Estimating Evapotranspiration of Pomegranate Trees Using Stochastic Configuration Networks (SCN) and UAV Multispectral Imagery

The accurate estimation and mapping of evapotranspiration (ET) are essential for crop water management. As one of the traditional ET estimation methods, crop coefficient (Kc) has been commonly used. Many studies indicated a linear regression relationship between the Kc curve and the vegetation index curve. The linear regression model is usually developed between the Kc and the normalized difference vegetation index (NDVI) derived from satellite imagery. The satellite images can provide temporally and spatially distributed measurements. However, multispectral satellite imagery's spatial resolution is in the range of meters, which is often not enough for crops with clumped canopy structures, such as trees and vines. Little ET estimation has been studied based on the single-tree level. Thus, the purpose of this study was to develop a reliable tree-level ET estimation method using UAV high-resolution multispectral images. Compared with satellite imagery, the spatial resolution of UAV images can be as high as centimeter-level. A field study was conducted to investigate pomegranate trees at the USDA-ARS (US Department of Agriculture, Agricultural Research Service) San Joaquin Valley Agricultural Sciences Center in Parlier, California, USA. The NDVI map was derived from UAV imagery. The Kc values were calculated based on the actual ET from a weighing lysimeter and reference ET from the weather station. The authors then established a linear regression model between the NDVI and Kc to estimate the actual daily ET. Results showed that the linear regression model could estimate tree-level ET with an R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and mean absolute error (MAE) of 0.9143 and 0.39 mm/day, respectively.

Evapotranspiration (ET) estimation is important agricultural research in many regions because of the water scarcity, growing population, and climate change. ET can be analyzed as the sum of evaporation from the soil and transpiration from the crops to the atmosphere. The accurate estimation and mapping of ET are necessary for crop water management. One traditional method is to use the crop coefficient (Kc) and reference ET (ETo) to estimate actual ET. With the advent of satellite technology, remote sensing images can provide spatially distributed measurements. Satellite images are used to calculate the Normalized Difference Vegetation Index (NDVI). The relation between NDVI and Kc is used to generate a new Kc. The spatial resolution of multispectral satellite images, however, is in the range of meters, which is often not enough for crops with clumped canopy structures, such as trees and vines. Moreover, the frequency of satellite overpasses is not high enough to meet the research or water management needs. The Unmanned Aerial Vehicles (UAVs) can help mitigate these spatial and temporal challenges. Compared with satellite imagery, the spatial resolution of UAV images can be as high as centimeter-level. In this study, a regression model was developed using the Deep Stochastic Configuration Networks (DeepSCNs). Actual evapotranspiration was estimated and compared with lysimeter data in an experimental pomegranate orchard. The UAV imagery provided a spatial and tree-by-tree view of ET distribution.

Mapping maize crop coefficient Kc using random forest algorithm based on leaf area index and UAV-based multispectral vegetation indices

Evaluation of optical remote sensing to estimate actual evapotranspiration and canopy conductance

Crop coefficient (K c ) methods have been commonly used for evapotranspiration estimation. Researchers estimate K c as a function of the vegetation index because of similarities between the K c curve and the vegetation index curve. A linear regression model is usually developed between the K c and the normalized difference vegetation index (NDVI) derived from satellite imagery. However, the spatial resolution of satellite imagery is in the range of meters or greater, which is often not enough for crops with clumped canopy structures, such as trees, and vines. In this study, the Unmanned Aerial Vehicles (UAVs) were used to collect high-resolution images in an experimental pomegranate orchard located at the USDA-ARS, San Joaquin Valley Agricultural Sciences Center, Parlier, CA. The NDVI values were derived from UAV images. The K c values were measured from a weighing lysimeter in the pomegranate field. The relationship between the NDVI and K c was established by using both a linear regression model and a deep stochastic configuration networks (DeepSCNs) model. Results show that the linear regression model has an R2 and RMSE value of 0.975 and 0.05, respectively. The DeepSCNs regression model has an R2 and RMSE value of 0.995 and 0.046, respectively. The DeepSCNs model showed improved performance than the linear regression model in predicting K c from NDVI.

