Prediction Of Evapotranspiration Research Articles

Advanced reference crop evapotranspiration prediction: a novel framework combining neural nets, bee optimization algorithm, and mode decomposition

AbstractVarious critical applications, spanning from watershed management to agricultural planning and ecological sustainability, hinge upon the accurate prediction of reference evapotranspiration (ETo). In this context, our study aimed to enhance the accuracy of ETo prediction models by combining a variety of signal decomposition techniques with an Artificial Bee Colony (ABC)–artificial neural network (ANN) (codename: ABC–ANN). To this end, historical (1979–2014) daily climate variables, including maximum temperature, minimum temperature, mean temperature, wind speed, relative humidity, solar radiation, and precipitation from four arid and semi-arid regions in Egypt: Al-Qalyubiyah, Cairo, Damietta, and Port Said, were used. Six techniques, namely, Empirical Mode Decomposition, Variational Mode Decomposition, Ensemble Empirical Mode Decomposition, Local Mean Decomposition, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, and Empirical Wavelet Transform were used to evaluate signal decomposition efficiency in ETo prediction. Our results showed that the highest ETo prediction accuracy was obtained with ABC-ANN (Train R2: 0.990 and Test R2: 0.989), (Train R2: 0.986 and Test R2: 0.986), (Train R2: 0.991 and Test R2: 0.989) and (Train R2: 0.988 and Test R2: 0.987) for Al-Qalyubiyah, Cairo, Damietta, and Port Said, respectively. The impressive results of our hybrid model attest to its importance as a powerful tool for tackling the problems associated with ETo prediction.

Predicting future evapotranspiration based on remote sensing and deep learning

Study regionThe watersheds of the four flux sites in the United States were selected as the study areas for this research. Study focusThis study validates the efficiency of Convolutional Long Short-Term Memory Network (ConvLSTM) models for site-scale ETa prediction. We enhanced the ConvLSTM model by adding a Spatial Pyramid Pooling module (SPPM) and a Multi-head Self-Attention Module (MSA-Module), creating the Multi-head Self-Attention ConvLSTM (MSA-ConvLSTM) model, which we applied to predicting regional-scale actual evapotranspiration (ETa). This study aims to investigate whether the MSA-ConvLSTM model can enhance the accuracy of predicting regional-scale ETa, considering multiple feature variables. Furthermore, we evaluated different performance indicators, discussed possible reasons for errors in regional ETa prediction, and conducted sensitivity analysis of the model characteristics. New hydrological insights for the regionThe MSA-ConvLSTM model accurately predicts the future state of ETa. The average R2 was 0.81, which is 11.6 % and 5.5 % higher than those of the ConvLSTM and Self-Attention ConvLSTM (SA-ConvLSTM) models, respectively. The average RMSE is 11.94 mm/m, which is 21.5 % and 13.7 % lower than ConvLSTM and SA-ConvLSTM, respectively. The average MAE is 9.46 mm/m, which is 21.3 % and 13 % lower than ConvLSTM and SA-ConvLSTM, respectively. Incorporating of a multi-head self-attention module enhances the model’s capacity for comprehensive understanding of input data features. This improvement allows the model to better adapt to feature relationships at varying scales and angles, enhancing its representational capacity and enabling effective adaptation to complex environmental changes.

An explainable hybrid framework for estimating daily reference evapotranspiration: Combining extreme gradient boosting with Nelder-Mead method

Accurate estimation of reference evapotranspiration (ETo) is essential for effective water resources management, irrigation system design, and various hydrological and agricultural applications. This study employed extreme gradient boosting (XGBoost) model, signal decomposition techniques, and XGBoost coupled with Nelder–Mead (NM) method to enhance ETo prediction across two meteorological stations in Iran. This study proposed a novel framework which lies in its comprehensive integration of advanced techniques to create a model that is both interpretable and highly accurate for ETo estimation. For this aim, sixty meteorological variables were categorized into solar and cloud-based, temperature-based, wind and humidity-based, and pressure-based groups to analyze their effect on ETo estimation. Feature selection methods, including the Gradient Boosting Machine, Kendall’s Tau, and Relief Algorithm, were employed to identify the most influential predictors. Variables with normalized weights equal to or greater than 0.9 were selected for model input, resulting in the top 10% of variables being utilized. The XGBoost models were then developed using these selected inputs (level 1), a wavelet-based hybrid was developed according to the most effective features (level 2), and the XGBoost model was coupled by NM algorithm (level 3) for ETo estimation. Results of estimated ETo by levels 1 to 3 were compared with four common empirical approaches. The results indicated that Kendall’s Tau-based feature selection provided the most accurate predictions in Shiraz, achieving an RMSE of 0.721 (mm/day) for solar and cloud-based variables during the test phase. Additionally, the application of wavelet analysis further refined the model inputs, which enhanced ETo estimation in most variable groups. Integrating the NM algorithm with XGBoost demonstrated significant improvements in ETo estimation, where it could improve RMSE to 0.091 and 0.155 (mm/day) for testing section in Fasa and Shiraz, respectively.

