid-growth period. The correlation analysis between evapotranspiration and environmental factors at different time scales suggested that energy was the dominant factor affecting evapotranspiration in the study area. The validation results of the complementary relationship of evaporation indicated a significant asymmetric complementary relationship in the study area. Both generalized nonlinear complementary relationship functions have good applicability, but the performance of the sigmoid function was slightly better than that of the polynomial function. The results provided a reference for local water resource management and agricultural production.

Performance evaluation of simpler reference crop evapotranspiration estimation equations with and without local calibration

The present study was taken up to demonstrate an overall methodology for local calibration of simpler reference crop evapotranspiration (ET0) estimation equations relative to the physically-based, albeit more data-intensive Penman-Monteith (PM) method. Climate records for the historical period 2006-2016 of 67 stations located across 10 agro-climatic zones of Karnataka State, India, were used for this purpose. The numerical coefficients in the original forms of the simpler equations namely, Blaney-Criddle (BC), Priestley-Taylor (PT), Radiation (RAD), and Turc (TC) were treated as unknown parameters and optimized for each station using PM ET0 estimates as reference. Results of local calibration indicated significant improvement in prediction accuracies and bias reduction for all the equations with the calibrated PT equation exhibiting the best performance. Spatial maps depicting the variations in the optimal values of parameters were developed to aid the accurate estimation of monthly ET0 values in the study area using only minimal climate inputs.

Changes in aridity and its impact on agricultural lands in East Asia for 1.5 and 2.0 °C temperature rise scenarios

This study aimed to assess the changes in aridity in East Asia (EA) over the next 80 years for the restriction of global warming based on Paris Agreement goals. Eight General Circulation Models (GCMs) that provide simulations for 1.5 and 2.0 °C global warming scenarios were used for this purpose. The Penman-Monteith Equation was utilized to calculate potential evapotranspiration (PET). The land-use projections data was used to identify the agricultural lands that aridity could impact. The results showed a likely increase in rainfall and PET in EA over the next 80 years. However, the spatial variability of the relative increase in rainfall and PET would cause an aridity shift in 1.2–9.7% of the total land area. Though most of the area would experience a transition to a wetter climate, nearly 2% of the land would experience a transition to a drier climate. It would cause nearly 4.4 and 6.2 thousand km2 of agricultural land to be converted from semi-arid to arid and 31.1 and 42.2 thousand km2 of land from sub-humid to semi-arid in the early period for 1.5 and 2.0 °C temperature rise scenarios, respectively. This indicates nearly one and a half times more expansion of aridity on agricultural land in the early period for only a 0.5 °C increase in temperature. A decrease in aridity in the far future for both scenarios would cause a reduction of total arid lands and, thus, its impacts on agriculture. Overall, the study revealed a possible reduction of aridity in EA in the long run if the Paris Agreement is enforced and global warming is limited.

The performance of SPEI integrated remote sensing data for monitoring agricultural drought in the North China Plain

Agricultural drought is significantly affecting sustainable crop production. One of climate-based drought indices, the Standardized Precipitation Evapotranspiration Index (SPEI) calculated by the difference between precipitation and potential evapotranspiration (PET), is being more and more widely employed to characterize the spatio-temporal pattern of agricultural drought. However, substantial uncertainties exist in the current PET methods due to unrealistic configurations of the heterogeneity of crop surface characteristics or complicated parameterization scheme. In this study, standard Penman–Monteith (PM) model is modified and derived by meteorological factors and leaf area index (LAI) and albedo data based on remote sensing. Then, the modified SPEI was calculated by the monthly difference between precipitation and PM model integrated remote sensing data (referred as PMRS) over the North China Plain (NCP) between 1982 and 2016. Comparing with the FAO56 reference evapotranspiration (referred as PMRC) and a simplified version of standard PM over open-water surface (referred as PMOW), this study examines how well the PMRS-SPEI captures drought evolution and impacts on crop growth and yield over the NCP in order to evaluate its performance in agricultural drought monitoring. The comparison of SPEIs based on three evapotranspiration equations with soil water moisture in root depth shows that a 6-month lag can be used as the optimum time scale over the NCP. Additionally, the correlation of PMRS-SPEI performs better than PMRC-SPEI and PMOW-SPEI. For typical drought events, PMRS-SPEI6 shows remarkable smaller (larger) severe drought values between April and June (August and October) and a shorter (longer) recovery period in the growing season for wheat (maize). Comparing to PMRC-SPEI6 and PMOW-SPEI6, the PMRS-SPEI6 shows better performance when examining the Vegetation Health Index and Composite Index of Crop Yield Reduction. Additionally, climate-induced crop yield correlates with PMRS-SPEI6 better than PMOW-SPEI6 and PMRC-SPEI6, particularly in the emergence and filling stages for winter wheat, and silking stage for summer maize. These results demonstrate that integrating remotely sensed data can enhance the agricultural drought monitoring accuracy of SPEI.

