Machine learning models to predict daily actual evapotranspiration of citrus orchards under regulated deficit irrigation

Pagano, Antonino; Amato, Federico; Ippolito, Matteo; De, Dario; Croce, Daniele; Motisi, Antonio; Provenzano, Giuseppe; Tinnirello, Ilenia

doi:10.1016/j.ecoinf.2023.102133

Cited by 13 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, using groundbased thermography for estimating actual evapotranspiration is still rare. While recent progress has been made in the use of machine learning for estimating ET a (Pagano et al, 2023), the use of well tested physical models with data acquired with a simpler device can still provide robust estimates of the energy fluxes and evapotranspiration, comparable to the gold standard of eddy covariance, as demonstrated in our results.…”

Section: A Simplified and User-friendly Approachmentioning

confidence: 60%

Energy balance determination of crop evapotranspiration using a wireless sensor network

Jimenez-Berni,

Cabello-Leblic,

Lopez-Guerrero

et al. 2023

Front. Agron.

View full text Add to dashboard Cite

Determining crop evapotranspiration (ET) is essential for managing water at various scales, from regional water accounting to farm irrigation. Quantification of ET may be carried out by several procedures, being eddy covariance and energy balance the most established methods among the research community. One major limitation is the high cost of the sensors included in the eddy covariance or energy balance systems. We report here the development of a simpler device (CORDOVA-ET: COnductance Recording Device for Observation and VAlidation of ET) to determine crop ET based on industrial-grade, commercial off-the-shelf (COTS) sensors costing far less than research-grade sensors. The CORDOVA-ET contains a sensor package that integrates the basic micrometeorological instrumentation and the infrared temperature sensors required for estimating ET over crops using the energy balance approach. One novel feature is the presence of four different nodes that allow the determination of ET in four different locations within a field or in four different fields of the same crop, thus allowing an assessment of ET spatial variability. The system was conceived as an open-source and hardware alternative to commercial devices, using a collaborative approach for the development of a regional ET network in countries of North Africa and the Near East. Comparisons of radiation, temperature, humidity, and wind against those of research-grade sensors yielded excellent results, with coefficients of correlation (R2) above 0.96. The estimated reference ET calculated from these measurements showed R2 = 0.99 and a root mean square error (RMSE) of 0.22 mm/day. The infrared temperature measurements at the four different nodes showed an RMSE below 0.56°C. The energy balance components and estimates of ET from the CORDOVA-ET were validated against an eddy-covariance system over a wheat crop. The high (R2) for net radiation (0.98), sensible heat (0.88), and latent heat (0.86) showed good agreement between the modeled energy fluxes and the field measurements. The hardware components, acquisition, and data processing software are available as open-source repositories to facilitate adoption for different applications, from water use efficiency research to irrigation management.

show abstract

Section: A Simplified and User-friendly Approachmentioning

confidence: 60%

Energy balance determination of crop evapotranspiration using a wireless sensor network

Jimenez-Berni,

Cabello-Leblic,

Lopez-Guerrero

et al. 2023

Front. Agron.

View full text Add to dashboard Cite

show abstract

“…The combination of SVR-M1, as shown in Table 2, exhibits the most favorable performance assessment measures, with a correlation coefficient (CC) of 0.9997 and 0.9998 in the calibration and verification stages, respectively. These results are valuable for assessing the strong agree-ment between the observed and projected total water storage (TWS) values [46,62]. The impressive performance of k-SVR may be attributed to the use of a robust and adaptable machine learning algorithm capable of effectively addressing both classification and regression objectives.…”

Section: Results Of Ai-based Modelsmentioning

confidence: 99%

Advancing SDGs: Predicting Future Shifts in Saudi Arabia’s Terrestrial Water Storage Using Multi-Step-Ahead Machine Learning Based on GRACE Data