Comparative analysis of advanced deep learning models for predicting evapotranspiration based on meteorological data in bangladesh.

Evapotranspiration is one of the crucial elements in water balance equations and plays a pivotal role in the water and energy cycle of an area. An accurate and precise estimation and prediction of reference evapotranspiration (ETo) is necessary for regional management of water resources and irrigation scheduling. The challenge of predicting daily evapotranspiration with limited meteorological data in Bangladesh. This study aims to predict daily evapotranspiration using limited meteorological data of Bangladesh by three deep learning (CNN, GRU, LSTM) and one hybrid (CNN-GRU) model. The novel method of hybrid CNN-GRU models, which have not been commonly used for this purpose. The performance of models was evaluated by five accuracy matrices R2, RMSE, MAE, MAPE, and CE and comparison is visualized by radar graphs. The study's novelty lies in the use of hybrid CNN-GRU models to estimate reference evapotranspiration, as this algorithm has not been commonly used for this purpose. In the case of the Rangpur station, the hybrid CNN-GRU algorithm outperformed other models, achieving the best values across various statistical metrics during both the training and testing phases. The highest correlation coefficient values of approximately 0.994 and 0.995. Moreover, during training and testing stages, the hybrid model had the lowest MAE (0.076, 0.068) and RMSE (0.138, 0.106) at the Rangpur station. Additionally, in the Sreemangal station, it can be notable that the statistical parameter RSME found superior results in the hybrid model around 0.225 and 0.174, respectively. In addition, the highest R2 and CE values were noted as 0.986, 0.987 and 0.985, 0.986 during the training and testing phases, respectively. The comparison suggests that the hybrid model will be best suited for prediction with the limited meteorological data. The outcome of the present research signifies the ability of deep learning methods in the prediction of evapotranspiration and the dominant variables affecting the changes the in context of Bangladesh.

Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain

Precise determination of the reference evapotranspiration (ET0) is vital to studying the hydrological cycle. In addition, It plays a significant role in properly managing and allocating water resources in agriculture. The objective of this research was to examine the effectiveness of five different data-driven techniques, including artificial neural networks "multilayer perceptron" (ANN), gene expression programming (GEP), random forest (RF), support vector machine "radial basis function" (SVM), and multiple linear regression (MLR) to model the daily ET0. These methods were also compared with Hargreaves-Samani (HS), Oudin, Ritchie, Makkink (MAK), and Jensen Haise (JH) empirical models and their calibrated versions. The empirical models JH and MAK performed better than the models HS and Oudin after being calibrated by linear regression. All data-driven methods with four inputs were superior to the original and calibrated empirical models. The RF and ANN methods generally demonstrated better estimation accuracy than other data-driven methods. The performance of the RF and ANN models that utilized Tmax, Tmin, and Rs inputs, as well as those that incorporated Tmax, Tmin, Rs, and U2 inputs, proved to be superior to their corresponding MLR-based and GEP-based models for predicting ET0 in the Adana plain, which is characterized by a Mediterranean climate. Nevertheless, the GEP and MLR methods have the advantage of utilizing explicit algebraic equations, making them more convenient to apply, especially in the context of agricultural irrigation practices.

Machine learning-based estimation of evapotranspiration under adaptation conditions: a case study in Heilongjiang Province, China.