Remote sensing of daily evapotranspiration and gross primary productivity of four forest ecosystems in East Asia using satellite multi-channel passive microwave measurements

Satellite multi-channel passive microwave observations provide valuable information of canopy vertical structure and vegetation water content, while their potential in the simultaneous estimation of forest evapotranspiration (ET) and gross primary productivity (GPP) has not been explored. This study combined satellite multi-channel microwave Emissivity Difference Vegetation Indices (EDVIs) from 6.9 to 36.5 GHz with the Penman-Monteith (PM), Priestley-Taylor (PT) and light use efficiency (LUE) models to estimate daily ET and GPP over four forest ecosystems in East Asia. In-situ measurements of daily ET, GPP and meteorological variables from ChinaFLUX network (2003 to 2010) were used to calculate and validate the method. An exponential relationship was found between EDVIs and canopy conductance across the forests. By inverting EDVIs-based LUE model coupled with PM and PT models when canopy carbon uptake and water content reached a maximum in growing seasons, the maximum LUE (EDVI-LUEmax) was derived and found to agree with other independent studies. Site validations showed that the EDVI-based method performed a good simultaneous estimation of daily ET and GPP at a tropical forest and three sub-tropical and temperate forests (R2 of 0.64 to 0.94 and RMSE of −11.7% to 19.6% for ET, R2 of 0.39 to 0.73 and RMSE of 31.2% to 50.4% for GPP). The modeled relationship between GPP and ET also agreed that from in-situ measurements. The results were also found to correlate with microwave frequencies. In-situ ET and GPP showed a stronger correlation with EDVI at 18.7 and 36.5 GHz than that at 10.7 and 18.7 GHz across the forests. EDVI-LUEmax of a temperate mixed forest increased as EDVI incorporated lower frequency microwave emissions from deeper canopy layers, which reduced the negative bias in GPP estimation. Overall, this study demonstrated the potential of multi-channel microwave measurements in estimating ET and GPP with the potential effects of vegetation vertical structure.

Modeling medium resolution evapotranspiration using downscaling techniques in north-western part of India

The present investigation provides a modeling solution to downscale MODIS-based evapotranspiration (ET) at a 30 m spatial resolution from its original 500 m spatial resolution using meteorological and Landsat 8 (Operational Land Imager, OLI) data by employing downscaling models. The nine indices namely Surface Albedo, Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Modified Soil-Adjusted Vegetation Index (MSAVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), and Normalized Difference Infrared Index for Band 7 (NDIIB7) were calculated from Lansat 8 data at 30 m spatial resolution. The multiple linear regression (MLR) and Least Square Support Vector Machine (LS-SVM) models were developed to generate the relationship between MODIS 500 m ET and Landsat indices at 500 m scale. Further, these develop models were used to estimate 30 m ET based on 30 m Landsat 8 indices. The performance of developed models (MLR and LS-SVM) was carried out using correlation coefficient (CC), Nash-Sutcliffe coefficient (NASH) efficiency, Root Mean Square Error (RMSE) and Normalised Mean Square Error (NMSE). Penman–Monteith (PM) method was used to estimate the ET using observed station data. The results show that lowest ETO was observed in the month of December while it was maximum in the month of May. Using the performances indices, it was found that LS-SVM model slightly outperformed than MLR model. However, the downscaled model overestimates ET in comparison to the Penman-Monteith method. Further, the significant correlation was found between MODIS ET and LS-SVM ET at all the stations.