The estimation of surface evapotranspiration (ET) with satellite dataset is one of the main subjects in the understanding of climate change, disaster monitoring and the circulation of water vapor and energy in Tibet Autonomous Region (TAR). This research selects satellite images on January 11, April 6, July 31 and October 19 in 2010 as the representative of winter, spring, summer and autumn respectively, estimates the distribution of daily surface ET based on the surface energy balance system (SEBS) along with potential evapotranspiration (PET) and ET derived from Penman-Monteith (P-M) method. The results are obtained as follows. (1) The seasonal distribution of ET and PET basically decreases from the southeast part to the northwest part of TAR. Although ET and PET have similar spatial distributions, there are still some differences to estimate the extreme values especially the maximum value in the middle and southeastern parts of TAR. No matter what kind of methods we adopted, the maximum value of ET and PET always appears in summer, followed by autumn or spring while that in winter is the smallest. (2) In order to better understand the accuracy of SEBS model in the estimation of ET, we compared the ET from SEBS and the ET obtained from P-M method. Results show that the ET from SEBS could estimates the variation trend of actual ET, but it slightly underestimates or overestimates the value of ET as a whole, especially for those areas with thick forest. (3) The spatial distribution of Normalized Difference Vegetation Index (NDVI) exhibits a decreasing trend from the southeast part to the northwest part of TAR which displays remarkable consistency of distributions between ET and vegetation index. ET is well positively related to NDVI, minimum, mean, maximum air temperature and sunshine duration in different seasons while negatively related to precipitation, relative humidity and wind speed in summer.

The use of the National Oceanic and Atmospheric Administration (NOAA) satellites, and the conventional Normalised Difference Vegetation Index (NDVI) model have shown promise as a large scale monitoring tool to understand the vegetation dynamics of the sparsely vegetated Sahelian grasslands. One of the assumptions of the NDVI model is that the soil background is spectrally homogeneous, which is not the case. Twelve sites, within two Système Probatoire d'Observation de Terre (SPOT) satellite imageries, corresponding to NOAA Advanced Very High Resolution Radiometer (AVHRR) Local Area Coverage (LAC) pixel resolution, were assigned representative soil NDVI values for both dry and wet conditions. These soil NDVI values, together with herbaceous above-ground biomass production estimates, were used in a multiple correlation and regression analysis to assess statistically the soil impact on integrated NDVI values, i.e. values supposed only to express the total amount of vegetation in the end of the rainy season. The analysis showed that soil influence varied significantly with different soil types and moisture content, and should therefore not be ignored in satellite based vegetation monitoring.

How to quickly and accurately obtain the basal crop coefficient is the key to estimating evapotranspiration in sparse vegetation. To enhance the accuracy of vineyard evapotranspiration estimation in the subhumid region of Northwest China, this study utilized the actual evapotranspiration (ETc) measured by the Bowen ratio system as the reference standard. The reference crop evapotranspiration (ETo) was calculated using the Penman formula, and the grape crop coefficient (Kc) was subsequently derived. The FAO-56 dual crop coefficient method was then employed to determine the soil evaporation coefficient (Ke) and the water stress coefficient (Ks), leading to the acquisition of the basal crop coefficient (Kcb). Concurrently, multispectral remote sensing images captured by unmanned aerial vehicle (UAV) were used to gather grape spectral data, from which the reflectance of multiple bands was extracted to compute four vegetation indices: the Normalized Difference Vegetation Index (NDVI), the Soil-Adjusted Vegetation Index (SAVI), the Ratio Vegetation Index (RVI), and the Difference Vegetation Index (DVI). Relationship models between the grape basal crop coefficient (Kcb) and these vegetation indices were established using univariate linear regression, polynomial regression, and multiple linear regression. These models were then used to estimate vineyard evapotranspiration and validate the accuracy of the UAV multispectral remote sensing in estimating the grape Kcb. The results indicated that: (1) The growth stage, type of vegetation index, and modeling method were three significant factors influencing the fitting accuracies of the relationship models between the grape basal crop coefficient (Kcb) and vegetation indices. These model fitting accuracies had a notable impact on the estimation accuracies of evapotranspiration. (2) The application of UAV-based multispectral remote sensing to estimate the grape basal crop coefficient in the subhumid region of Northwest China was feasible. Compared to the Kcb values recommended by the FAO-56, the Kcb values derived from the UAV data improved the estimation accuracies of evapotranspiration by more than 11% in 2021 and 13% in 2022.

