Development of a novel precision applicator for spot treatment of granular agrochemical in wild blueberry.

While spot spraying has gained increasing popularity in recent years, spot application of granule agrochemical has seen little development. Despite the potential for the technology, there currently exists no commercially available granular applicators capable of spot application. Therefore, the goal of this study was to design, build, and lab evaluate a precision applicator for spot applying granular agrochemical in wild blueberry. The design incorporated a John Deere RC2000 with a custom control box, recirculation system, and electrically actuated valves. All components were modified to fit a Valmar 1255 Twin-Roller. The system receives inputs from a predeveloped prescription map and can actuate each of the twelve valves separately to provide individual orifice control. Casoron® G4 was used as the testing agrochemical and in cycling the product pneumatically for 1 hour incurred no significant product degradation (p = 0.110). In lab evaluations, the applicator encountered zero errors in reading prescription maps and actuating the correct valves accordingly. Further, the granule recycling system had zero instances where product built up in the lines or jammed the valves. In all, this project represents the first successful development of a precision granular spot applicator for any cropping system.

Enhancing surface drainage mapping in eastern Canada with deep learning applied to LiDAR-derived elevation data.

Agricultural dykelands in Nova Scotia rely heavily on a surface drainage technique called land forming, which is used to alter the topography of fields to improve drainage. The presence of land-formed fields provides useful information to better understand land utilization on these lands vulnerable to rising sea levels. Current field boundaries delineation and classification methods, such as manual digitalization and traditional segmentation techniques, are labour-intensive and often require manual and time-consuming parameter selection. In recent years, deep learning (DL) techniques, including convolutional neural networks and Mask R-CNN, have shown promising results in object recognition, image classification, and segmentation tasks. However, there is a gap in applying these techniques to detecting surface drainage patterns on agricultural fields. This paper develops and tests a Mask R-CNN model for detecting land-formed fields on agricultural dykelands using LiDAR-derived elevation data. Specifically, our approach focuses on identifying groups of pixels as cohesive objects within the imagery, a method that represents a significant advancement over pixel-by-pixel classification techniques. The DL model developed in this study demonstrated a strong overall performance, with a mean Average Precision (mAP) of 0.89 across Intersection over Union (IoU) thresholds from 0.5 to 0.95, indicating its effectiveness in detecting land-formed fields. Results also revealed that 53% of Nova Scotia's dykelands are being used for agricultural purposes and approximately 75% (6924 hectares) of these fields were land-formed. By applying deep learning techniques to LiDAR-derived elevation data, this study offers novel insights into surface drainage mapping, enhancing the capability for precise and efficient agricultural land management in regions vulnerable to environmental changes.

Deep learning supported machine vision system to precisely automate the wild blueberry harvester header.

An operator of a wild blueberry harvester faces the fatigue of manually adjusting the height of the harvester's head, considering spatial variations in plant height, fruit zone, and field topography affecting fruit yield. For stress-free harvesting of wild blueberries, a deep learning-supported machine vision control system has been developed to detect the fruit height and precisely auto-adjust the header picking teeth rake position. The OpenCV AI Kit (OAK-D) was used with YOLOv4-tiny deep learning model with code developed in Python to solve the challenge of matching fruit heights with the harvester's head position. The system accuracy was statistically evaluated with R2 (coefficient of determination) and σ (standard deviation) measured on the difference in distances between the berries picking teeth and average fruit heights, which were 72, 43% and 2.1, 2.3 cm for the auto and manual head adjustment systems, respectively. This innovative system performed well in weed-free areas but requires further work to operate in weedy sections of the fields. Benefits of using this system include automated control of the harvester's head to match the header picking rake height to the level of the fruit height while reducing the operator's stress by creating safer working environments.

Ecological impacts of the N-viro biosolids land-application for wild blueberry (Vaccinium angustifolium. Ait) production in Nova Scotia.

Land application of biosolids from processed sewage sludge may deteriorate soil, water, and plants. We investigated the impact of the N-Viro biosolids land-application on the quality of the soil water that moved through Orthic Humo-Ferric Podzols soil of Nova Scotia (NS) at the Wild Blueberry Research Institute, Debert, NS Canada. In addition, the response of major soilproperties and crop yield was also studied. Wild blueberry (Vaccinium angustifolium. Ait) was grown under irrigated and rainfed conditions in 2008 and 2009. Four experimental treatments including (i) NI: N-Viro irrigated, (ii) NR: N-Viro rainfed, (iii) FI: inorganic fertilizer irrigated, and (iv) FR: inorganic fertilizer rainfed (control) were replicated 4 times under randomized complete block design. Soil samples were collected at the end of each year and analyzed for changes in cation exchange capacity (CEC), soil organic matter (SOM), and pH.Soil water samples were collected four times during the study period from the suction cup lysimeters installed within and below crop root zone at 20 and 40 cm depths, respectively. The samples were analyzed for a range of water quality parameters including conductance, hardness, pH, macro- and micronutrients, and the infectious pathogens Escherichia coli (E. coli) and salmonella. Berries were harvested for fruit yield estimates. Irrigation significantly increased CEC during 2008 and the soil pH decreased from 4.93 (2008) to 4.79 (2009). There were significant influences of irrigation, fertilizer, and their interaction, in some cases, on most of the soil water quality parameters except on the infectious bacteria. No presence of E. coli or salmonella were observed in soil and water samples, reflecting the absence of these bacteria in biosolids used in this experiment. Nutrient concentration in the soil water samples collected from the four treatments were higher in the sequence NI > NR > FI > FR. The irrigation treatment had significant effect on the unripe fruit yield. We conclude that the comparable performance of N-Viro biosolids and the increasing prices of inorganic fertilizers would compel farmers to use economically available N-Viro biosolids that, coupled with the supplemental irrigation, did not deteriorate the studied soil properties, soil water quality, and the wild blueberry yield during this experiment.