Estimating daily potential evapotranspiration using GNSS-based precipitable water vapor

Potential evapotranspiration (PET) is a crucial component of the hydrological cycle and energy balance. Although the Penman-Monteith (PM) model is the most widely used method to estimate daily PET, it requires temperature, relative humidity, solar radiation, and wind speed. In Thailand, the number of potential weather stations to provide the required data is limited, which resulted in the absence of some input variables in many locations. The objective of this study is to develop the revised potential evapotranspiration (RPET) model to estimate daily PET using Global Navigation Satellite System-derived Precipitable Water Vapor (GNSS-PWV) and temperature data. The multiple linear regression analysis was used to develop and validate the RPET model. The performance of the RPET model along with the Global Land Evaporation Amsterdam Model (GLEAM v3.2 b) and the European Centre for Medium-Range Weather Forecasts Reanalysis-5 (ERA5-Land) products was investigated using the PM model. The results revealed that the RPET model showed a strong correlation with the PM model (r = 0.85, RMSE = 0.97 mm day−1, RSR = 0.53, NSE = 0.72) under limited meteorological inputs. The RPET model performance was superior when compared to GLEAM and ERA5-Land (r = 0.80, RMSE = 1.06 mm day−1). Therefore, the proposed model is greatly suitable for daily PET estimation with only required GNSS-PWV and temperature data, and this can be implemented for drought assessment and water resources management.

Study on the detection of water status of tomato (Solanum lycopersicum L.) by multimodal deep learning.

Water plays a very important role in the growth of tomato (Solanum lycopersicum L.), and how to detect the water status of tomato is the key to precise irrigation. The objective of this study is to detect the water status of tomato by fusing RGB, NIR and depth image information through deep learning. Five irrigation levels were set to cultivate tomatoes in different water states, with irrigation amounts of 150%, 125%, 100%, 75%, and 50% of reference evapotranspiration calculated by a modified Penman-Monteith equation, respectively. The water status of tomatoes was divided into five categories: severely irrigated deficit, slightly irrigated deficit, moderately irrigated, slightly over-irrigated, and severely over-irrigated. RGB images, depth images and NIR images of the upper part of the tomato plant were taken as data sets. The data sets were used to train and test the tomato water status detection models built with single-mode and multimodal deep learning networks, respectively. In the single-mode deep learning network, two CNNs, VGG-16 and Resnet-50, were trained on a single RGB image, a depth image, or a NIR image for a total of six cases. In the multimodal deep learning network, two or more of the RGB images, depth images and NIR images were trained with VGG-16 or Resnet-50, respectively, for a total of 20 combinations. Results showed that the accuracy of tomato water status detection based on single-mode deep learning ranged from 88.97% to 93.09%, while the accuracy of tomato water status detection based on multimodal deep learning ranged from 93.09% to 99.18%. The multimodal deep learning significantly outperformed the single-modal deep learning. The tomato water status detection model built using a multimodal deep learning network with ResNet-50 for RGB images and VGG-16 for depth and NIR images was optimal. This study provides a novel method for non-destructive detection of water status of tomato and gives a reference for precise irrigation management.