The rapid, accurate, and real-time estimation of crop coefficients at the farm scale is one of the key prerequisites in precision agricultural water management. This study aimed to map the maize crop coefficient (Kc) with improved accuracy under different levels of deficit irrigation. The proposed method for estimating the Kc is based on multispectral images of high spatial resolution taken using an unmanned aerial vehicle (UAV). The analysis was performed on five experimental plots using Kc values measured from the daily soil water balance in Ordos, Inner Mongolia, China. To accurately estimate the Kc, the fraction of vegetation cover (fc) derived from the normalized difference vegetation index (NDVI) was used to compare with field measurements, and the stress coefficients (Ks) calculated from two vegetation index (VI) regression models were compared. The results showed that the NDVI values under different levels of deficit irrigation had no significant difference in the reproductive stage but changed significantly in the maturation stage, with a decrease of 0.09 with 72% water applied difference. The fc calculated from the NDVI had a high correlation with field measurement data, with a coefficient of determination (R2) of 0.93. The ratios of transformed chlorophyll absorption in reflectance index (TCARI) to renormalized difference vegetation index (RDVI) and TCARI to soil-adjusted vegetation index (SAVI) were used, respectively, to establish two types of Ks regression models to retrieve Kc. Compared to the TCARI/SAVI model, the TCARI/RDVI model under different levels of deficit irrigation had better correlation with Kc, with R2 and root-mean-square error (RMSE) values ranging from 0.68 to 0.80 and from 0.140 to 0.232, respectively. Compared to Kc calculated from on-site measurements, the Kc values retrieved from the VI regression models established in this study had greater ability to assess the field variability of soil and crops. Overall, use of the UAV-measured multispectral vegetation index approach could improve water management at the farm scale.

Crop coefficient (Kc) based estimation of crop evapotranspiration (ETc) is one of the most commonly used methods for irrigation water management. However the standard FAO Penman-Monteith approach for estimating ETc from reference evapotranspiration and tabulated generalized Kc values has some limitations. In this paper, we present a modified approach towards estimating Kc values from remotely sensed data. Surface Energy Balance Algorithm for Land (SEBAL) model was used for estimating spatial distribution of ETc during 2005 growing season in south-central Nebraska. The alfalfa based reference evapotranspiration (ETr) was calculated using multi-automatic weather station data with geostatistical analysis. Based upon the mean absolute error (MAE) and coefficient of determination (r2), the ordinary Kriging method resulted as the best interpolation technique for determining the reference evapotranspiration. The crop coefficient was estimated based on crop evapotranspiration and reference evapotranspiration. Land use map was used for sampling and profiling the crop coefficients on dates of satellite overpass for various major crops grown in south-central Nebraska. Finally a regression based model was developed to establish the relationship between the Normalized Difference Vegetation Index (NDVI) and the ETr based crop coefficient (Kcr) for corn, soybean, sorghum, and alfalfa under irrigated and dryland conditions. Validation of the model for the corn using Bowen ratio energy balance system based Kcr and estimated Kcr has shown good correlation (r2=0.73). This approach can be very useful for estimation of evapotranspiration using NDVI based crop coefficient and reference evapotranspiration.

