Management zones delineation using fuzzy clustering techniques in grapevines

Precision viticulture aims at managing vineyards at a sub-field scale according to the real needs of each part of the field. The current study focused on delineating management zones using fuzzy clustering techniques and developing a simplified approach for the comparison of zone maps. The study was carried out in a 1.0 ha commercial vineyard in Central Greece during 2009 and 2010. Variation of soil properties across the field was initially measured by means of electrical conductivity, soil depth and topography. To estimate grapevine canopy properties, NDVI was measured at different stages during the vine growth cycle. Yield and grape composition (must sugar content and total acidity) mapping was carried out at harvest. Soil properties, yield and grape composition parameters showed high spatial variability. All measured data were transformed on a 48-cell grid (10 × 20 m) and maps of two management zones were produced using the MZA software. Pixel-by-pixel comparison between maps of electrical conductivity, elevation, slope, soil depth and NDVI with yield and grape composition maps, set as reference parameters, allowed for the calculation of the degree of agreement, i.e. the percentage of pixels belonging to the same zone. The degree of agreement was used to select the best-suited parameters for final management zones delineation. For the year 2009 soil depth, early and mid season NDVI were used for yield-based management zones while for quality-based management zones ECa, early and mid season NDVI were utilized. For the year 2010 ECa, elevation and NDVI acquired during flowering and veraison were used for the delineation of yield-based management zones while for quality-based management zones ECa and NDVI acquired during flowering and harvest were utilized. Results presented here could be the basis for simple management zone delineation and subsequent improved vineyard management.     

Relevance of sink-size estimation for within-field zone delineation in vineyards

Source to sink size ratio, i.e.: the relative abundance of photosynthetically active organs (leaves) with regards to photosynthate demanding organs (mainly bunches), is widely known to be one of the main drivers of grape oenological quality. However, due to the difficulty of remote sink size estimation, Precision Viticulture (PV) has been mainly based on within-field zone delineation using vegetation indices. This approach has given only moderately satisfactory results for discriminating zones with differential quality. The aim of this work was to investigate an approach to delineate within-vineyard quality zones that includes an estimator of sink size in the data-set. The study was carried out during two consecutive seasons on a 4.2 ha gobelet-trained cv. ‘Tempranillo’ vineyard. Zone delineation was performed using Normalized Difference Vegetation Index (NDVI), soil apparent electrical conductivity (EC_a) and bunch number (BN) data. These variables were considered separately, in pairs, or the three altogether, using fuzzy k-means cluster analysis for combinations. The zones delineated based on single variables did not allow a sufficient discrimination for grape composition at harvest, NDVI being the only variable that by itself resulted in zones that to some extent differed in grape composition. On the contrary, when two variables were combined, discrimination in terms of grape composition improved remarkably, provided the sink size estimation variable (BN) was included in the combination. Lastly, the combination of the three variables yielded the best discriminating zoning, improving slightly on those provided by NDVI + BN and EC_a + BN combinations. Thus, the relevance of including a variable related to sink size (in this case the number of bunches per plant) has been confirmed, which makes its consideration highly advisable for any PV work aiming at zone delineation for grape quality purposes.     

Evaluation of vegetation indices and apparent soil electrical conductivity for site-specific vineyard management in Chile

Spatial variability of Chilean vineyards, in terms of yield and quality, is high, which fully justifies site-specific management, particularly differential harvest. In this study, the most common zoning tools (NDVI and ECa measurements) were evaluated and compared. Comparisons also included a calibrated GVI. Two contrasting large field experiments (pruning, irrigation, and N fertilization treatments) were established in vineyards to (1) evaluate two vegetation indices: (i) a non-calibrated airplane-based NDVI and (ii) calibrated satellite-based GVI and to (2) evaluate the ECa measurements. The GVI was also assessed at the commercial level, in different vineyards and valleys. The GVI was more sensitive in discriminating grape yields and quality while the NDVI failed to adequately sense vigor patterns and fruit quality in the more homogeneous site. Thus, a calibrated GVI can be recommended as a better tool than NDVI for defining management zones as well as making spatial and temporal comparisons among fields and seasons. In general, ECa explained few differences in the alluvial soil properties and did not predict differences in plant vigor as measured by either vegetation indices, therefore ECa by itself was not a good estimator of the most commonly measured soil properties for establishing management zones in these fields with low variability in terms of EC and other soil characteristics.     

