A Non-Invasive Method Based on Computer Vision for Grapevine Cluster Compactness Assessment Using a Mobile Sensing Platform under Field Conditions.

Grapevine cluster compactness affects grape composition, fungal disease incidence, and wine quality. Thus far, cluster compactness assessment has been based on visual inspection performed by trained evaluators with very scarce application in the wine industry. The goal of this work was to develop a new, non-invasive method based on the combination of computer vision and machine learning technology for cluster compactness assessment under field conditions from on-the-go red, green, blue (RGB) image acquisition. A mobile sensing platform was used to automatically capture RGB images of grapevine canopies and fruiting zones at night using artificial illumination. Likewise, a set of 195 clusters of four red grapevine varieties of three commercial vineyards were photographed during several years one week prior to harvest. After image acquisition, cluster compactness was evaluated by a group of 15 experts in the laboratory following the International Organization of Vine and Wine (OIV) 204 standard as a reference method. The developed algorithm comprises several steps, including an initial, semi-supervised image segmentation, followed by automated cluster detection and automated compactness estimation using a Gaussian process regression model. Calibration (95 clusters were used as a training set and 100 clusters as the test set) and leave-one-out cross-validation models (LOOCV; performed on the whole 195 clusters set) were elaborated. For these, determination coefficient (R2) of 0.68 and a root mean squared error (RMSE) of 0.96 were obtained on the test set between the image-based compactness estimated values and the average of the evaluators' ratings (in the range from 1-9). Additionally, the leave-one-out cross-validation yielded a R2 of 0.70 and an RMSE of 1.11. The results show that the newly developed computer vision based method could be commercially applied by the wine industry for efficient cluster compactness estimation from RGB on-the-go image acquisition platforms in commercial vineyards.

On-The-Go Hyperspectral Imaging Under Field Conditions and Machine Learning for the Classification of Grapevine Varieties.

Grapevine varietal classification is an important plant phenotyping issue for grape growing and wine industry. This task has been achieved from destructive techniques like classic ampelography and DNA analysis under laboratory conditions. This work displays a new approach for the classification of a high number of grapevine (Vitis vinifera L.) varieties under field conditions using on-the-go hyperspectral imaging and different machine learning algorithms. On-the-go imaging was performed under natural illumination using a hyperspectral camera mounted on an all-terrain vehicle at 5 km/h. Spectra were acquired over two different leaf phenological stages on the canopy of 30 different varieties on a commercial vineyard located in La Rioja, Spain. A total of 1,200 spectral samples were generated. Support vector machines (SVM) and artificial neural networks (multilayer perceptrons, MLP) were used for the development of a large number of models, testing different algorithm parameters and spectral pre-processing techniques. Both classifiers yielded notable performance values and were able to train models with recall F1 scores and area under the receiver operating characteristic curve marks up to 0.99 for 5-fold cross validation. Statistical analyses supported that the best SVM kernel was linear and the best activation function for MLP was the hyperbolic tangent function. The prediction performance for individual varieties of MLP ranged from 0.94 to 0.99, displaying low levels of variability. In the case of SVM, slightly higher differences were obtained, ranging from 0.83 to 0.97 for individual varieties. These results support the possibility of deploying an on-the-go hyperspectral imaging system in the field capable of successfully classifying leaves from different grapevine varieties. This technology could thus be considered as a new useful non-destructive tool for plant phenotyping under field conditions.

Development and Validation of a New Methodology to Assess the Vineyard Water Status by On-the-Go Near Infrared Spectroscopy.

Assessing water status and optimizing irrigation is of utmost importance in most winegrowing countries, as the grapevine vegetative growth, yield, and grape quality can be impaired under certain water stress situations. Conventional plant-based methods for water status monitoring are either destructive or time and labor demanding, therefore unsuited to detect the spatial variation of moisten content within a vineyard plot. In this context, this work aims at the development and comprehensive validation of a novel, non-destructive methodology to assess the vineyard water status distribution using on-the-go, contactless, near infrared (NIR) spectroscopy. Likewise, plant water status prediction models were built and intensely validated using the stem water potential (ψs) as gold standard. Predictive models were developed making use of a vast number of measurements, acquired on 15 dates with diverse environmental conditions, at two different spatial scales, on both sides of vertical shoot positioned canopies, over two consecutive seasons. Different cross-validation strategies were also tested and compared. Predictive models built from east-acquired spectra yielded the best performance indicators in both seasons, with determination coefficient of prediction ([Formula: see text]) ranging from 0.68 to 0.85, and sensitivity (expressed as prediction root mean square error) between 0.131 and 0.190 MPa, regardless the spatial scale. These predictive models were implemented to map the spatial variability of the vineyard water status at two different dates, and provided useful, practical information to help delineating specific irrigation schedules. The performance and the large amount of data that this on-the-go spectral solution provides, facilitates the exploitation of this non-destructive technology to monitor and map the vineyard water status variability with high spatial and temporal resolution, in the context of precision and sustainable viticulture.

