Early detection of grapevine viral diseases is critical for early interventions in order to prevent the disease from spreading to the entire vineyard. Hyperspectral remote sensing can potentially detect and quantify viral diseases in a nondestructive manner. This study utilized hyperspectral imagery at the plant level to identify and classify grapevines inoculated with the newly discovered DNA virus grapevine vein-clearing virus (GVCV) at the early asymptomatic stages. An experiment was set up at a test site at South Farm Research Center, Columbia, MO, USA (38.92 N, −92.28 W), with two grapevine groups, namely healthy and GVCV-infected, while other conditions were controlled. Images of each vine were captured by a SPECIM IQ 400–1000 nm hyperspectral sensor (Oulu, Finland). Hyperspectral images were calibrated and preprocessed to retain only grapevine pixels. A statistical approach was employed to discriminate two reflectance spectra patterns between healthy and GVCV vines. Disease-centric vegetation indices (VIs) were established and explored in terms of their importance to the classification power. Pixel-wise (spectral features) classification was performed in parallel with image-wise (joint spatial–spectral features) classification within a framework involving deep learning architectures and traditional machine learning. The results showed that: (1) the discriminative wavelength regions included the 900–940 nm range in the near-infrared (NIR) region in vines 30 days after sowing (DAS) and the entire visual (VIS) region of 400–700 nm in vines 90 DAS; (2) the normalized pheophytization index (NPQI), fluorescence ratio index 1 (FRI1), plant senescence reflectance index (PSRI), anthocyanin index (AntGitelson), and water stress and canopy temperature (WSCT) measures were the most discriminative indices; (3) the support vector machine (SVM) was effective in VI-wise classification with smaller feature spaces, while the RF classifier performed better in pixel-wise and image-wise classification with larger feature spaces; and (4) the automated 3D convolutional neural network (3D-CNN) feature extractor provided promising results over the 2D convolutional neural network (2D-CNN) in learning features from hyperspectral data cubes with a limited number of samples.

Early detection of water stress is critical for precision farming for improving crop productivity and fruit quality. To investigate varying rootstock and irrigation interactions in an open agricultural ecosystem, different irrigation treatments were implemented in a vineyard experimental site either: (i) nonirrigated (NIR); (ii) with full replacement of evapotranspiration (FIR); or (iii) intermediate irrigation (INT, 50% replacement of evapotranspiration). In the summers 2014 and 2015, we collected leaf reflectance factor spectra of the vineyard using field spectroscopy along with grapevine physiological parameters. To comprehensively analyze the field-collected hyperspectral data, various band combinations were used to calculate the normalized difference spectral index (NDSI) along with 26 various indices from the literature. Then, the relationship between the indices and plant physiological parameters were examined and the strongest relationships were determined. We found that newly-identified NDSIs always performed better than the indices from the literature, and stomatal conductance (G_s) was the plant physiological parameter that showed the highest correlation with NDSI(R₆₀₃,R₅₅₈) calculated using leaf reflectance factor spectra (R² = 0.720). Additionally, the best NDSI(R₆₈₅,R₄₁₅) for non-photochemical quenching (NPQ) was determined (R² = 0.681). G_s resulted in being a proxy of water stress. Therefore, the partial least squares regression (PLSR) method was utilized to develop a predictive model for G_s. Our results showed that the PLSR model was inferior to the NDSI in G_s estimation (R² = 0.680). The variable importance in the projection (VIP) was then employed to investigate the most important wavelengths that were most effective in determining G_s. The VIP analysis confirmed that the yellow band improves the prediction ability of hyperspectral reflectance factor data in G_s estimation. The findings of this study demonstrate the potential of hyperspectral spectroscopy data in motoring plant stress response.