The prediction of evapotranspiration (ET0) is crucial for agricultural ecosystems, irrigation management, and environmental climate regulation. Traditional methods for predicting ET0 require a variety of meteorological parameters. However, obtaining data for these multiple parameters can be challenging, leading to inaccuracies or inability to predict ET0 using traditional methods. This affects decision-making in critical applications such as agricultural irrigation scheduling and water management, consequently impacting the development of agricultural ecosystems. This issue is particularly pronounced in economically underdeveloped regions. Therefore, this paper proposes a machine learning-based evapotranspiration estimation method adapted to evapotranspiration conditions. Compared to traditional methods, our approach relies less on the variety of meteorological parameters and yields higher prediction accuracy. Additionally, we introduce a 'region of evapotranspiration adaptability' division method, which takes into account geographical differences in ET0 prediction. This effectively mitigates the negative impact of anomalies or missing data from individual meteorological stations, making our method more suitable for practical agricultural irrigation and ecosystem water resource management. We validated our approach using meteorological data from 25 stations in Heilongjiang, China. Our results indicate that non-adjacent geographical areas, despite different climatic conditions, can have similar impacts on ET0 prediction. In summary, our method facilitates accurate ET0 prediction, offering new insights for the development of agricultural irrigation and ecosystems, and further contributes to agricultural food supply.

Structural Constraints in Current Stomatal Conductance Models Preclude Accurate Prediction of Evapotranspiration

AbstractEvapotranspiration (ET) plays a critical role in water and energy budgets at regional to global scales. ET is composed of direct evaporation (E) and plant transpiration (T) where the latter is regulated via stomatal conductance (gsc), which depends on a multitude of plant physiological processes and hydrometeorological forcings. In recent years, significant advances have been made toward estimating gsc using a variety of models, ranging from relatively simple empirical models to more complex and data‐intensive plant hydraulic models. Using machine learning (ML) and eddy covariance flux tower data of 642 site years across 84 sites distributed across 10 land covers globally, here we show that structural constraints inherent in current empirical and plant hydraulic models of gsc limit their effectiveness for predicting ET. These constraints also prevent the models from fully utilizing the available hydrometeorological data at eddy covariance sites. Even if these gsc models are calibrated locally, structural simplifications inherent in them limit their capability to accurately capture gsc dynamics. In contrast, a ML approach, wherein the model structure is learned from the data, outperforms traditional models, thus highlighting that there still is significant room for improvement in the structure of traditional models for predicting ET. These results underscore the need to prioritize improvements in gsc models for more accurate ET estimation. This, in turn, will help reduce uncertainties in the assessments of plants' role in regulating the Earth's climate.

Sensitivity of daily reference evapotranspiration to weather variables in tropical savanna: a modelling framework based on neural network

Accurate prediction of reference evapotranspiration (ETo) is crucial for many water-related fields, including crop modelling, hydrologic simulations, irrigation scheduling and sustainable water management. This study compares the performance of different soft computing models such as artificial neural network (ANN), wavelet-coupled ANN (WANN), adaptive neuro-fuzzy inference systems (ANFIS) and multiple nonlinear regression (MNLR) for predicting ETo. The Gamma test technique was adopted to select the suitable input combination of meteorological variables. The performance of the models was quantitatively and qualitatively evaluated using several statistical criteria. The study showed that the ANN-10 model performed superior to the ANFIS-06, WANN-11 and MNLR models. The proposed ANN-10 model was more appropriate and efficient than the ANFIS-06, WANN-11 and MNLR models for predicting daily ETo. Solar radiation was found to be the most sensitive input variable. In contrast, actual vapour pressure was the least sensitive parameter based on sensitivity analysis.

Verification of Long‐Term Ensemble Evapotranspiration Hindcast Using a Conditional Nonlinear Optimal Parameter Perturbation Ensemble Prediction Method on the Tibetan Plateau

AbstractIn this research, a conditional nonlinear optimal perturbation related to parameters (CNOP‐P) method is employed to propose an ensemble prediction method titled as the conditional nonlinear optimal perturbation related to parameters ensemble prediction (CNOP‐PEP) method. Within the CNOP‐PEP method, all ensemble members are generated by the CNOP‐P method. To explore the operability and validity of the CNOP‐PEP method, long‐term evapotranspiration (ET) hindcast skill is evaluated at 13 sites on the Tibetan Plateau (TP) during the period of 2001–2018 with a land surface model. Two traditional ensemble prediction methods (the stochastically perturbed parameters (SPP) method and the one‐at‐a‐time (OAT) method) are also applied to assess the ET hindcast skills. The numerical results indicate that the CNOP‐PEP method shows the best hindcast skill for estimated ET at 13 stations on the TP among the three methods (CNOP‐PEP, OAT, and SPP methods) during the period of 2001–2018. This suggests that the CNOP‐PEP method is helpful and effective for long‐term and interannual hydrological predictions, such as long‐term and interannual ET predictions. The numerical results also indicate that ensemble members with certain special properties of fast‐growing types should be selected to implement ensemble prediction compared to these ordinary and traditional samples. The CNOP‐PEP method could supply special samples to improve the ensemble prediction and hindcast skill of hydrological cycle.

