terclim by ICS banner
IVES 9 IVES Conference Series 9 GiESCO 9 Using the fraction of transpirable soil water to estimate grapevine leaf water potential: comparing the classical statistical regression approach to machine learning algorithms

Using the fraction of transpirable soil water to estimate grapevine leaf water potential: comparing the classical statistical regression approach to machine learning algorithms

Abstract

Context and purpose of the study – Weather uncertainty is forcing Mediterranean winegrowers to adopt new irrigation strategies to cope with water scarcity while ensuring a sustainable yield and improved berry and wine quality standards. Therefore, more accurateand high-resolution monitoring of soil water content and vine water status is a major concern. Leaf water potential measured at pre-dawn (YPD) is considered to be in equilibrium with soil water potential and is highly correlated with soil water content at the soil depth where roots extract water.
The aim of this study is to evaluate a dataset of eco-physiological data collected in a 3-year vineyard irrigation trial to assess the explanatory power of the fraction of transpirable soil water (FTSW) to predict YPD by comparing the classical statistical regression approach with a machine learning algorithm (MLA).

Material and methods – Deficit irrigation trials were conducted from 2013 to 2015 in a commercial vineyard in the Alentejo (southern Portugal). Trial plot was planted with Vitis vinifera (L.) cv. Aragonez (ARA)(syn. Tempranillo), grafted onto 1103 Paulsen rootstock and spaced 1.5 m within and 3.0 m between N-S oriented rows. The experimental layout was a randomized complete block design with two treatments: sustained deficit irrigation (SDI – control; ~30% Etc) and regulated deficit irrigation (RDI; ~15% Etc) and 4 replicates per treatment. The YPD and soil water content were measured the day before and the day after each irrigation event by using a capacitance probe down to a soil depth of 1 m and a Scholander pressure chamber. Models predicting YPD from FTSW were trained on 600 data cases and validated on an independent dataset (10% of all available data) using MATLAB R2022b (Mathworks, USA) and STATISTICA 13 (Tibco, USA). 

Results – Our results show that 87.6% of the observed YPD variability is explained by the FTSW using a linear regression model (LRM) with a linear-logarithmic transformation of the independent variables. The accuracy of the prediction model, as measured by root mean squared error (RMSE), in the independent validation dataset, was 0.08 MPa. These results were compared to the estimation accuracy of a set of MLAs. Two support vector machine (SVM) algorithms with a quadratic and a medium Gaussian kernel function, and three Gaussian process regression (GPR) algorithms with an exponential, a squared exponential and a rational quadratic kernel functions were tested. All trained MLAs showed an accuracy in explaining the variability of the YPD (86-87%) similar to the LRM. An increase in the model explained variability of the independent dataset from 89 to 91% was observed in all MLAs, with an accuracy of 0.087 to 0.096MPa as measured by the RMSE.
Both statistical methods indicate that YPD can be estimated with good accuracy using FTSW as an explanatory variable. Regarding the comparative performance of the two types of statistical models no differences were found in the ability of the tested models to estimate YPD.

DOI:

Publication date: June 29, 2023

Issue: GiESCO 2023

Type: Poster

Authors

Ricardo EGIPTO1*, J. Miguel COSTA2, José SILVESTRE1, Carlos M. LOPES2

1INIAV IP – Polo de Inovação de Dois Portos, 2565-191 Dois Portos, Portugal
2LEAF – Linking Landscape, Environment, Agriculture and Food, Instituto Superior de Agronomia, Univ. Lisboa, Portugal

Contact the author*

Keywords

deficit irrigation, soil water content, machine learning algorithms

Tags

GiESCO | GIESCO 2023 | IVES Conference Series

Citation

Related articles…

Quantification of newly identified C8 aroma compounds in musts and wines as an analytical tool for the early detection of Fresh Mushroom Off-Flavor

The Fresh Mushroom Off-Flavor (FMOff) is a concerning undesirable aroma in wine specific of certain vintages, characterized by a typical button mushroom aroma. The appearance of this off-flavor is linked to the presence of certain fungus on the grape [1-3].

Comparison of the principal production methods for alcohol-free wine based on analytical parameters

Production, demand, and brand awareness of dealcoholized wine (<0.5% v/v) is steadily increasing worldwide. However, there have been few studies to date investigating and comparing the different physical processes for dealcoholizing wine.

Evolution of oak barrels C-glucosidic ellagitannins in model wine solution

Oak wood has a significant impact on the chemical composition of wine, leading to transformations that influence its organoleptic properties, such as its aroma, structure, astringency, bitterness and color. Among the main extractible non-volatile polyphenol compounds released from oak wood, the ellagitannins are found [1].

Single plant oenotyping: a novel approach to better understand the impact of drought on red wine quality in Vitis x Muscadinia genotypes

Adopting disease-tolerant varieties is an efficient solution to limit environmental impacts linked to pesticide use in viticulture. In most breeding programs, these varieties are selected depending on their abilities to tolerate diseases, but little is known about their behaviour in response to abiotic constraints.

Quality assessment of partially dealcoholized and dealcoholized red, rosé, and white wines: physicochemical, color, volatile, and sensory insights

The global non-alcoholic wine market is projected to grow from USD 2.7 billion in 2024 to USD 6.97 billion by 2034, driven by health awareness, lifestyle shifts, and religious factors [1-3]. Consequently, the removal of alcohol can significantly alter the key quality parameters of wine.