Search

Crop evapotranspiration (ET) is one of the most important components in many hydrological processes. The crop reference evapotranspiration (ETo) represents the atmospheric water demand in each crop type, development stage, and management practices. The Penman-Monteith equation in the version suggested by the Food and Agriculture Organization (FAO56-PM), is one of the most used methods to estimate ETo. In several regions of the world, meteorological observations are not always available. The most recent reanalysis database ERA5-Land, released in 2019, can be useful to overcome this limit. The database provides, with a spatial grid of 0.1° latitude and 0.1° longitude, several hourly climate data such as air temperature, dew point temperature, solar radiation, and wind speed components all at 2.0 m above the soil surface, except wind speed components at 10 m, useful to apply the FAO56-PM equation. The objective of this research is to assess the quality of ERA5-Land climate variables data to estimate daily ETo in Sicily, Italy. The effect of the weather station’s elevation associated with the statistical indicators was also evaluated to verify how the morphology affects the measurements. Finally, the sensitivity analysis of the FAO56-PM equation was carried out to identify which climate variables have the most influence on the ETo estimation. For the period 2006–2015, the comparison between air temperature, global solar radiation, wind speed, and relative air humidity, measured from 39 ground weather stations in Sicily, and ERA5-Land was carried out and then, through FAO56-PM equation daily ETo values were estimated using both databases. The statistical indicators Root Mean Square Error (RMSE) and Mean Bias Error (MBE) confirm the possibility of considering the ERA5-Land a suitable solution to estimate ETo. The sensitivity analysis showed that good ETo estimation depends mainly on the accuracy of the relative air humidity and air temperature data.

The knowledge of crop evapotranspiration is crucial for several hydrological processes, including those related to the management of agricultural water sources. In particular, the estimations of actual evapotranspiration fluxes within fields are essential to managing irrigation strategies to save water and preserve water resources. Among the indirect methods to estimate actual evapotranspiration, ETa, the eddy covariance (EC) method allows to acquire continuous measurement of latent heat flux (LE). However, the time series of EC measurements are sometimes characterized by a lack of data due to the sensors' malfunctions. At this aim, Machine Learning (ML) techniques could represent a powerful tool to fill possible gaps in the time series. In this paper, the ML technique was applied using the Gaussian Process Regression (GPR) algorithm to fill gaps in daily actual evapotranspiration. The technique was tested in six different plots, two in Italy, three in the United States of America, and one in Canada, with different crops and climatic conditions in order to consider the suitability of the ML model in various contexts. For each site, the climate variables were not the same, therefore, the performance of the method was investigated on the basis of the available information. Initially, a comparison of ground and reanalysis data, where both databases were available, and between two different satellite products, when both databases were available, have been conducted. Then, the GPR model was tested. The mean and the covariance functions were set by considering a database of climate variables, soil water status measurements, and remotely sensed vegetation indices. Then, five different combinations of variables were analyzed to verify the suitability of the ML approach when limited input data are available or when the weather variables are replaced with reanalysis data. Cross-validation was used to assess the performance of the procedure. The model performances were assessed based on the statistical indicators: Root Mean Square Error (RMSE), coefficient of determination (R2), Mean Absolute Error (MAE), regression coefficient (b), and Nash-Sutcliffe efficiency coefficient (NSE). The quite high Nash Sutcliffe Efficiency (NSE) coefficient, and the root mean square error (RMSE) low values confirm the suitability of the proposed algorithm.