Evaluating unoccupied aerial systems (UAS) imagery as an alternative tool towards cotton-based management zones

Unoccupied aerial system (UAS) imagery may serve as an additional tool towards management zone delineation. This is because UAS data collection is relatively flexible. However, it is unclear how useful UASs can be towards generating management zones, relative to preexisting tools (e.g. apparent soil electrical conductivity or EC_a). The purpose of this study, therefore, was to evaluate UAS imagery, relative to EC_a, in terms of their ability to: 1) predict cotton traits (i.e. height, seed cotton yield), and 2) define cotton management zones based on these traits. Single-season UAS images from multispectral/thermal sensors were collected and processed into Normalized Difference Vegetation Index (NDVI) and radiometric surface temperature (T_r), respectively. Management zones were also delineated using digital camera (RGB) imagery collected at periods before planting and near harvest. RGB management zones were delineated by a novel open boll mapping approach. In-season NDVI and T_r layers were significant (P?<?0.01) predictors of canopy height. Additionally, NDVI and T_r maps produced statistically different management zones during flowering and boll filling growth stages in terms of yield (P?=?0.001 or less). Open boll layers were all more accurate predictors of cotton seed yield than EC_a data—these two layers also produced statistically distinct management zones. ANOVA tests revealed that, given EC_a alone, adding UAS information via the RGB open boll map resulted in a significantly different yield prediction model (P?<?0.001). These results suggest that UAS imagery can offer valuable information for cotton management zone delineation that other techniques cannot.

     

Electrical imaging of soil water availability to grapevine: a benchmark experiment of several machine-learning techniques

Electrical resistivity (ER) can be used to assess soil water in the field. This study investigated the possibility of extending the use of ER to measure plant available soil water variables, i.e. available soil water (ASW), total transpirable SW (TTSW), and fraction of transpirable SW (FTSW) using a pedotransfer approach. In a vineyard, 224 electrical resistivity tomography (ERT) transects and 672 time domain reflectometry (TDR) soil water profiles were acquired over 2 years. Soil physical–chemical properties were measured on 73 soil samples from eight different sites. To estimate the amount of soil water available to plants, grapevine (Vitis vinifera L.) water status was monitored by means of leaf water potentials. A benchmark experiment was carried out to compare four machine-learning techniques: multivariate adaptive regression splines (MARS), k-nearest neighbours (KNN), random forest (RF), and gradient boosting machine (GBM). Model interpretation led to a deeper understanding of the relationships between electrical resistivity and soil properties when predicting soil water availability for the plant. The models assessed had good predictive performance and were therefore used to map ASW, TTSW and FTSW in the vineyard. ER coupled to machine-learning algorithms was shown to be a good proxy for quantification and visualisation of plant available soil water with low disturbance.     

Evaluation of the use of LIDAR laser scanner to map pruning wood in vineyards and its potential for management zones delineation

Vine vigour assessment has been a major concern of precision viticulture studies in order to identify areas of uniform vine performance within vineyards. Moreover, the counting and weighing of winter dormant canes is considered as the most informative measurement to indicate vine balance and is commonly performed manually by grape growers for management purposes. The main concern of this measurement is that it is time consuming and laborious and it cannot accommodate detailed sampling density. In the present study, the potential of using laser scanner technology as an automated, easy and rapid way to perform mapping of the winter pruning wood across the vineyard was investigated. The study was conducted during 2010 and 2011, in a one hectare commercial vineyard in central Greece, planted with cv. Agiorgitiko, a traditional Greek variety for the production of red wine. Parameters of topography, soil depth, soil texture, canopy properties (NDVI), yield, and grape quality were mapped and analysed in conjunction to winter canes weighing at pruning time. The mapping of the dormant canes was carried out using a 2D laser scanner sensor prior to pruning and manually measuring the pruning weight on a 10 × 20 m grid. Laser scanner measurements showed significant relationship in both 2010 and 2011 with pruning weight (r = 0.809 and r = 0.829 respectively, p < 0.001), yield and early season NDVI, showing the potential of using laser scanner measurements to assess variability in vine vigour within vineyards. These results suggest that laser scanners offer great promise to characterize within field variability in vine performance.     