Prediction of Large-Scale Regional Evapotranspiration Based on Multi-Scale Feature Extraction and Multi-Headed Self-Attention

Accurately predicting actual evapotranspiration (ETa) at the regional scale is crucial for efficient water resource allocation and management. While previous studies mainly focused on predicting site-scale ETa, in-depth studies on regional-scale ETa are relatively scarce. This study aims to address this issue by proposing a MulSA-ConvLSTM model, which combines the multi-headed self-attention module with the Pyramidally Attended Feature Extraction (PAFE) method. By extracting feature information and spatial dependencies in various dimensions and scales, the model utilizes remote sensing data from ERA5-Land and TerraClimate to attain regional-scale ETa prediction in Shandong, China. The MulSA-ConvLSTM model enhances the efficiency of capturing the trend of ETa successfully, and the prediction results are more accurate than those of the other contrast models. The Pearson’s correlation coefficient between observed and predicted values reaches 0.908. The study has demonstrated that MulSA-ConvLSTM yields superior performance in forecasting various ETa scenarios and is more responsive to climatic changes than other contrast models. By using a convolutional network feature extraction method, the PAFE method extracts global features via various convolutional kernels. The customized MulSAM module allows the model to concentrate on data from distinct subspaces, focusing on feature changes in multiple directions. The block-based training method is employed for the large-scale regional ETa prediction, proving to be effective in mitigating the constraints posed by limited hardware resources. This research provides a novel and effective method for accurately predicting regional-scale ETa.

Evapotranspiration prediction for European forest sites does not improve with assimilation of in situ soil water content data

Abstract. Land surface models (LSMs) are an important tool for advancing our knowledge of the Earth system. LSMs are constantly improved to represent the various terrestrial processes in more detail. High-quality data, freely available from various observation networks, are being used to improve the prediction of terrestrial states and fluxes of water and energy. To optimize LSMs with observations, data assimilation methods and tools have been developed in the past decades. We apply the coupled Community Land Model version 5 (CLM5) and Parallel Data Assimilation Framework (PDAF) system (CLM5-PDAF) for 13 forest field sites throughout Europe covering different climate zones. The goal of this study is to assimilate in situ soil moisture measurements into CLM5 to improve the modeled evapotranspiration fluxes. The modeled fluxes will be evaluated using the predicted evapotranspiration fluxes with eddy covariance (EC) systems. Most of the sites use point-scale measurements from sensors placed in the ground; however, for three of the forest sites we use soil water content data from cosmic-ray neutron sensors, which have a measurement scale closer to the typical land surface model grid scale and EC footprint. Our results show that while data assimilation reduced the root-mean-square error for soil water content on average by 56 % to 64 %, the root-mean-square error for the evapotranspiration estimation is increased by 4 %. This finding indicates that only improving the soil water content (SWC) estimation of state-of-the-art LSMs such as CLM5 is not sufficient to improve evapotranspiration estimates for forest sites. To improve evapotranspiration estimates, it is also necessary to consider the representation of leaf area index (LAI) in magnitude and timing, as well as uncertainties in water uptake by roots and vegetation parameters.

Prediction of monthly evapotranspiration by artificial neural network model development with Levenberg–Marquardt method in Elazig, Turkey

