Hyperspectral Reflectance as a Basis to Discriminate Olive Varieties—A Tool for Sustainable Crop Management

Discrimination of 14 olive cultivars using morphological analysis and machine learning algorithms

Traditional morphological analysis is a widely employed tool for the identification and discrimination of olive germplasm by using morphological markers which are monitored by subjective manual measurements that are labor intensive and time-consuming. Alternatively, an automated methodology can quantify the geometrical features of fruits, leaves and endocarps with high accuracy and efficiency in order to define their morphological characteristics. In this study, 24 characteristics for fruits, 16 for leaves and 25 for endocarps were determined and used in an automated way with basic classifiers combined with a meta-classsifier approach. This resulted to the discrimination of 14 olive cultivars utilizing data obtained from two consecutive olive growing periods. The cultivar classification algorithms were based on machine learning techniques. The 95% accuracy rate of the meta-classifier approach indicated that was an efficient tool to discriminate olive cultivars. The contribution of each morphological feature to cultivar discrimination was quantified, and the significance of each one was automatically detected in a quantitative way. The higher the contribution of each feature, the higher the significance for cultivar discrimination. The identification of most cultivars was guided by the features of both endocarps and fruits, while those of leaves were only efficient to identify the Kalamon cultivar. The combined use of morphological features of three olive organs might have an additive effect leading to higher capacity for discrimination of cultivars. The proposed methodology might be considered a phenomics tool for olive cultivar identification and discrimination in a wide range of applications including breeding.

In-field hyperspectral imaging dataset of Manzanilla and Gordal olive varieties throughout the season

Because spectral technology has exhibited benefits in food-related applications, an increasing amount of effort is being dedicated to develop new food-related spectral technologies. In recent years, the use of remote sensing or unmanned aerial vehicles for precision agriculture has increased. As spectral technology continues to improve, portable spectral devices become available in the market, offering the possibility of realising in-field monitoring. This study demonstrates hyperspectral imaging and spectral olive signatures of the Manzanilla and Gordal cultivars analysed throughout the table-olive season from May to September. The data were acquired using an in-field technique and sampled via a non-destructive approach. The olives were monitored periodically during the season using a hyperspectral camera. A white reference was used to normalise the illumination variability in the spectra. The acquired data were saved in files named raw, normalised, and processed data. The normalised data were calculated by the sensor by correcting the white and black levels using the acquired reflectance values. The olive spectral signature of the images is saved in the processed data files. The images were labelled and processed using an algorithm to retrieve the olive spectral signatures. The results were stored as a chart with 204 columns and 'n' rows. Each row represents the pixel of an olive in the image, and the columns contain the reflectance information at that specific band. These data provide information about two olive cultivars during the season, which can be used for various research purposes. Statistical and artificial intelligence approaches correlate spectral signatures with olive characteristics such as growth level, organoleptic properties, or even cultivar classification.

Hyperspectral Imagery Detects Water Deficit and Salinity Effects on Photosynthesis and Antioxidant Enzyme Activity of Three Greek Olive Varieties

The olive tree (Olea europaea L.) is one of the main crops of the Mediterranean region which suffers from drought and soil salinization. We assessed the photosynthetic rate, leaf water content and antioxidative enzyme activity (APX, GPX, SOD and CAT) of three Greek olive cultivars (‘Amfisis’, ‘Mastoidis’ and ‘Lefkolia Serron’) subjected to drought and salinity stresses. Hyperspectral reflectance data were acquired using an analytical spectral device (ASD) FieldSpec® 3 spectroradiometer, while principal component regression, partial least squares regression and linear discriminant analysis were used to estimate the relationship between spectral and physiological measurements. The photosynthetic rate and water content of stressed plants decreased, while enzyme activity had an increasing tendency. ‘Amfisis’ was more resistant to drought and salinity stress than ‘Mastoidis’ and ‘Lefkolia Serron’. The NDVI appeared to have the highest correlation with the photosynthetic rate, followed by the PRI. APX enzyme activity was the most highly correlated with the 1150–1370 nm range, with an additional peak at 1840 nm. CAT enzyme activity resulted in the highest correlation with the visible part of the spectrum with two peaks at 1480 nm and 1950 nm, while GPX enzyme activity appeared to have a strong correlation within all the available spectral ranges except for 670–1180 nm. Finally, SOD activity showed high correlation values within 1190–1850 nm. This is the first time the correlation of hyperspectral imagery with photosynthetic rate and antioxidant enzyme activities was determined, providing the background for high-throughput plant phenotyping through a drone with a hyperspectral camera. This progress would provide the possibility of early stress detection in large olive groves and assist farmers in decision making and optimizing crop management, health and productivity.

High-Resolution UAV Imagery for Field Olive (Olea europaea L.) Phenotyping

Remote sensing techniques based on images acquired from unmanned aerial vehicles (UAVs) could represent an effective tool to speed up the data acquisition process in phenotyping trials and, consequently, to reduce the time and cost of the field work. In this study, we assessed the ability of a UAV equipped with RGB-NIR cameras in highlighting differences in geometrical and spectral canopy characteristics between eight olive cultivars planted at different planting distances in a hedgerow olive orchard. The relationships between measured and estimated canopy height, projected canopy area and canopy volume were linear regardless of the different cultivars and planting distances (RMSE of 0.12 m, 0.44 m2 and 0.68 m3, respectively). A good relationship (R2 = 0.95) was found between the pruning mass material weighted on the ground and its volume estimated by aerial images. NDVI measured in February 2019 was related to fruit yield per tree measured in November 2018, whereas no relationships were observed with the fruit yield measured in November 2019 due to abiotic and biotic stresses that occurred before harvest. These results confirm the reliability of UAV imagery and structure from motion techniques in estimating the olive geometrical canopy characteristics and suggest further potential applications of UAVs in early discrimination of yield efficiency between different cultivars and in estimating the pruning material volume.