Search

Weed control between plastic covered, raised beds in Florida vegetable crops relies predominantly on herbicides. Broadcast applications of post-emergence herbicides are unnecessary due to the general patchy distribution of weed populations. Development of precision herbicide sprayers to apply herbicides where weeds occur would result in input reductions. The objective of the study was to test a state-of-the-art object detection convolutional neural network, You Only Look Once 3 (YOLOV3), to detect vegetation both indiscriminately (1-class network) and to detect and discriminate three classes of vegetation commonly found within Florida vegetable plasticulture row-middles (3-class network). Vegetation was discriminated into three categories: broadleaves, sedges and grasses. The 3-class network (Fscore = 0.95) outperformed the 1-class network (Fscore = 0.93) in overall vegetation detection. The increase in target variability when combining classes increased and potentially negated benefits from pooling classes into a single target (and increasing the available data per class). The 3-class network Fscores for grasses, sedges and broadleaves were 0.96, 0.96 and 0.93 respectively. Recall was the limiting factor for all classes. With consideration to how much of the plant was identified (broadleaves and grasses), the 3-class network (Fscore = 0.93) outperformed the 1-class network (Fscore = 0.79). The 1-class network struggled to detect grassy weed species (recall = 0.59). Use of YOLOV3 as an object detector for discrimination of vegetation classes is a feasible option for incorporation into precision applicators.

Objective We aimed to determine the rate of Candidatus Liberibacter asiaticus (CLas) DNA disappearance from Huanglongbing (citrus greening disease)-affected citrus trees after bacterial death from heat treatment. Results Using the leaf disc sampling method, we followed CLas qPCR Ct values in leaves of potted ‘Valencia’ orange trees after a heat-treatment that eliminated viable CLas. Although titer declined, CLas remained detectable 5 months after treatment. These results warn caution in interpreting experiments that use CLas titer to assess effects therapeutic treatments on diseased plants. Residual DNA may be detectable for 6 months, but the time to decay depends on pretreatment titer.

BACKGROUND Weed infestations reduce turfgrass aesthetics and uniformity. Postemergence (POST) herbicides are applied uniformly on turfgrass, hence areas without weeds are also sprayed. Deep learning, particularly the architecture of convolutional neural network (CNN), is a state-of-art approach to recognition of images and objects. In this paper, we report deep learning CNN (DL-CNN) models that are remarkably accurate at detection of broadleaf weeds in turfgrasses. RESULTS VGGNet was the best model for detection of various broadleaf weeds growing in dormant bermudagrass [Cynodon dactylon (L.)] and DetectNet was the best model for detection of cutleaf evening-primrose (Oenothera laciniata Hill) in bahiagrass (Paspalum notatum Flugge) when the learning rate policy was exponential decay. These models achieved high F1 scores (>0.99) and overall accuracy (>0.99), with recall values of 1.00 in the testing datasets. CONCLUSION The results of the present research demonstrate the potential for detection of broadleaf weed using DL-CNN models for detection of broadleaf weeds in turfgrass systems. Further research is required to evaluate weed control in field conditions using these models for in situ video input in conjunction with a smart sprayer. © 2019 Society of Chemical Industry.

Precision spraying of herbicides can significantly reduce herbicide use. The detection system is the critical component within smart sprayers that is used to detect target weeds and make spraying decisions. In this work, we report several deep convolutional neural network (DCNN) models that are exceptionally accurate at detecting weeds in bermudagrass [Cynodon dactylon (L.) Pers.]. VGGNet achieved high F1 score values (>0.95) and out-performed GoogLeNet for detection of dollar weed (Hydrocotyle spp.), old world diamond-flower (Hedyotis cormybosa L. Lam.), and Florida pusley (Richardia scabra L.) in actively growing bermudagrass. A single VGGNet model reliably detected these summer annual broadleaf weeds in bermudagrass across different mowing heights and surface conditions. DetectNet was the most successful DCNN architecture for detection of annual bluegrass (Poa annua L.) or Poa annua growing with various broadleaf weeds in dormant bermudagrass. DetectNet exhibited an excellent performance for detection of weeds while growing in dormant bermudagrass, with F1 scores >0.99. Based on the high level of performance, we conclude that DCNN-based weed recognition can be an effective decision system in the machine vision subsystem of a precision herbicide applicator for weed control in bermudagrass turfgrasses.