Ground-Sensor Soil Reflectance as Related to Soil Properties and Crop Response in a Cotton Field

Bare soil reflectance from airborne imagery or laboratory spectrometers has been used to infer soil properties such as soil texture, organic matter, water content, salinity and crop residue cover. However, the relation of soil properties to reflectance data often varies with soil type and conditions and surface reflectance may not be representative of the conditions in the root zone. The objectives of this study were to assess the soil reflectance data obtained by ground-based sensors and to model soil properties in the root zone as a function of surface soil reflectance and plant response. Ground-based sensors were used to simultaneously monitor soil and canopy reflectance in the visible and near-infrared (VNIR) along six rows and in two growth stages in a 7 ha cotton field. The reflectance data were compared to soil properties, leaf nutrients and biomass measured at 33 sampling positions along the rows. Brightness values of the blue and green bands of soil reflectance were better correlated to soil water content, particulate organic matter and extractable potassium and phosphorus, while those in the red and NIR bands were correlated to soil carbonate content, total nitrogen, electrical conductivity and foliar nutrients. The correlation of red soil reflectance with canopy reflectance was significant and indicated an indirect inverse relationship between soil fertility and plant stress. The integration of surface soil reflectance and plant response variables in a multiple regression model did not substantially improve the prediction of soil properties in the root zone. However, crop nutrient status explained a significant portion of the spatial variability of soil properties related to nitrification processes when soil reflectance did not. The implication of these findings to agricultural management is discussed.     

Are precision agriculture tools and methods relevant at the whole-vineyard scale?

Precision viticulture (PV) has been mainly applied at the field level, for which the ability of high resolution data to match within-field variability has been already shown. However, the interest of PV for grape growers would be greater if its principles could also apply at a larger scale, as most growers still focus their management on a multi-field scale, not considering each field as an isolated unit. The aim of this study was to analyse whether it is possible and relevant to use PV tools to define meaningful management zones at the whole-vineyard scale. The study was carried out on a 90-ha vineyard made of 27 contiguous fields. The spatial variability of vine vigour, estimated with the Normalized Difference Vegetation Index (NDVI), was analysed at within-field and whole-vineyard scales. The spatial variability of the vigour was significant and spatially organized whatever the considered scale. Besides, vineyard spatial variability was characterised using information on environmental factors (soil apparent conductivity and elevation) and vine response (yield, vigour and grape composition). At both scales, NDVI and measured environmental factors were used to establish a three-level classification, whose agronomic significance was tested comparing the vine response observed for each class. The analysis of high resolution information allowed the definition of classes with agronomic and oenological implications, although there was not a straightforward correspondence between the classes defined and quality. Analysing the variability at the whole-vineyard scale highlighted a trend of spatial variation associated to elevation that was hardly visible at the within-field level.     

Oenological significance of vineyard management zones delineated using early grape sampling

Early definition of oenologically significant zones within a vineyard is one of the main goals of precision viticulture, as it would allow an increase in profitability through the adaptation of agronomic practices to the specific requirements of each zone, and/or segregation of the harvest into different batches to produce wines with different qualities. The aim of this work was to evaluate whether early grape sampling is a relevant tool for within-vineyard zone definition. The study was carried out in 2010 and 2011 in a 4.2 ha vineyard, where a grid of 60 sampling points was defined. 300-berry samples were picked from each sampling point after veraison and at harvest, post-veraison information being used to define zones within the vineyard after fuzzy k-means analysis and subsequent application of a zoning procedure that took into account membership degree and neighbourhood criteria. Two variations of the zoning procedure were used, standard (StdZ) and top (TopZ) zoning. Each was designed to meet different requirements of wineries; StdZ gave the same oenological relevance to all the zones, and TopZ differentiated the zones producing “top class” grapes, minimizing the within-zone variability in the top-class zone. Grape composition obtained at harvest from the zones delineated post-veraison was compared. Zone delineation using post-veraison data was proved to be oenologically relevant, provided sampling is performed once veraison is completed. The two zoning algorithms designed were shown to be suitable for objective zone delineation according to the goals intended for each.     

