Re-shaping pruning improves the dynamic response of centuries-old olive trees to branch-shaker vibrations application.

Introduction: The Mediterranean basin is home to centuries-old large olive trees; high-vigor cultivars are widespread, with training forms poorly adapted to mechanical harvesting by trunk/branch shakers. The significant quantity of leaves, the considerable tree height, and the presence of multiple dichotomous hanging branches reduce the transmission of vibrations applied by the branch-shaker machines. Thus, re-shaping pruning may improve the performance of this modern mechanical harvesting method by focusing on removing both the hanging branches and those forming dichotomies. The goal of this study was to evaluate the dynamic responses of large-sized olive trees to pruning (or not) through various field tests under different excitation forces. We hypothesized that more rational pruning could significantly increase vibration transmissions. Methods: To assess the transmission of vibrations, tests were conducted before and after the pruning on representative trees. Tri-axial accelerometers packed in a small titanium housing were used. Trees were assessed before and after the re-shaping pruning. This study reports the first data about the dynamic behavior of centuries-old tree skeletons, in the context of very large-sized olive trees, while taking into account the effects of two different vibrations application modes: a realistic one represented by the system vibration head-tree, originated when the gripper of a shaking machine wrapped and fastened the main branch of the olive trees, and a more speculative one, represented by a single impulse of a short-duration force originated by a hammer. Results: After pruning, spectral density increased 10 fold in the tertiary branches of pruned trees (ranging 1.0-10 m s-2) compared to that of not-pruned ones (ranging 0.1-1.0 m s-2) at frequency >50 Hz under vibration excitation. Moreover, vibrational decay times (120-150 ms) and amplitude (>10-1 m s-2) were higher under single-impulse excitation. Discussion: A more rational pruning applied to ancient large-sized olive trees significantly increased the vibration transmission under both impulse and vibratory excitation forces, without affected their typical "look". Moreover, these insights are helpful in turn in achieving maximum fruit-removal efficiency. These insights could be applied to various horticultural conditions which would improve the economic sustainability of monumental olive trees, a key portion of the Mediterranean landscape and cultural heritage.

In-Field Automatic Identification of Pomegranates Using a Farmer Robot.

Ground vehicles equipped with vision-based perception systems can provide a rich source of information for precision agriculture tasks in orchards, including fruit detection and counting, phenotyping, plant growth and health monitoring. This paper presents a semi-supervised deep learning framework for automatic pomegranate detection using a farmer robot equipped with a consumer-grade camera. In contrast to standard deep-learning methods that require time-consuming and labor-intensive image labeling, the proposed system relies on a novel multi-stage transfer learning approach, whereby a pre-trained network is fine-tuned for the target task using images of fruits in controlled conditions, and then it is progressively extended to more complex scenarios towards accurate and efficient segmentation of field images. Results of experimental tests, performed in a commercial pomegranate orchard in southern Italy, are presented using the DeepLabv3+ (Resnet18) architecture, and they are compared with those that were obtained based on conventional manual image annotation. The proposed framework allows for accurate segmentation results, achieving an F1-score of 86.42% and IoU of 97.94%, while relieving the burden of manual labeling.

Exposure of farm workers to electromagnetic radiation from cellular network radio base stations situated on rural agricultural land.

The electromagnetic field (EMF) levels generated by mobile telephone radio base stations (RBS) situated on rural-agricultural lands were assessed in order to evaluate the exposure of farm workers in the surrounding area. The expected EMF at various distances from a mobile telephone RBS was calculated using an ad hoc numerical forecast model. Subsequently, the electric fields around some RBS on agricultural lands were measured, in order to obtain a good approximation of the effective conditions at the investigated sites. The viability of this study was tested according to the Italian Regulations concerning general and occupational public exposure to time-varying EMFs. The calculated E-field values were obtained with the RBS working constantly at full power, but during the in situ measurements the actual power emitted by RBS antennas was lower than the maximum level, and the E-field values actually registered were much lower than the calculated values.