The estimation of crop evapotranspiration (ETc) is crucial for irrigation water management, especially in arid regions. This can be particularly relevant in the Po Valley (Italy), where arable lands suffer from drought damages on an annual basis, causing drastic crop yield losses. This study presents a novel approach for vegetation-based estimation of crop evapotranspiration (ETc) for maize. Three years of high-resolution multispectral satellite (Sentinel-2)-based Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Normalized Difference Red Edge Index (NDRE), and Leaf Area Index (LAI) time series data were used to derive crop coefficients of maize in nine plots at the Acqua Campus experimental farm of Irrigation Consortium for the Emilia Romagna Canal (CER), Italy. Since certain vegetation indices (VIs) (such as NDVI) have an exponential nature compared to the other indices, both linear and power regression models were evaluated to estimate the crop coefficient (Kc). In the context of linear regression, the correlations between Food and Agriculture Organization (FAO)-based Kc and NDWI, NDRE, NDVI, and LAI-based Kc were 0.833, 0.870, 0.886, and 0.771, respectively. Strong correlation values in the case of power regression (NDWI: 0.876, NDRE: 0.872, NDVI: 0.888, LAI: 0.746) indicated an alternative approach to provide crop coefficients for the vegetation period. The VI-based ETc values were calculated using reference evapotranspiration (ET0) and VI-based Kc. The weather station data of CER were used to calculate ET0 based on Penman-Monteith estimation. Out of the Vis, NDWI and NDVI-based ETc performed the best both in the cases of linear (NDWI RMSE: 0.43 ± 0.12; NDVI RMSE: 0.43 ± 0.095) and power (NDWI RMSE: 0.44 ± 0.116; NDVI RMSE: 0.44 ± 0.103) approaches. The findings affirm the efficacy of the developed methodology in accurately assessing the evapotranspiration rate. Consequently, it offers a more refined temporal estimation of water requirements for maize cultivation in the region.

As the key principle of precision farming, variation of actual crop evapotranspiration (ET) within the field serves as the basis for crop management. Although the estimation of evapotranspiration has achieved great progress through the combination of different remote sensing data and the FAO-56 crop coefficient (Kc) method, lack of the accurate crop water stress coefficient (Ks) at different space–time scales still hinder its operational application to farmer practices. This work aims to explore the potential of multispectral images taken from unmanned aerial vehicles (UAVs) for estimating the temporal and spatial variability of Ks under the water stress condition and mapping the variability of field maize ET combined with the FAO-56 Kc model. To search for an optimal estimation method, the performance of several models was compared including models based on Ks either derived from the crop water stress index (CWSI) or calculated by the canopy temperature ratio (Tc ratio), and combined with the basal crop coefficient (Kcb) based on the normalized difference vegetation index (NDVI). Compared with the Ks derived from the Tc ratio, the CWSI-based Ks responded well to water stress and had strong applicability and convenience. The results of the comparison show that ET derived from the Ks-CWSI had a higher correlation with the modified FAO-56 method, with an R2 = 0.81, root mean square error (RMSE) = 0.95 mm/d, and d = 0.94. In contrast, ET derived from the Ks-Tc ratio had a relatively lower correlation with an R2 = 0.68 and RMSE = 1.25 mm/d. To obtain the evapotranspiration status of the whole maize field and formulate reasonable irrigation schedules, the CWSI obtained by a handheld infrared thermometer was inverted by the renormalized difference vegetation index (RDVI) and the transformed chlorophyll absorption in reflectance index (TCARI). Then, the whole map of Ks can be derived from the VIs by the relationship between CWSI and Ks and can be taken as the basic input for ET estimation at the field scale. The final ET results based on multispectral UAV interpolation measurements can well reflect the crop ET status under different irrigation levels, and greatly help to improve irrigation scheduling through more precise management of deficit irrigation.