Machine learning techniques in estimation of eggplant crop evapotranspiration

This study predicted the daily evapotranspiration of eggplant (Solanum melongena L.) under full and deficit irrigation in the Bafra district of Samsun province, Turkey, using machine learning methods. Artificial neural networks (ANNs), deep neural networks (DNN), M5 model tree (M5Tree), random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and adaptive boosting were investigated as machine learning approaches. Determination of evapotranspiration in this study consists of three methods: (i) The reference evapotranspiration (ETo) was obtained from the Food and Agriculture Organization-56 Penman–Monteith equation, (ii) the values of evapotranspiration (ETc) calculated by multiplying the reference evapotranspiration by the crop coefficient (Kc), and (iii) the values of evapotranspiration (ETa) measured using soil water balance between successive soil water measurements as the outputs. The model’s performance in ETo estimation was higher when minimum and maximum temperature (Tmax and Tmin), wind speed (u2), average relative humidity (RHavg), solar radiation (Rs), and days of the year were used as inputs. The best performance was obtained in the ANN model with a coefficient of determination (R2) value of 0.984, a mean absolute error (MAE) of 0.098 mm d−1, a root-mean-square error (RMSE) of 0.153 mm d−1, and Nash–Sutcliffe efficiency of 0.983. The model’s performance in ETc estimation was significantly improved with the addition of leaf area index (LAI) and crop height (hc) to the climate parameters (MAE and RMSE values decreased by 22.6 and 23.2%, respectively). The accuracy of ETc estimation for some plant traits (hc and LAI) and average temperature (Tavg) was sufficient. The best statistical performance in estimating ETa was obtained by the RF model (Tavg, u2, RHavg, and Rs) using climate parameters. DNN proved to be the least successful model compared to the other six models in predicting ETo, ETc, and ETa.

Using artificial neural networks to predict the reference evapotranspiration

Artificial neural network models (ANNs) were used in this study to predict reference evapotranspiration ( ETo) using climatic data from the meteorological station at the test station in Kafr El-Sheikh Governorate as inputs and reference evaporation values computed using the Penman–Monteith (PM) equation. These datasets were used to train and test seven different ANN models that included different combinations of the five diurnal meteorological variables used in this study, namely, maximum and minimum air temperature ( Tmax and Tmin), dew point temperature ( Tdw), wind speed ( u), and precipitation (P), how well artificial neural networks could predict ETo values. A feed- forward multi-layer artificial neural network was used as the optimization algorithm. Using the tansig transfer function, the final architected has a 6-5-1 structure with 6 neurons in the input layer, 5 neurons in the hidden layer, and 1 neuron in the output layer that corresponds to the reference evapotranspiration. The root mean square error ( RMSE) of 0.1295 mm∙day –1 and the correlation coefficient ( r) of 0.996 are estimated by artificial neural network ETo models. When fewer inputs are used, ETo values are affected. When three separate variables were employed, the RMSE test values were 0.379 and 0.411 mm∙day –1 and r values of 0.971 and 0.966, respectively, and when two input variables were used, the RMSE test was 0.595 mm∙day –1 and the r of 0.927. The study found that including the time indicator as an input to all groups increases the prediction of ETo values significantly, and that including the rain factor has no effect on network performance. Then, using the Penman–Monteith method to estimate the missing variables by using the ETo calculator the normalised root mean squared error ( NRMSE) reached about 30% to predict ETo if all data except temperature is calculated, while the NRMSE reached about of 13.6% when used ANN to predict ETo using variables of temperature only.

Evaluating the Crop Coefficient for Cherries Plants in Michigan State

Crop coefficient for cherries was evaluated by measure the water consumption in Michigan State to find its variation with time as the plant growth. Crop coefficients value (Kc) for cherries were predicated by Michigan State University (MSU) and also by Food and Agriculture Organization (FAO) according to consume of water through the season. In this paper crop coefficients for cherries are modified accordingly to the actual measurements of soil moisture content. Actual evapotranspiration (consumptive use) were measured by the soil moisture readings using Time Domain Reflectometers (TDR), and compared with the actual potential evapotranspiration that calculated by using modified Penman-Monteith equation which depends on metrological station and by using pan evaporation method. Absolut error techniques show that the predicated crop coefficient by MSU should be modified and changed from 1.0 to 1.20 during June, and from 1.02 during July and August to 1.2 to reduce the crop water stress and give better water management and perfect schedule for irrigation process.