terclim by ICS banner
IVES 9 IVES Conference Series 9 Combination of NIR multispectral information acquired from a ground moving vehicle with AI methods to assess the vine water status in a Tempranillo (Vitis vinifera L.) commercial vineyard

Combination of NIR multispectral information acquired from a ground moving vehicle with AI methods to assess the vine water status in a Tempranillo (Vitis vinifera L.) commercial vineyard

Abstract

Increasing water scarcity and unpredictable rainfall patterns necessitate efficient water management in grape production. This study proposes a novel approach for monitoring grapevine water status in a commercial vertically-shoot-positioned Vitis vinifera L. Tempranillo vineyard using non-invasive spectroscopy with a battery of different AI methods to assess vineyard water status, that could drive precise irrigation. A contactless, miniature NIR spectrometer (900-1900 nm) mounted on a moving vehicle (3 Km/h) was employed to collect spectral data from the vines’ northeast side along six dates in season 2021.Grapevines were monitored at solar noon using stem water potential (Ψs) as reference parameter of plant water status. At each date, 36 measurements of Ψs were taken making a total of 396 data in the whole season. AI techniques, including linear regression, gaussian process regression (GPR) support vector machine (SVM), and neural networks, trained with Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) algorithms were implemented in MATLAB (using the Regression Learner and Natural Net Fitting apps) to analyze the spectral data and predict vine water status. The optimized GPR model achieved the best performance, with a determination coefficient (R2P) above 0.83 and a root mean squared error of prediction (RMSEP) of 0.112 MPa. However, several neural network models trained with the LM algorithm exhibited superior performance, with R2P values over 0.92 and RMSEP values of approximately 0.080 MPa. This study demonstrates the potential of non-invasive spectroscopy combined with AI methods for accurate prediction of grapevine water status, paving the way for precision irrigation in vineyards.

DOI:

Publication date: June 14, 2024

Issue: Open GPB 2024

Type: Article

Authors

Fernando Rubio-Ordoyo1, María Paz Diago,1,2, Ignacio Barrio1,2, Juan Fernández-Novales1,2*

1 Department of Agriculture and Food Science. University of La Rioja. C/Madre de Dios 53. 26007. Logroño, (La Rioja) Spain
2 Institute of Sciences of Vine and Wine (CSIC, University of La Rioja, La Rioja Government) Finca La Grajera. Ctra. de Burgos Km 6. 26007. Logroño. (La Rioja). Spain

Contact the author*

Keywords

Vine water status, NIR spectrophotometer, Stem water potential, Gaussian Regression Process, Levenberg-Marquardt algorithm

Tags

IVES Conference Series | Open GPB | Open GPB 2024

Citation

Related articles…

Exploring the influence of grapevine rootstock on yield components 

Yield is an agronomic trait that is critical to the sustained success and profitability of the wine industry. In the context of global warming, overall yield tends to decrease. Rootstock has been identified as a relevant lever for adaptation to changing environmental conditions. The aims of this study are; i) to finely identify the components of the yield influenced by rootstock; ii) to characterise the rootstock × scion interaction; iii) to understand the trade-off between vigour and yield.

Composition and molar mass distribution of different must and wine colloids

A major problem for winemakers is the formation of proteinaceous haze after bottling. Although the exact mechanisms remain unclear, this haze is formed by unfolding and agglomeration of grape proteins, being additionally influenced by numerous further factors.

A new AI-based system for early and accurate vineyard yield forecasting

Vineyard yield forecasting is a key issue for vintage scheduling and optimization of winemaking operations. High errors in yield forecasting can be found in the wine industry, mainly due to the high spatial variability in vineyards, strong dependency on historical yield data, insufficient use of agroclimatic data and inadequate sampling methods

Development of spectral indices to monitoring non-destructive of ripeness for water stressed grapevine (Vitis vinifera L.) using contour map optimization

Accurate and non-destructive monitoring of grape ripening is essential for optimising harvest decisions, particularly under water stress conditions.

Ecophysiological performance of Vitis rootstocks under water stress

The use of rootstocks tolerant to soil water deficit is an interesting strategy to cope with limited water availability. Currently, several nurseries are breeding new genotypes, but the physiological basis of its responses under water stress are largely unknown. To this end, an ecophysiological assessment of the conventional 110-Richter (110R) and SO4, and the new M1 and M4 rootstocks was carried out in potted ungrafted plants. During one season, these Vitis genotypes were grown under greenhouse conditions and subjected to two water regimes, well-watered and water deficit. Water potentials of plants under water deficit down to < -1.4 MPa, and net photosynthesis (AN) <5 μmol m-2 s-1 did not cause leaf oxidative stress damage compared to well-watered conditions in any of the genotypes. The antioxidant capacity was sufficient to neutralize the mild oxidative stress suffered. Under both treatments, gravimetric differences in daily water use were observed among genotypes, leading to differences in the biomass of root, shoot and leaf. Under well-watered conditions, SO4 and 110R were the most vigorous and M1 and M4 the least. However, under water stress, SO4 exhibited the greatest reduction in biomass while M4 showed the lowest. Remarkably, under these conditions, SO4 reached the least negative stem water potential (Ψstem), while M1 reduced stomatal conductance (gs) and AN the most. In addition, SO4 and M1 genotypes also showed the highest and lowest hydraulic conductance values, respectively. Our results suggest that there are differences in water use regulation among genotypes, not only attributed to differences in stomatal regulation or intrinsic water use efficiency at the leaf level. Therefore, because no differences in canopy-to-root ratio were achieved, it is hypothesized that xylem vessel anatomical differences may be driving the reported differences among rootstocks performance. Results demonstrate that each Vitis rootstock differs in its ecophysiological responses under water stress.