Building a physical barrier around citrus trees or groves can prevent contact between trees and Asian citrus psyllids, the carrier of the pathogen that causes huanglongbing. This new 4-page article is for growers, scientists, and industries that are interested in this approach to protect citrus from huanglongbing. Written by Timothy A. Ebert, Arnold W. Schumann, Laura Waldo, Daniel Stanton, and Philippe Rolshausen, and published by the UF/IFAS Department of Soil and Water Sciences.

Optimal harvest windows for wild blueberries (Vaccinium angustifolium Ait.) can be as small as a few days to ensure peak ripeness. Confirming this critical timing is one of the most important steps in harvesting wild blueberries. If the harvest window is mistimed it can result in a significant portion of the berries being under or overripe and ultimately unmarketable. In this study, four different convolutional neural networks (YOLOv3, YOLOv3-Tiny, YOLOv3-SPP and YOLOv4) were trained on the Darknet deep learning framework and compared. Each of the networks were trained to recognize green (unripe), red (unripe) and blue (ripe) berries from a series of 6,766 labelled images. These images were cropped from 337 high resolution images taken across four commercial wild blueberry field sites on eight days during July and August of 2018 and 2019. Independent testing yielded the best results with the YOLOv3-SPP network. YOLOv3-SPP achieved AP scores of 88.40% (blue), 78.91% (green), 66.37% (red) for a mAP score of 77.90%. Data from this study in combination with yield data will be integrated into a mobile phone app which will be available for determining harvest timings and estimating yields.

The uniform application (UA) of agrochemicals results in the over-application of harmful chemicals, increases crop input costs, and deteriorates the environment when compared with variable rate application (VA). A smart variable rate sprayer (SVRS) was designed, developed, and tested using deep learning (DL) for VA application of agrochemicals. Real-time testing of the SVRS took place for detecting and spraying and/or skipping lambsquarters weed and early blight infected and healthy potato plants. About 24,000 images were collected from potato fields in Prince Edward Island and New Brunswick under varying sunny, cloudy, and partly cloudy conditions and processed/trained using YOLOv3 and tiny-YOLOv3 models. Due to faster performance, the tiny-YOLOv3 was chosen to deploy in SVRS. A laboratory experiment was designed under factorial arrangements, where the two spraying techniques (UA and VA) and the three weather conditions (cloudy, partly cloudy, and sunny) were the two independent variables with spray volume consumption as a response variable. The experimental treatments had six repetitions in a 2 × 3 factorial design. Results of the two-way ANOVA showed a significant effect of spraying application techniques on volume consumption of spraying liquid (p-value < 0.05). There was no significant effect of weather conditions and interactions between the two independent variables on volume consumption during weeds and simulated diseased plant detection experiments (p-value > 0.05). The SVRS was able to save 42 and 43% spraying liquid during weeds and simulated diseased plant detection experiments, respectively. Water sensitive papers’ analysis showed the applicability of SVRS for VA with >40% savings of spraying liquid by SVRS when compared with UA. Field applications of this technique would reduce the crop input costs and the environmental risks in conditions (weed and disease) like experimental testing.

Visual identification of nutrient deficiencies in foliage is an important diagnostic tool for fine-tuning nutrient management of citrus. This new 2-page article describes a new smartphone app that uses a trained neural network to identify disease and pest symptoms on citrus leaves through your phone's camera. Written by Arnold Schumann, Laura Waldo, Perseveranca Mungofa, and Chris Oswalt, and published by the UF/IFAS Department of Soil and Water Sciences.https://edis.ifas.ufl.edu/ss691

This new 2-page article provides instructions for using the Diagnosis and Recommendation Integrated System, or DRIS, a web tool designed for analyzing leaf nutrient concentrations of Florida citrus. Written by Arnold Schumann and published by the UF/IFAS Department of Soil and Water Sciences.

