Abstract
Understanding variations in sap flow rates and the environmental factors that influence sap flow is important for exploring grape water consumption patterns and developing reasonable greenhouse irrigation schedules. Three irrigation levels were established in this study: adequate irrigation (W1), moderate deficit irrigation (W2) and deficit irrigation (W3). Grape sap flow estimation models were constructed using partial least squares (PLS) and random forest (RF) algorithms, and the simulation accuracy and stability of these models were evaluated. The results showed that the daily mean sap flow rates in the W2 and W3 treatments were 14.65 and 46.94% lower, respectively, than those in the W1 treatment, indicating that the average daily sap flow rate increased gradually with an increase in the irrigation amount within a certain range. Based on model error and uncertainty analyses, the RF model had better simulation results in the different grape growth stages than the PLS model did. The coefficient of determination and Willmott’s index of agreement for RF model exceeded 0.78 and 0.90, respectively, and this model had smaller root mean square error and d-factor (evaluation index of model uncertainty) values than the PLS model did, indicating that the RF model had higher prediction accuracy and was more stable. The relative importance of the model predictors was determined. Moreover, the RF model more comprehensively reflected the influence of meteorological factors and the moisture content in different soil layers on the sap flow rate than the PLS model did. In summary, the RF model accurately simulated sap flow rates, which is important for greenhouse grape irrigation.
Highlights
Surface evapotranspiration (ET) is a very important material and energy conversion and transport process in the soil–plant–atmosphere system
From the perspective of energy balance, evapotranspiration accounts for approximately 59% of the available surface energy [2]; from the perspective of water balance, ET can account for two-thirds of the global average annual precipitation [2], of which transpiration accounts for more than 80% of land evapotranspiration; this ratio is even greater in arid regions [3]
support vector machines (SVM), XGBoost, artificial neural networks (ANNs) and deep neural network (DNN) models to estimate the daily transpiration of maize, and the results showed that the DNN model was slightly better than the SVM model, followed by the XGBoost model and the ANN model
Summary
Surface evapotranspiration (ET) is a very important material and energy conversion and transport process in the soil–plant–atmosphere system. ET is related to the cycling of water, energy and carbon on the earth [1]. From the perspective of energy balance, evapotranspiration accounts for approximately 59% of the available surface energy [2]; from the perspective of water balance, ET can account for two-thirds of the global average annual precipitation [2], of which transpiration accounts for more than 80% of land evapotranspiration; this ratio is even greater in arid regions [3]. Accurate estimation of surface evapotranspiration and its components, evaporation and transpiration can meet the needs of the rational management of global limited water resources and optimal irrigation decision-making projects for farmland. Accurate estimates can provide important countermeasures for potential changes in the global water cycle under various climate change scenarios [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