Reliable assessment of grapevine productivity is a destructive and time-consuming process. In addition, the mixed effects of grapevine water status and scion-rootstock interactions on grapevine productivity are not always linear. Despite the potential opportunity of applying remote sensing and machine learning techniques to predict plant traits, there are still limitations to previously studied techniques for vine productivity due to the complexity of the system not being adequately modeled. During the 2014 and 2015 growing seasons, hyperspectral reflectance spectra were collected using a handheld spectroradiometer in a vineyard designed to investigate the effects of irrigation level (0%, 50%, and 100%) and rootstocks (1103 Paulsen, 3309 Couderc, SO4 and Chambourcin) on vine productivity. To assess vine productivity, it is necessary to measure factors related to fruit ripeness and not just yield, as an over cropped vine may produce high-yield but poor-quality fruit. Therefore, yield, Total Soluble Solids (TSS), Titratable Acidity (TA) and the ratio TSS/TA (maturation index, IMAD) were measured. A total of 20 vegetation indices were calculated from hyperspectral data and used as input for predictive model calibration. Prediction performance of linear/nonlinear multiple regression methods and Weighted Regularized Extreme Learning Machine (WRELM) were compared with our newly developed WRELM-TanhRe. The developed method is based on two activation functions: hyperbolic tangent (Tanh) and rectified linear unit (ReLU). The results revealed that WRELM and WRELM-TanhRe outperformed the widely used multiple regression methods when model performance was tested with an independent validation dataset. WRELM-TanhRe produced the highest prediction accuracy for all the berry yield and quality parameters (R² of 0.522–0.682 and RMSE of 2–15%), except for TA, which was predicted best with WRELM (R² of 0.545 and RMSE of 6%). The results demonstrate the value of combining hyperspectral remote sensing and machine learning methods for improving of berry yield and quality prediction.

Grafting connects root and shoot systems of distinct individuals, bringing microbial communities of different genotypes together in a single plant. How do root system and shoot system genotypes influence plant microbiota in grafted grapevines? To address this, we utilized clonal replicates of the grapevine ‘Chambourcin’, growing ungrafted and grafted to three different rootstocks in three irrigation treatments. Our objectives were to (1) characterize the microbiota (bacteria and fungi) of below-ground compartments (roots, adjacent soil) and above-ground compartments (leaves, berries), (2) determine how rootstock genotype, irrigation, and their interaction influences grapevine microbiota in different compartments, and (3) investigate abundance of microorganisms implicated in the late-season grapevine disease sour rot (Acetobacterales and Saccharomycetes). We found that plant compartment had the largest influence on microbial diversity. Neither rootstock genotype nor irrigation significantly influenced microbial diversity or composition. However, differential abundance of bacterial and fungal taxa varied as a function of rootstock and irrigation treatment; in particular, Acetobacterales and Saccharomycetes displayed higher relative abundance in berries of grapevines grafted to ‘1103P’ and ‘SO4’ rootstocks and varied across irrigation treatments. This study demonstrates that grapevine compartments retain distinct microbiota and identifies associations between rootstock genotypes, irrigation treatment, and the relative abundance of agriculturally relevant microorganisms in the berries.

Efficient and accurate methods to monitor crop physiological responses help growers better understand crop physiology and improve crop productivity. In recent years, developments in unmanned aerial vehicles (UAV) and sensor technology have enabled image acquisition at very-high spectral, spatial, and temporal resolutions. However, potential applications and limitations of very-high-resolution (VHR) hyperspectral and thermal UAV imaging for characterization of plant diurnal physiology remain largely unknown, due to issues related to shadow and canopy heterogeneity. In this study, we propose a canopy zone-weighting (CZW) method to leverage the potential of VHR (≤9 cm) hyperspectral and thermal UAV imageries in estimating physiological indicators, such as stomatal conductance (G_s) and steady-state fluorescence (F_s). Diurnal flights and concurrent in-situ measurements were conducted during grapevine growing seasons in 2017 and 2018 in a vineyard in Missouri, USA. We used neural net classifier and the Canny edge detection method to extract pure vine canopy from the hyperspectral and thermal images, respectively. Then, the vine canopy was segmented into three canopy zones (sunlit, nadir, and shaded) using K-means clustering based on the canopy shadow fraction and canopy temperature. Common reflectance-based spectral indices, sun-induced chlorophyll fluorescence (SIF), and simplified canopy water stress index (siCWSI) were computed as image retrievals. Using the coefficient of determination (R²) established between the image retrievals from three canopy zones and the in-situ measurements as a weight factor, weighted image retrievals were calculated and their correlation with in-situ measurements was explored. The results showed that the most frequent and the highest correlations were found for G_s and F_s, with CZW-based Photochemical reflectance index (PRI), SIF, and siCWSI (PRI_CZW, SIF_CZW, and siCWSI_CZW), respectively. When all flights combined for the given field campaign date, PRI_CZW, SIF_CZW, and siCWSI_CZW significantly improved the relationship with G_s and F_s. The proposed approach takes full advantage of VHR hyperspectral and thermal UAV imageries, and suggests that the CZW method is simple yet effective in estimating G_s and F_s.