无核白葡萄在半干旱荒漠地区的生态适应性及栽培管理技术

无核白葡萄对生态环境要求比较严格。地处半干旱荒漠的乌海市根据当地的自然条件，比较系统地研究、总结出一套无核白葡萄栽培技术，使无核白葡萄的种植做到１ 年全苗，２ 年放条，３ 年结果，５ 年丰产。     

Comparison of QuickBird Satellite Imagery and Airborne Imagery for Mapping Grain Sorghum Yield Patterns

Timely and accurate information on crop conditions obtained during the growing season is of vital importance for crop management. High spatial resolution satellite imagery has the potential for mapping crop growth variability and identifying problem areas within fields. The objectives of this study were to use QuickBird satellite imagery for mapping plant growth and yield patterns within grain sorghum fields as compared with airborne multispectral image data. A QuickBird 2.8-m four-band image covering a cropping area in south Texas, USA was acquired in the 2003 growing season. Airborne three-band imagery with submeter resolution was also collected from two grain sorghum fields within the satellite scene. Yield monitor data collected from the two fields were resampled to match the resolutions of the airborne imagery and the satellite imagery. The airborne imagery was related to yield at original submeter, 2.8 and 8.4 m resolutions and the QuickBird imagery was related to yield at 2.8 and 8.4 m resolutions. The extracted QuickBird images for the two fields were then classified into multiple zones using unsupervised classification and mean yields among the zones were compared. Results showed that grain yield was significantly related to both types of image data and that the QuickBird imagery had similar correlations with grain yield as compared with the airborne imagery at the 2.8 and 8.4 m resolutions. Moreover, the unsupervised classification maps effectively differentiated grain production levels among the zones. These results indicate that high spatial resolution satellite imagery can be a useful data source for determining plant growth and yield patterns for within-field crop management.     

Vineyard zone delineation by cluster classification based on annual grape and vine characteristics

This study describes a method for vineyard zone delineation based on spatial interpolation of data on annual monitoring of grape and vine growth from 2007 to 2012 for four commercial vines (Cabernet Sauvignon, Mencía, Merlot and Tempranillo) located in the Bierzo Denomination of Origen (NW Spain). A sampled grid of 20 × 29 m (14 vines/ha) was defined for each vineyard and data were collected for ten soil, six grape composition, three grape production and five vine vigour variables. Continuous maps of each variable were created by spatial interpolation from the sampled points. Several zone delineations were obtained by clustering—using the iterative self-organizing data analysis (ISODATA) algorithm—according to different combinations of the studied variables. The resulting zone delineations were analysed (ANOVA) in order to determine whether the variables in the two cluster classifications for two or three zones were statistically different from each other. The selected delineation was the cluster that included total soluble solids, titratable acidity, total phenolic content, pH, mean cluster weight and length of the internode in two zones. The results point to the feasibility of this approach to vineyard zone delineation. Further research is necessary to confirm the effectiveness of this approach for other locations and evaluate the usefulness of introducing new grape and vine variables.     

A Web-based system for vineyards management, relating inventory data, vectors and images

A Web-based system is presented, integrating spatial information from remote sensing images, GPS measurements and inventory data. Monitoring, research and management of the grape production at Rio Grande do Sul State, Brazil (624,000 metric tons in 2006) can be done through a system entirely based in open-source codes. Information from three different sources are integrated: Information on production comes from the State’s Viticultural Inventory, detailing the regional yearly grape production; positional information comes from field GPS measurements of vine parcels and the system’s capabilities of making maps; imagery information comes from aerial or satellite images. Further capabilities on image classification leads to the identification of vine areas; this allows crossing this data with information provided by owners. This system allows both the monitoring of grape production for administrative purposes and investigations either on regional land and soil cover, or in other applications derived from image classification. The system concept can be readily extended to other applications in land use monitoring.     