Goosegrass is a problematic weed species in Florida vegetable plasticulture production. To reduce costs associated with goosegrass control, a post-emergence precision applicator is under development for use atop the planting beds. To facilitate in situ goosegrass detection and spraying, tiny- You Only Look Once 3 (YOLOv3-tiny) was evaluated as a potential detector. Two annotation techniques were evaluated: (1) annotation of the entire plant (EP) and (2) annotation of partial sections of the leaf blade (LB). For goosegrass detection in strawberry, the F-score was 0.75 and 0.85 for the EP and LB derived networks, respectively. For goosegrass detection in tomato, the F-score was 0.56 and 0.65 for the EP and LB derived networks, respectively. The LB derived networks increased recall at the cost of precision, compared to the EP derived networks. The LB annotation method demonstrated superior results within the context of production and precision spraying, ensuring more targets were sprayed with some over-spraying on false targets. The developed network provides online, real-time, and in situ detection capability for weed management field applications such as precision spraying and autonomous scouts.

The information provided in the 2008 2nd edition is still sound for healthy citrus trees under Florida production conditions. Much of the information provided in this document on nutrients, application methods, leaf and soil sampling and irrigation scheduling are also effective for huanglongbing (HLB) affected citrus trees. However, research conducted since HLB was detected in Florida in 2005 has established changes in many production practices, including nutrient rates, irrigation scheduling, soil pH management, and use of Citrus Under Protective Screen (CUPS). Changes to the 2nd edition of SL253 will appear in boxes similar to this one at the beginnings of chapters 2, 6, 8, 9, and 11.

The information provided in the 2008 2nd edition is still sound for healthy citrus trees under Florida production conditions. Much of the information provided in this document on nutrients, application methods, leaf and soil sampling and irrigation scheduling are also effective for huanglongbing (HLB) affected citrus trees. However, research conducted since HLB was detected in Florida in 2005 has established changes in many production practices, including nutrient rates, irrigation scheduling, soil pH management, and use of Citrus Under Protective Screen (CUPS). Changes to the 2nd edition of SL253 will appear in boxes similar to this one at the beginnings of chapters 2, 6, 8, 9, and 11.

To achieve optimal grove nutrition, citrus growers must test grove soil before beginning any fertilization program. Standard procedures for sampling, preparing, and analyzing soil should be followed for meaningful interpretations of the test results and accurate recommendations. This new two-page fact sheet, published by the UF/IFAS Department of Soil and Water Sciences, provides illustrated soil sampling procedures and tables to aid in basic interpretation of lab results. Written by Davie Kadyampakeni, Kelly Morgan, Arnold Schumann, and Rhuanito S. Ferrarezi.https://edis.ifas.ufl.edu/ss667

Preemergence herbicides are typically applied by broadcasting to the top of raised beds before laying the plastic mulch in plasticulture production systems. Broadleaf and grass emergence is limited to transplant holes in the mulch. As a result, most herbicides are applied under the mulch in locations where weeds cannot emerge and herbicides are unnecessary. To reduce this excessive off-target application, a precision hole-punch sprayer was developed at the University of Florida for use in plasticulture production systems. The technology facilitates the application of herbicides during the hole-punch operation immediately before transplant. Application of napropamide and S-metolachlor in an application volume of 233 L ha–1 of water using the precision hole-punch applicator had no effect on tomato and bell pepper growth and yield. Equipment accuracy ranged from 55% to 90%. Preemergence herbicide use was reduced by 88% to 92% with no reduction in weed control. The hole-punch applicator is an effective way to reduce PRE herbicide use in transplant vegetables grown using the plasticulture production system.Nomenclature: Napropamide; S-metolachlor; bell pepper, Capsicum annuum L.; tomato, Solanum lycopersicum L.

Weed interference during crop establishment is a serious concern for Florida strawberry [Fragaria×ananassa(Weston) Duchesne ex Rozier (pro sp.) [chiloensis×virginiana]] producers. In situ remote detection for precision herbicide application reduces both the risk of crop injury and herbicide inputs. Carolina geranium (Geranium carolinianumL.) is a widespread broadleaf weed within Florida strawberry production with sensitivity to clopyralid, the only available POST broadleaf herbicide.Geranium carolinianumleaf structure is distinct from that of the strawberry plant, which makes it an ideal candidate for pattern recognition in digital images via convolutional neural networks (CNNs). The study objective was to assess the precision of three CNNs in detectingG. carolinianum. Images ofG. carolinianumgrowing in competition with strawberry were gathered at four sites in Hillsborough County, FL. Three CNNs were compared, including object detection–based DetectNet, image classification–based VGGNet, and GoogLeNet. Two DetectNet networks were trained to detect either leaves or canopies ofG. carolinianum. Image classification using GoogLeNet and VGGNet was largely unsuccessful during validation with whole images (FscoreG. carolinianumdetection during validation for VGGNet (Fscore=0.77) and GoogLeNet (Fscore=0.62). TheG. carolinianumleaf–trained DetectNet achieved the highestFscore(0.94) for plant detection during validation. Leaf-based detection led to more consistent detection ofG. carolinianumwithin the strawberry canopy and reduced recall-related errors encountered in canopy-based training. The smaller target of leaf-based DetectNet did increase false positives, but such errors can be overcome with additional training images for network desensitization training. DetectNet was the most viable CNN tested for image-based remote sensing ofG. carolinianumin competition with strawberry. Future research will identify the optimal approach for in situ detection and integrate the detection technology with a precision sprayer.