Vineyard water status assessment using on-the-go thermal imaging and machine learning.

The high impact of irrigation in crop quality and yield in grapevine makes the development of plant water status monitoring systems an essential issue in the context of sustainable viticulture. This study presents an on-the-go approach for the estimation of vineyard water status using thermal imaging and machine learning. The experiments were conducted during seven different weeks from July to September in season 2016. A thermal camera was embedded on an all-terrain vehicle moving at 5 km/h to take on-the-go thermal images of the vineyard canopy at 1.2 m of distance and 1.0 m from the ground. The two sides of the canopy were measured for the development of side-specific and global models. Stem water potential was acquired and used as reference method. Additionally, reference temperatures Tdry and Twet were determined for the calculation of two thermal indices: the crop water stress index (CWSI) and the Jones index (Ig). Prediction models were built with and without considering the reference temperatures as input of the training algorithms. When using the reference temperatures, the best models casted determination coefficients R2 of 0.61 and 0.58 for cross validation and prediction (RMSE values of 0.190 MPa and 0.204 MPa), respectively. Nevertheless, when the reference temperatures were not considered in the training of the models, their performance statistics responded in the same way, returning R2 values up to 0.62 and 0.65 for cross validation and prediction (RMSE values of 0.190 MPa and 0.184 MPa), respectively. The outcomes provided by the machine learning algorithms support the use of thermal imaging for fast, reliable estimation of a vineyard water status, even suppressing the necessity of supervised acquisition of reference temperatures. The new developed on-the-go method can be very useful in the grape and wine industry for assessing and mapping vineyard water status.

Image analysis-based modelling for flower number estimation in grapevine.

BACKGROUND: Grapevine flower number per inflorescence provides valuable information that can be used for assessing yield. Considerable research has been conducted at developing a technological tool, based on image analysis and predictive modelling. However, the behaviour of variety-independent predictive models and yield prediction capabilities on a wide set of varieties has never been evaluated. RESULTS: Inflorescence images from 11 grapevine Vitis vinifera L. varieties were acquired under field conditions. The flower number per inflorescence and the flower number visible in the images were calculated manually, and automatically using an image analysis algorithm. These datasets were used to calibrate and evaluate the behaviour of two linear (single-variable and multivariable) and a nonlinear variety-independent model. As a result, the integrated tool composed of the image analysis algorithm and the nonlinear approach showed the highest performance and robustness (RPD = 8.32, RMSE = 37.1). The yield estimation capabilities of the flower number in conjunction with fruit set rate (R2 = 0.79) and average berry weight (R2 = 0.91) were also tested. CONCLUSION: This study proves the accuracy of flower number per inflorescence estimation using an image analysis algorithm and a nonlinear model that is generally applicable to different grapevine varieties. This provides a fast, non-invasive and reliable tool for estimation of yield at harvest. © 2016 Society of Chemical Industry.

Effects of ambient solar UV radiation on grapevine leaf physiology and berry phenolic composition along one entire season under Mediterranean field conditions.

In the present study we assessed the effects of ambient solar UV exclusion on leaf physiology, and leaf and berry skin phenolic composition, of a major grapevine cultivar (Tempranillo) grown under typically Mediterranean field conditions over an entire season. In general, the effects of time were stronger than those of UV radiation. Ambient UV caused a little stressing effect (eustress) on leaf physiology, with decreasing net photosynthesis rates and stomatal conductances. However, it was not accompanied by alterations in Fv/Fm or photosynthetic pigments, and was partially counterbalanced by the UV-induced accumulation of protective flavonols. Consequently, Tempranillo leaves are notably adapted to current UV levels. The responses of berry skin phenolic compounds were diverse, moderate, and mostly transitory. At harvest, the clearest response in UV-exposed berries was again flavonol accumulation, together with a decrease in the flavonol hydroxylation level. Contrarily, responses of anthocyanins, flavanols, stilbenes and hydroxycinnamic derivatives were much more subtle or nonexistent. Kaempferols were the only compounds whose leaf and berry skin contents were correlated, which suggests a mostly different regulation of phenolic metabolism for each organ. Interestingly, the dose of biologically effective UV radiation (UVBE) was correlated with the leaf and berry skin contents of quercetins and kaempferols; relationships were linear except for the exponential relationship between UVBE dose and berry skin kaempferols. This opens management possibilities to modify kaempferol and quercetin contents in grapevine through UV manipulation.