Integration of optical and analogue sensors for monitoring canopy health and vigour in precision viticulture

Remote-Sensing (RS) is the most widely used technique for crop monitoring in precision viticulture systems. This paper considers the possibility of substituting RS information obtained by various proximal sensing technologies employed directly in vineyards in order to enable a simultaneous evaluation of canopy health and vigour status. To this aim, a mobile lab has been developed. It consists of (a) two GreenSeeker RT100 sensors, a commercial optical device calculating NDVI, and Red/NIR indices in real time; (b) three pairs of ultrasonic sensors to estimate canopy thickness; and (c) a DGPS receiver to geo-reference data collected while travelling in a vineyard. During the 2007–2008 campaign, tests were carried out in a commercial vineyard in order to evaluate the monitoring system performance regarding disease appearance, diffusion, and vegetative development variations due to the normal growing process of vines. Surveys with the mobile lab were conducted in two groups of rows, treated and untreated with agrochemicals, and compared to manual morphological and physiological observations that characterised the phytosanitary status of the canopy. Measurement repeatability was verified; both NDVI values and ultrasonic data showed high repeatability (with r = 0.88 and r = 0.85, respectively). Optical data were processed in order to obtain NDVI maps, which clearly showed differences in canopy vigour evolution in the two examined groups, with low vegetative vigour in areas infected by Plasmopara viticola, as confirmed by manual assessment. Maps of the percentage infection index (I%I) were produced according to pathological manual survey results. The comparison between I%I and NDVI maps qualitatively confirmed the real vine phytosanitary status. Ultrasonically measured canopy thickness (UCT) was calculated and compared to manually measured canopy thickness (MCT) (r = 0.78). UCT and NDVI values were compared in order to identify areas affected by disease among zones presenting critical vegetation conditions.     

Delineating site-specific management zones for pH-induced iron chlorosis

Iron chlorosis can limit crop yield, especially on calcareous soil. Typical management for iron chlorosis includes the use of iron fertilizers or chlorosis tolerant cultivars. Calcareous and non-calcareous soil can be interspersed within fields. If chlorosis-prone areas within fields can be predicted accurately, site-specific use of iron fertilizers and chlorosis-tolerant cultivars might be more profitable than uniform management. In this study, the use of vegetation indices (VI) derived from aerial imagery, on-the-go measurement of soil pH and apparent soil electrical conductivity (EC_a) were evaluated for their potential to delineate chlorosis management zones. The study was conducted at six sites in 2004 and 2005. There was a significant statistical relationship between grain yield and selected properties at two sites (sites 1 (2005) and 3), moderate relationships at sites 2 and 4, and weak relationships at site 5. For sites 1 (2005) and 3, and generally across all sites, yield was predicted best with the combination of NDVI and deep EC_a. These two properties were used to delineate chlorosis management zones for all sites. Sites 1 and 3 showed a good relationship between delineated zones and the selected properties, and would be good candidates for site-specific chlorosis management. For site 5, differences in the properties between mapped zones were small, and the zones had weak relationships to yield. This site would be a poor candidate for site-specific chlorosis management. Based on this study, the delineation of chlorosis management zones from aerial imagery combined with soil EC_a appears to be a useful tool for the site-specific management of iron chlorosis.     

一种基于多模态图像技术的葡萄水分胁迫识别

提出了一种利用多模态图像技术,以实现被葡萄水分胁迫水平的测定方法,通过检测获取葡萄植株表面图像的反射率和纹理信息与水分胁迫水平之间的关系,从而实现植物缺水报警。试验将盆栽葡萄人为建立不同的水分胁迫水平,利用3CCD照相机(三通道的R,G和IR)、多光谱相机(在900,970 nm的光谱波段覆盖)和一个数字彩色摄像机(RGB)对叶片定期进行监测。试验采用偏最小二乘(PLS)方法预测水含量的纹理特征和光谱特性,在葡萄生长的前期,RGB相机获得的纹理参量对含水量预测结果的rp,RMSEP和偏差值分别为0.77,1.15和-0.14,而利用3CCD相机获取的反射参量对含水量预测结果的rp,RMSEP和偏差值分别为0.77,1.22和-0.26;在葡萄生长后期,RGB相机获取的纹理参量对含水量预测结果的rp,RMSEP和偏差值分别为0.81,1.34和0.26,而利用3CCD相机获取的反射参量对含水量预测结果的rp,RMSEP和偏差值分别为0.74,1.46和0.15。通过监测植株覆盖率与不同水分灌溉植株的生长周期发现,植株覆盖率能对葡萄植株的水分胁迫检测做辅助参考变量。试验结果表明,所设计的多传感器系统可用于支持葡萄水分胁迫检测的决策,有利于葡萄的田间管理。     