The phenomenon of evapotranspiration (ET) is closely linked to the issue of water scarcity, as it involves water loss through both evaporation and plant transpiration. Accurate prediction of evapotranspiration is of utmost importance in the strategic planning of agricultural irrigation, effective management of water resources, and precise hydrological modeling. The current investigation aims to predict the monthly ET values in the Elazig province by developing an artificial neural network (ANN) model utilizing the Levenberg–Marquardt method. Consequently, the values of temperature, precipitation, relative humidity, solar hour, and mean wind speed were utilized in forecasting evapotranspiration values by implementing ANN algorithms. This research makes a valuable contribution to the existing body of literature by utilizing an ANN model developed with the Levenberg–Marquardt method to estimate evapotranspiration. It has been discovered that evapotranspiration values are impacted by various factors such as temperature (minimum, average, maximum), relative humidity (minimum, average, maximum), wind speed, solar hour, and precipitation values, which are taken into consideration for prediction. The findings indicated that Elazig, Keban, Baskil, and Agin sites had R values of 0.9995, 0.9948, 0.9898, and 0.9994 in the proposed model. It was found that Elazig’s MAPE ranged from 0 to 0.2288, Keban’s was 0.0001 to 0.3703, Baskil’s was between 0 and 0.4453, and Agin’s was both 0 and 0.2784. The findings obtained from the proposed model are compatible with evapotranspiration values computed from the Hargreaves method (R2 = 0.996). The study’s findings provide significant insights for planners and decision-makers involved in the planning and managing water resources and agricultural irrigation.

Machine Learning-Based Estimation of Daily Cropland Evapotranspiration in Diverse Climate Zones

The accurate prediction of cropland evapotranspiration (ET) is of utmost importance for effective irrigation and optimal water resource management. To evaluate the feasibility and accuracy of ET estimation in various climatic conditions using machine learning models, three-, six-, and nine-factor combinations (V3, V6, and V9) were examined based on the data obtained from global cropland eddy flux sites and Moderate Resolution Imaging Spectroradiometer (MODIS) remote sensing data. Four machine learning models, random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), and backpropagation neural network (BP), were used for this purpose. The input factors included daily mean air temperature (Ta), net radiation (Rn), soil heat flux (G), evaporative fraction (EF), leaf area index (LAI), photosynthetic photon flux density (PPFD), vapor pressure deficit (VPD), wind speed (U), and atmospheric pressure (P). The four machine learning models exhibited significant simulation accuracy across various climate zones, reflected by their global performance indicator (GPI) values ranging from −3.504 to 0.670 for RF, −3.522 to 1.616 for SVM, −3.704 to 0.972 for XGB, and −3.654 to 1.831 for BP. The choice of suitable models and the different input factors varied across different climatic regions. Specifically, in the temperate–continental zone (TCCZ), subtropical–Mediterranean zone (SMCZ), and temperate zone (TCZ), the models of BPC-V9, SVMS-V6, and SVMT-V6 demonstrated the highest simulation accuracy, with average RMSE values of 0.259, 0.373, and 0.333 mm d−1, average MAE values of 0.177, 0.263, and 0.248 mm d−1, average R2 values of 0.949, 0.819, and 0.917, and average NSE values of 0.926, 0.778, and 0.899, respectively. In climate zones with a lower average LAI (TCCZ), there was a strong correlation between LAI and ET, making LAI more crucial for ET predictions. Conversely, in climate zones with a higher average LAI (TCZ, SMCZ), the significance of the LAI for ET prediction was reduced. This study recognizes the impact of climate zones on ET simulations and highlights the necessity for region-specific considerations when selecting machine learning models and input factor combinations.

Artificial Neural Network for Forecasting Reference Evapotranspiration in Semi-Arid Bioclimatic Regions

A correct determination of irrigation water requirements necessitates an adequate estimation of reference evapotranspiration (ETo). In this study, monthly ETo is estimated using artificial neural network (ANN) models. Eleven combinations of long-term average monthly climatic data of air temperature (min and max), wind speed (WS), relative humidity (RH), and solar radiation (SR) recorded at nine different weather stations in Tunisia are used as inputs to the ANN models to calculate ETo given by the FAO-56 PM (Penman–Monteith) equation. This research study proposes to: (i) compare the FAO-24 BC, Riou, and Turc equations with the universal PM equation for estimating ETo; (ii) compare the PM method with the ANN technique; (iii) determine the meteorological parameters with the greatest impact on ETo prediction; and (iv) determine how accurate the ANN technique is in estimating ETo using data from nearby weather stations and compare it to the PM method. Four statistical criteria were used to evaluate the model’s predictive quality: the determination coefficient (R2), the index of agreement (d), the root mean square error (RMSE), and the mean absolute error (MAE). It is quite evident that the Blaney–Criddle, Riou, and Turc equations underestimate or overestimate the ETo values when compared to the PM method. Values of ETo underestimation ranged from 1.9% to 66.1%, while values of overestimation varied from 0.9% to 25.0%. The comparisons revealed that the ANN technique could be adeptly utilized to model ETo using the available meteorological data. Generally, the ANN technique performs better on the estimates of ETo than the conventional equations studied. Among the meteorological parameters considered, maximum temperature was identified as the most significant climatic parameter in ETo modeling, reaching values of R and d of 0.936 and 0.983, respectively. The research showed that trained ANNs could be used to yield ETo estimates using new data from nearby stations not included in the training process, reaching high average values of R and d values of 0.992 and 0.997, respectively. Very low values of MAE (0.233 mm day−1) and RMSE (0.326 mm day−1) were also obtained.

