Olive Actual “on Year” Yield Forecast Tool Based on the Tree Canopy Geometry Using UAS Imagery

Abstract

Olive has a notable importance in countries of Mediterranean basin and its profitability depends on several factors such as actual yield, production cost or product price. Actual "on year" Yield (AY) is production (kg tree −1 ) in "on years", and this research attempts to relate it with geometrical parameters of the tree canopy. Regression equation to forecast AY based on manual canopy volume was determined based on data acquired from different orchard categories and cultivars during different harvesting seasons in southern Spain. Orthoimages were acquired with unmanned aerial systems (UAS) imagery calculating individual crown for relating to canopy volume and AY. Yield levels did not vary between orchard categories; however, it did between irrigated orchards (7000-17,000 kg ha −1 ) and rainfed ones (4000-7000 kg ha −1 ). After that, manual canopy volume was related with the individual crown area of trees that were calculated by orthoimages acquired with UAS imagery. Finally, AY was forecasted using both manual canopy volume and individual tree crown area as main factors for olive productivity. AY forecast only by using individual crown area made it possible to get a simple and cheap forecast tool for a wide range of olive orchards. Finally, the acquired information was introduced in a thematic map describing spatial AY variability obtained from orthoimage analysis that may be a powerful tool for farmers, insurance systems, market forecasts or to detect agronomical problems.

Assessment of Olive Tree Canopy Characteristics and Yield Forecast Model Using High Resolution UAV Imagery

“…In contrast to other developed yield forecast models [21,22], our model can be used in hilly olive orchards, which are common in Mediterranean regions (e.g., Greece), because the slope factor is used and related with crown volume and vegetation index (NDVI). Also, the usage of high spatial resolution NDVI vegetation index in such models is pioneering because we would be able to have more accurate yield forecast using indices during cultivation period and therefore to intervene with proper cultivation techniques.…”

“…The product of the above process was a polygonal shapefile, which was further processed. The following Equation (3) was used to estimate the volume of the olive tree canopy, using the field measurements [22]:…”

“…It is evident that our model compared to other already developed yield forecast models has a similar satisfactory performance. Sola-Guirado et al [22] developed a yield forecast tool for rainfed olive trees, with a similar regression adjustment (R 2 = 0.62, p ≤ 0.01). Zhang et al [29] utilized machine learning approaches for almond orchard-level yield prediction, performing R 2 with a range of 0.48 to 0.71, depending on the prediction time and the approach of the machine learning algorithm.…”

“…The developed methodology was capable of local implementation, but it could also reproduce the variation of production at national level. A tool with the same goal was developed by Sola-Guirado et al [22]. Ground measurements of olive trees' canopy were taken in order to calculate the volume and the surface of the crown.…”

Assessment of the Accuracy of a Multi-Beam LED Scanner Sensor for Measuring Olive Canopies

“…On the other hand, electronic methods involve the use of different sensors to obtain, depending on the case, several parameters of the canopy geometry. The information that the sensors provide may be from drones [28], from satellite imagery [29], or from the ground [30]. The main advantages of these systems are their precision and their automatic work but, on the other hand, they usually need specific training in onboard electronics, image analysis or programming to access all their potential).…”