Use of Visible and Short-Wave Near-Infrared Hyperspectral Imaging To Fingerprint Anthocyanins in Intact Grape Berries.

In red grape berries, anthocyanins account for about 50% of the skin phenols and are responsible for the final wine color. Individual anthocyanin levels and compositional profiles vary with cultivar, maturity, season, region, and yield and have been proposed as chemical markers to differentiate wines and to provide valuable information regarding the adulteration of musts and wines. A fast, easy, solvent-free, nondestructive method based on visible, short-wave, and near-infrared hyperspectral imaging (HSI) in intact grape berries to fingerprint the color pigments in eight different grape varieties was developed and tested against HPLC. Predictive models based on modified partial least-squares (MPLS) were built for 14 individual anthocyanins with coefficients of determination of cross-validation (R2CV) ranging from 0.70 to 0.93. For the grouping of total and nonacylated anthocyanins, external validation was conducted with coefficient of determination of prediction (R2P) of 0.86. HSI could potentially become an alternative to HPLC with reduced analysis time and labor costs while providing reliable and robust information on the anthocyanin composition of grape berries.

Data Mining and NIR Spectroscopy in Viticulture: Applications for Plant Phenotyping under Field Conditions.

Plant phenotyping is a very important topic in agriculture. In this context, data mining strategies may be applied to agricultural data retrieved with new non-invasive devices, with the aim of yielding useful, reliable and objective information. This work presents some applications of machine learning algorithms along with in-field acquired NIR spectral data for plant phenotyping in viticulture, specifically for grapevine variety discrimination and assessment of plant water status. Support vector machine (SVM), rotation forests and M5 trees models were built using NIR spectra acquired in the field directly on the adaxial side of grapevine leaves, with a non-invasive portable spectrophotometer working in the spectral range between 1600 and 2400 nm. The ν-SVM algorithm was used for the training of a model for varietal classification. The classifiers' performance for the 10 varieties reached, for cross- and external validations, the 88.7% and 92.5% marks, respectively. For water stress assessment, the models developed using the absorbance spectra of six varieties yielded the same determination coefficient for both cross- and external validations (R² = 0.84; RMSEs of 0.164 and 0.165 MPa, respectively). Furthermore, a variety-specific model trained only with samples of Tempranillo from two different vintages yielded R² = 0.76 and RMSE of 0.16 MPa for cross-validation and R² = 0.79, RMSE of 0.17 MPa for external validation. These results show the power of the combined use of data mining and non-invasive NIR sensing for in-field grapevine phenotyping and their usefulness for the wine industry and precision viticulture implementations.

Estimation of total soluble solids in grape berries using a hand-held NIR spectrometer under field conditions.

BACKGROUND: Recent studies have reported the potential of near infrared (NIR) spectral analysers for monitoring the ripeness of grape berries as an alternative to wet chemistry methods. This study covers various aspects regarding the calibration and implementation of predictive models of total soluble solids (TSS) in grape berries using laboratory and in-field collected NIR spectra. RESULTS: The performance of the calibration models obtained under laboratory conditions indicated that at least 700 berry samples are required to assure enough prediction accuracy. A statistically significant error reduction (ΔRMSECV = 0.1°Brix) with P < 0.001 was observed when measuring berries without epicuticular wax, which was negligible from a practical point of view. Under field conditions, the prediction errors (RMSEP = 1.68°Brix, and SEP = 1.67°Brix) were close to those obtained with the laboratory dataset (RMSEP = 1.42°Brix, SEP = 1.40°Brix). CONCLUSION: This work clarifies several methodological factors to develop a protocol for in-field assessing TSS in grape berries using an affordable, non-invasive, portable NIR spectral analyser. © 2015 Society of Chemical Industry.

Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer.

The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network's modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves monitored at post-veraison and harvest was also built up, reaching a 77.08% of correctly classified samples. The outcomes obtained demonstrate the capability of using a reliable method for fast, in-field, non-destructive grapevine varietal classification that could be very useful in viticulture and wine industry, either global or site-specific.

Assessment of cluster yield components by image analysis.