Yassin,

Abba,

Pradipta

et al. 2024

Water

View full text Add to dashboard Cite

The availability of water is crucial for the growth and sustainability of human development. The effective management of water resources is essential due to their renewable nature and their critical role in ensuring food security and water safety. In this study, the multi-step-ahead modeling approach of the Gravity Recovery and Climate Experiment (GRACE) terrestrial water storage (TWS) was utilized to gain insights into and forecast the fluctuations in water resources within Saudi Arabia. This study was conducted using mascon solutions obtained from the University of Texas Center for Space Research (UT-CSR) over the period of 2007 to 2017. The data were used in the development of artificial intelligence models, namely, an Elman neural network (ENN), a backpropagation neural network (BPNN), and kernel support vector regression (k-SVR). These models were constructed using various input variables, such as t-12, t-24, t-36, t-48, and TWS, with the output variable being the focus. A simple and weighted average ensemble was introduced to improve the accuracy of marginal and weak predictive results. The performance of the models was assessed with the use of several evaluation metrics, including mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), correlation coefficient (CC), and Nash–Sutcliffe efficiency (NSE). The results of the estimate indicate that k-SVR-M1 (NSE = 0.993, MAE = 0.0346) produced favorable outcomes, whereas ENN-M3 (NSE = 0.6586, MAE = 0.6895) emerged as the second most effective model. The combinations of all other models exhibited accuracies ranging from excellent to marginal, rendering them unreliable for decision-making purposes. Error ensemble methods improved the standalone model and proved merit. The results also serve as an important tool for monitoring changes in global water resources, aiding in drought management, and understanding the Earth’s water cycle.

show abstract

“…However, the interpretation of these predictive results should be contextualized within conventional techniques and measurements. A limited number of studies in existing literature have illustrated the potential of ANNs to estimate ET with fewer variables and greater prediction accuracy than models based on empirical data (Pagano et al, 2023).Yet, research has neither evaluated the predictive capabilities of ANNs for ET in M. × giganteus nor compared ANNs with empirical models for ET prediction.…”

Section: Discussionmentioning

confidence: 99%

Artificial Neural Networks Estimate Evapotranspiration For Miscanthus × Giganteus As Effectively As Empirical Model But With Fewer Inputs

Sungur,

Moore,

Bernacchi

et al. 2024

Preprint

View full text Add to dashboard Cite

Estimating actual evapotranspiration (ET) is particularly crucial for addressing how vegetation affects the water balance of ecosystems. ET estimation can be complex with empirical models due to their many parameters and reliance on aridity. In contrast, artificial neural networks (ANNs) could potentially estimate ET with fewer and more common meteorological parameters. In this study, we trained two ANNs, one using a feed-forward approach (FFN) and the other a nonlinear auto-regressive network (NARX), to predict ET and compared them to the commonly used empirical model Granger and Gray (GG). We trained our models on a nine-year eddy covariance (EC) dataset for Miscanthus × giganteus (M. × giganteus) from Illinois (UIEF), then tested them using out-of-sample data from both UIEF and a different location in Iowa (SABR) to compare the accuracy of FFN, NARX, and GG models in estimating daily ET. A combination of air temperature (Ta) and solar radiation (Rs) was chosen as inputs due to the highest R2 for FFN (R2= 0.79, 0.81, and 0.79 for training, testing, and validation, respectively) and only Ta for NARX (R2= 0.70 for out-of-sample validation). The predictive power of the FFN model was superior to the NARX and GG models at the UIEF site (R2= 0.84, 0.70, and 0.83 for out-of-sample validation, respectively). Our analysis showed that ANN approaches are as accurate as empirical approaches for estimating ET but use fewer inputs.

show abstract

Machine learning models to predict daily actual evapotranspiration of citrus orchards under regulated deficit irrigation

Cited by 13 publications

References 58 publications

Energy balance determination of crop evapotranspiration using a wireless sensor network

Energy balance determination of crop evapotranspiration using a wireless sensor network

Advancing SDGs: Predicting Future Shifts in Saudi Arabia’s Terrestrial Water Storage Using Multi-Step-Ahead Machine Learning Based on GRACE Data

Artificial Neural Networks Estimate Evapotranspiration For Miscanthus × Giganteus As Effectively As Empirical Model But With Fewer Inputs

Contact Info

Product

Resources

About