Nutrient Management Zones for Citrus Based on Variation in Soil Properties and Tree Performance

Site-specific soil management can improve profitability and environmental protection of citrus groves having large spatial variation in soil and tree characteristics. The objectives of this study were to identify soil factors causing tree performance decline in a variable citrus grove, and to develop soil-specific management zones based on easily measured soil/tree parameters for variable rate applications of appropriate soil amendments. Selected soil properties at six profile depths (0–1.5 m), water table depth, ground conductivity, leaf chlorophyll index, leaf nutrients and normalized difference vegetation index were compared at 50 control points in a highly variable 45-ha citrus grove. Regression analysis indicated that 90% of spatial variation in tree growth, assessed by NDVI, was explained by average soil profile properties of organic matter, color, near-infrared reflectance, soil solution electrical conductivity, ground conductivity and water table depth. Regression results also showed that soil samples at the surface only (0–150 mm) explained 78% of NDVI variability with NIR and DTPA-extractable Fe. Excessive available copper in low soil organic matter areas of the grove apparently induced Fe deficiency, causing chlorotic foliage disorders and stunted tree growth. The semivariograms of selected variables showed a strong spatial dependence with large ranges (varied from 230 m to 255 m). This grove can be divided into different management zones on the basis of easily measured NDVI and/or soil organic matter for variable rate application of dolomite and chelated iron to improve tree performance.     

Spatial variability in grape yield and quality influenced by soil and crop nutrition characteristics

Knowledge of spatial variability of soil fertility and plant nutrition is critical for planning and implementing site-specific vineyard management. To better understand the key drivers behind vineyard variability, yield mapping from 2002 to 2005 and 2007 (the monitor broke down in 2006) was used to identify zones of different productive potential in a Pinot Noir field located in Raimat (Lleida, Spain). Simultaneously, the vineyard field was sampled in 2002, 2003 and 2007, applying three different schemes (depending on the number of target vines in different grape yield zones). The sampling carried out in 2002, which involved different soil, topographic and crop properties (mineral contents in petiole), made it possible to evaluate the influence of these parameters on the grape yield variability. The zones of lowest yield coincided with locations in which the nutritional status of the crop exhibited the lowest values, particularly with respect to petiole contents of calcium and manganese. Sampling systems adopted in 2003 and 2007 (grape quality and soil attributes) confirmed the inverse spatial correlation between grape yield and some grape quality parameters and, more importantly, showed that the percentage of soil carbonates had a great influence on grape quality probably due to the reduced availability of manganese in calcareous soils. Site-specific vineyard management could therefore be considered using two different strategies: variable-rate application of foliar fertilizers to increase the yield in areas with low production and also foliar or soil fertilizers to improve the quality specifications in some areas.     

Variations of soil properties affect the vegetative growth and yield components of “Tempranillo” grapevines

To obtain the best must quality, winegrowers must harvest uniform batches of grapes, thus they might define sub-units of the vineyard and treat them as separate management units for cultivation and harvest. The objectives of this work were to determine if there were variations of soil properties that could be arranged into different units of relative uniformity and separated from each other by discrete boundaries, and if there was a significant relationship between those units and the vegetative development and yield components of the grapevines. A soil index that is a linear combination of four soil characteristics was constructed and an interpolation method allowed the definition of soil areas with relative uniformity. These areas were significantly correlated with the vine growth that, in turn, had a significant correlation with the yield components of the vines. This methodology might prove useful to define areas within vineyards where the vegetative development and yields warrant a differentiated management within the vineyard.