Crop coefficient is one of the most important parameters used for the estimation of crop evapotranspiration (ETc). Crop coefficient (Kc)-based estimation of crop evapotranspiration is most commonly used methods for irrigation water management. However, crop coefficient approach used for estimation ETc using the generalized crop coefficients mentioned in Irrigation and Drainage Paper No. 56 of the Food and Agricultural Organization of the United Nations can contribute to crop evapotranspiration estimates that are substantially different from actual crop evapotranspiration. The colinear relationship between the crop coefficient curve and a satellitederived Normalized Difference Vegetation Index (NDVI) showed potential for modeling a crop coefficient as a function of the NDVI, which is also one among the methods used for estimation of ETc in irrigation water management. The present study was conducted with objectives to present the techniques and procedures to develop and estimates Kc based on vegetation index (NDVI) extracted from satellite data. The relationships between and NDVI and crop coefficients (Kc) of wheat and chickpea for corresponding months were developed. The regression models developed are: (Kc) NDVI = 6.3268*NDVI-1.4207 for wheat and (Kc) NDVI = 5.7866 * NDVI-1.6699 for chickpea. The models showed strong relationships with R2= 0.86 and R2=0.84 for wheat and chickpea, respectively. The model and techniques to develop and estimate crop coefficients can be used in other regions in the global, and hence estimate crop evapotranspiration. The crop coefficients (Kc) estimated based on NDVI are useful for irrigation scheduling, evaluating irrigation performance, irrigation water management, and estimation of water use efficiency.

Many scientists have been investigating Land Surface Temperature (LST) because of its relevance in water management science due to its direct influence on the hydrological water cycle. This effect stems from being one of the most significant variables influencing evapotranspiration. One of the most important reasons for the evapotranspiration retrieved from MODIS data’s limited suitability for scheduling and planning irrigation schemes is the lack of spatial resolution. As a result, high-resolution LST is required for estimating evapotranspiration. The goal of this study is to improve the resolution of the available LST data, to improve evapotranspiration (ETa) estimation using statistical downscaling with Normalized Difference Vegetation Index (NDVI) as a predictor. The DisTrad (Disaggregation of Radiometric Surface Temperature) method was used for the LST downscaling procedure, which is based on aggregating the NDVI map to the LST map resolution and then calculating the coefficient of variation of the native NDVI map within the aggregated pixel and classifying the aggregated map into three classes: NDVI &lt; 0.2 for the bare soil, 0.2 ≤ NDVI ≤ 0.5 for the partial vegetation, and NDVI &gt; 0.5 for the full vegetation. DisTrad uses 25% of the pixels with the lowest coefficient of variation from each class to calculate the regression coefficients. In this work, adjustments to the DisTrad method were implemented to enhance downscaling LST and to examine the impacts of that alteration on the evapotranspiration estimation. The linear regression model was tested as an alternative to the original second-order polynomial. In using 10% of the pixels instead of the originally proposed 25% with the lowest coefficient of variation values, it is assumed that a group of pixels with a lower coefficient of variation represents a more homogeneous area, thus it gives more accurate values. The downscaled LST map retrieval was validated using Landsat 8 thermal maps (100 m). Applying the modified DisTrad approach to disaggregate Landsat LST to 30 m (NDVI resolution) yielded an R2 of 0.72 for the 10%, 0.74 for the 25% and 0.61 for the second-order polynomial lowest coefficient of variation compared to native LST Landsat, which means that 10% can be used as an alternative. Applying the downscaled LST map to estimate ETa yielded R2 0.84 in both cases, compared to ETa yielded from the native Landsat LST. These results prove that using the robust linear regression provided better results than using polynomial regression. With the downscaled Land Surface Temperature data, it was possible to create detailed ETa maps of the small agricultural fields in the test area.

Remotely-sensed groundwater evapotranspiration from alkali scrub affected by declining water table