BACKGROUND: Berry weight, berry number and cluster weight are key parameters for yield estimation for wine and tablegrape industry. Current yield prediction methods are destructive, labour-demanding and time-consuming. In this work, a new methodology, based on image analysis was developed to determine cluster yield components in a fast and inexpensive way. RESULTS: Clusters of seven different red varieties of grapevine (Vitis vinifera L.) were photographed under laboratory conditions and their cluster yield components manually determined after image acquisition. Two algorithms based on the Canny and the logarithmic image processing approaches were tested to find the contours of the berries in the images prior to berry detection performed by means of the Hough Transform. Results were obtained in two ways: by analysing either a single image of the cluster or using four images per cluster from different orientations. The best results (R(2) between 69% and 95% in berry detection and between 65% and 97% in cluster weight estimation) were achieved using four images and the Canny algorithm. The model's capability based on image analysis to predict berry weight was 84%. CONCLUSION: The new and low-cost methodology presented here enabled the assessment of cluster yield components, saving time and providing inexpensive information in comparison with current manual methods.

Effects of UV exclusion on the physiology and phenolic composition of leaves and berries of Vitis vinifera cv. Graciano.

BACKGROUND: Ultraviolet (UV) radiation induces adaptive responses that can be used for plant production improvement. The aim of this study was to assess the effect of solar UV exclusion on the physiology and phenolic compounds of leaves and berry skins of Vitis vinifera L. cv. Graciano under field conditions. Phenolic compounds were analyzed globally and individually in both the vacuolar fraction and, for the first time in grapevine, the cell wall-bound fraction. These different locations may represent diverse modalities of phenolic response to and protection against UV. RESULTS: UV exclusion led to a decrease in Fv /Fm in leaves, revealing that solar UV is needed for adequate photoprotection. Only p-caffeoyl-tartaric acid from the soluble fraction of leaves and myricetin-3-O-glucoside from the soluble fraction of berry skins were significantly higher in the presence of UV radiation, and thus they could play a role in UV protection. Other hydroxycinnamic acids, flavonols, flavanols and stilbenes did not respond to UV exclusion. CONCLUSION: UV exclusion led to subtle changes in leaves and berry skins of Graciano cultivar, which would be well adapted to current UV levels. This may help support decision-making on viticultural practices modifying UV exposure of leaves and berries, which could improve grape and wine quality.

Assessment of flower number per inflorescence in grapevine by image analysis under field conditions.

BACKGROUND: Flowers, flowering and fruit set are key determinants of grapevine yield. Currently, practical methods to assess the flower number per inflorescence, necessary for fruit set estimation, are time and labour demanding. This work aims at developing a simple, cheap, fast, accurate and robust machine vision methodology to be applied to RGB images taken under field conditions, to estimate the number of flowers per inflorescence automatically. RESULTS: Ninety images of individual inflorescences of Vitis vinifera L. cultivars Tempranillo, Graciano and Carignan were acquired in the vineyard with a pocket RGB camera prior to flowering, and used to develop and test the 'flower counting' algorithm. Strong and significant relationships, with R(2) above 80% for the three cultivars were observed between actual and automated estimation of inflorescence flower numbers, with a precision exceeding 90% for all cultivars. CONCLUSION: The developed algorithm proved that the analysis of digital images captured by pocket cameras under uncontrolled outdoors conditions was able to automatically provide a useful estimation of the number of flowers per inflorescence of grapevines at early stages of flowering.

Phenolic composition of Tempranillo wines following early defoliation of the vines.

BACKGROUND: Early defoliation is a viticultural practice aimed at crop control. So far, the impact of early leaf removal on the monomeric phenolic composition of wines has not been explored. This study examines the effects of early defoliation on the phenolic profile and content in Tempranillo wines. The influence of the defoliation method (manual vs mechanical) and the timing of leaf removal (pre-bloom vs fruit set) was investigated. RESULTS: Over two consecutive seasons, 2007 and 2008, the monomeric phenolic composition in Tempranillo wines was studied by high-performance liquid chromatography with photodiode array detection, and 22 compounds were identified and quantified. Overall, early defoliation led to wines more intensely coloured, of higher alcohol content and with larger concentrations of hydroxycinnamic acids, flavonols and anthocyanins (in 2008 only for mechanical treatments). In the absence of fungal infection, resveratrol was found to increase in wines corresponding to early defoliation treatments. The method of leaf removal seemed to be more critical than the timing of intervention, and larger effects on wine phenolic composition were observed for mechanical treatments. CONCLUSION: Early defoliation proved to be an effective technique for improving the phenolic composition of Tempranillo wines, by favouring the accumulation of hydroxycinnamics, flavonols and anthocyanins. This is an important achievement, as wine quality is often described by its colour and phenolic attributes.