Long-term gridded land evapotranspiration reconstruction using Deep Forest with high generalizability

Previous datasets have limitations in generalizing evapotranspiration (ET) across various land cover types due to the scarcity and spatial heterogeneity of observations, along with the incomplete understanding of underlying physical mechanisms as a deeper contributing factor. To fill in these gaps, here we developed a global Highly Generalized Land (HG-Land) ET dataset at 0.5° spatial resolution with monthly values covering the satellite era (1982–2018). Our approach leverages the power of a Deep Forest machine-learning algorithm, which ensures good generalizability and mitigates overfitting by minimizing hyper-parameterization. Model explanations are further provided to enhance model transparency and gain new insights into the ET process. Validation conducted at both the site and basin scales attests to the dataset’s satisfactory accuracy, with a pronounced emphasis on the Northern Hemisphere. Furthermore, we find that the primary driver of ET predictions varies across different climatic regions. Overall, the HG-Land ET, underpinned by the interpretability of the machine-learning model, emerges as a validated and generalized resource catering to scientific research and various applications.

Estimation of Daily Actual Evapotranspiration of Tea Plantations Using Ensemble Machine Learning Algorithms and Six Available Scenarios of Meteorological Data

The tea plant (Camellia sinensis), as a major, global cash crop providing beverages, is facing major challenges from droughts and water shortages due to climate change. The accurate estimation of the actual evapotranspiration (ETa) of tea plants is essential for improving the water management and crop health of tea plantations. However, an accurate quantification of tea plantations’ ETa is lacking due to the complex and non-linear process that is difficult to measure and estimate accurately. Ensemble learning (EL) is a promising potential algorithm for accurate evapotranspiration prediction, which solves this complexity through the new field of machine learning. In this study, we investigated the potential of three EL algorithms—random forest (RF), bagging, and adaptive boosting (Ad)—for predicting the daily ETa of tea plants, which were then compared with the commonly used k-nearest neighbor (KNN), support vector machine (SVM), and multilayer perceptron (MLP) algorithms, and the experimental model. We used 36 estimation models with six scenarios from available meteorological and evapotranspiration data collected from tea plantations over a period of 12 years (2010–2021). The results show that the combination of Rn (net radiation), Tmean (mean air temperature), and RH (relative humidity) achieved reasonable precision in assessing the daily ETa of tea plantations in the absence of climatic datasets. Compared with other advanced models, the RF model demonstrated superior performance (root mean square error (RMSE): 0.41–0.56 mm day−1, mean absolute error (MAE): 0.32–0.42 mm day−1, R2: 0.84–0.91) in predicting the daily ETa of tea plantations, except in Scenario 6, followed by the bagging, SVM, KNN, Ad, and MLP algorithms. In addition, the RF and bagging models exhibited the highest steadiness with low RMSE values increasing (−15.3~+18.5%) in the validation phase over the testing phase. Considering the high prediction accuracy and stability of the studied models, the RF and bagging models can be recommended for estimating the daily ETa estimation of tea plantations. The importance analysis from the studied models demonstrated that the Rn and Tmean are the most critical influential variables that affect the observed and predicted daily ETa dynamics of tea plantations.

Hybrid model to improve reference evapotranspiration prediction: Integrating ANN and PSO

Reference evapotranspiration (ETo), one of the key elements of the hydrological cycle, is crucial for managing irrigation and drainage systems. In order to estimate monthly ETo, this study tested the prediction abilities of a unique hybrid methodology that coupled data pre-processing with a hybrid model composed of an artificial neural network (ANN) and particle swarm optimisation (PSO). In order to train and evaluate the model, monthly meteorological data were collected in Al-Kut City, Iraq, from 1990 to 2020. A range of statistical indicators were used to assess the model, including RMSE, NSE, and R2. The outcomes showed that the model, with a coefficient of determination of 0.93, is effective and has good simulation levels.
 

Evapotranspiration Estimation Using Machine Learning Methods

Abstract The study examined the performance of four machine learning algorithms (regression trees, boosted trees, random forests, and artificial neural networks) for estimating evapotranspiration (ETo) based on incomplete meteorological data. Meteorological variables (mean and maximum air temperature, average air humidity, average level of solar radiation, vapor pressure deficit, extraterrestrial solar radiation, and day number of the year) were used as input. The simulation used two calculation scenarios: data with and without average solar radiation. The performance of the different machine learning models was evaluated using the mean square error, root mean square error, coefficient of determination, and slope of regression forced through the origin between the measured and simulated ETo. The results demonstrated that the applied models were able to describe nonlinear relationships between weather parameters and evapotranspiration. The accuracy of evapotranspiration estimation depended on the type of input variables and the machine learning model used. The highest level of evapotranspiration prediction was obtained using the artificial neural networks model. Including solar radiation data in the calculations improved the quality of evapotranspiration prediction in all four models. In the absence of data on the actual solar radiation reaching the Earth's surface, it is advisable to supplement the input data with data on extraterrestrial solar radiation and the day number of the year. Such an approach can be helpful in areas and situations with limited access to meteorological data.

Constraining the power-function complementary relationship with a steady-state Budyko equation for predicting terrestrial evapotranspiration globally

The power-function complementary relationship (CR) represents the latest advancement in definitive CR models, offering enhanced predictions of terrestrial evapotranspiration (E), all while elucidating the physical interpretations of its associated parameters. In this study, we introduced practical approaches to integrate the traditional Budyko framework into the novel CR model for global-scale E prediction. Under a steady-state assumption, the power-function CR was equated with the Turc-Mezentsev equation, thereby introducing an additional constraint for determining key parameters. We presented two illustrative cases where the aridity index and land-specific parameter constrain the exponent and the Priestley-Taylor coefficient of the CR, respectively. Compared to its calibration-free counterpart, the CR model constrained by the Budyko framework demonstrated improved performance in capturing spatial and temporal variations of E in point locations, mesoscale catchments, and large river basins. This improvement was not only from considering long-term precipitation partitioning, but also from the ability of the combined framework to rectify biases in input data. While the calibration-free methods exhibited poorer performance, they hold potential for superior results with higher-quality forcing inputs. By merging the Turc-Mezentsev equation with the power-function CR, this study provides insights into refining E predictions, accounting for climatic conditions and input data quality.

A Multi-sensor Analysis of Selected Reflectance-Based Crop Coefficient Models for Daily Maize Evapotranspiration Estimation

This study evaluated three reflectance-based crop coefficient models (RBCC) for daily maize actual evapotranspiration (ETa) estimates, using multispectral data from spaceborne, airborne, and proximal platforms. The goal was to identify the optimal multispectral sensor that gives more accurate daily ETa estimates. The remote sensing (RS) multispectral platforms included Landsat-8, Sentinel-2, Planet CubeSat, handheld multispectral radiometer (MSR), and unmanned aerial system or UAS, spatial resolution from 30 m to 0.03 m. Three RBCC models that use different vegetation indices as input variables were evaluated in the study. One RBCC uses the normalized difference vegetation index (NDVI). The second model uses the soil-adjusted vegetation index (SAVI), and the third model uses canopy cover (fc). The data for this study were from two maize research sites in Greeley and Fort Collins, Colorado, USA, collected in 2020 and 2021. The Greeley site had a subsurface drip system, while the Fort Collins site had surface irrigation (furrow). Daily maize ETa predictions were compared with observed daily maize ETa data from an Eddy Covariance system installed at each research site. Results indicated that, depending on the RS of ETa algorithm and platform, the optimal input RS data was different. The MSR sensor (1 m) provided the best remote sensing data (input) for the SAVI-based RBCC ETa model, with a maize ETa error (MBE±RMSE) of -0.13 (-3%)±0.67 (16%) mm/d. Sentinel-2 was the best sensor for the remaining two RBCC daily maize ETa algorithms, since the errors for the NDVI-based and fc-based RBCC models for maize ETa were 0.21 (5%)±0.78 (18%) mm/d and 0.59 (14%)±1.07 (25%) mm/d, respectively. These results indicate the need for methods to improve the spectral quality of the remote sensing data to improve spatial ETa estimates and advance sustainable irrigation water management.