Models help to describe and predict complex processes and scenarios that are difficult to understand or measure in environmental management systems. Thus, model simulations were performed (i) to calibrate HYDRUS-2D for water and solute movement as a possible decision support system for Candler and Immokalee fine sand using data from microsprinkler and drip irrigation methods, (ii) to validate the performance of HYDRUS-2D using field data of microsprinkler and drip irrigation methods, and (iii) to investigate Br, NO, and water movement using annual or seasonal weather data and variable fertigation scenarios. The model showed reasonably good agreement between measured and simulated values for soil water content ( = 0.87-1.00), Br ( = 0.63-0.96), NO-N ( = 0.66-0.98), P ( = 0.25-0.78), and K ( = 0.44-0.99) movement. The model could be successfully used for scheduling irrigation and predicting nutrient leaching for both microsprinkler and drip irrigation systems on Florida's sandy soils.

Objective This study was carried out with the purpose of testing the ability of deep learning machine vision to identify microscopic objects and geometries found in chemical crystal structures. Results A database of 6994 images taken with a light microscope showing microscopic crystal details of selected chemical compounds along with 180 images of an unknown chemical was created to train and test, respectively the deep learning models. The models used were GoogLeNet (22 layers deep network) and VGG-16 (16 layers deep network), based on the Caffe framework (University of California, Berkeley, CA) of the DIGITS platform (NVIDIA Corporation, Santa Clara, CA). The two models were successfully trained with the images, having validation accuracy values of 97.38% and 99.65% respectively. Finally, both models were able to correctly identify the unknown chemical sample with a high probability score of 93.34% (GoogLeNet) and 99.41% (VGG-16). The positive results found in this study can be further applied to other unknown sample identification tasks using light microscopy coupled with deep learning machine vision.

Wild blueberry crop yields are dependent on heavy agrochemical applications to control weeds competing with the crop. Goldenrod is a creeping herbaceous perennial weed that occurred in 90% of wild blueberry fields surveyed in Nova Scotia. A colour co-occurrence matrices (CCMs) based algorithm can be used for spot-application of herbicide on goldenrod within wild blueberry fields. The objective of this study was to analyse the effect of different parameters on computational complexity and goldenrod identification accuracy of CCMs in wild blueberry cropping system. An image acquisition graphical user interface (GUI) and CCMs based textural analysis algorithm were developed in Microsoft Visual® C# programming language. The GUI was used to acquire 2244 area of interest images along with a set of 2244 full frame images from two different wild blueberry fields in central Nova Scotia, Canada. Six image intensity levels, seven image sizes, and three CCMs were used to for the study. The results indicated that intensity levels and image size significantly influenced the computational requirements of CCMs. Images with 256 or 128 intensity levels could be used as these levels correctly classified 94% and 89% of test observations respectively. The processing times were increased from 535 μs to 10,650 μs and 9864 μs to 63,750 μs as the intensity increased from 8 to 256 levels and image size increased from 16 × 16 to 1024 × 1024 pixels, respectively. The time required for textural feature extraction was not statistically significant for different image sizes used in this study. Overall, the results indicated that intensity levels of 128 or 256, a unit image size of 128 × 128 pixels, and saturation colour plane alone or in combination with hue can help to minimise the processing burden without compromising the classification accuracy for real-time applications.

An essential part of the wild blueberry cropping system is the proper management of agrochemical inputs including herbicides, fungicides and insecticides. A machine vision system was developed and mounted on the rear sprayer boom 0.18 m in front of the sprayer nozzles capable of targeting the agrochemical application on an as-needed basis. The three-point hitch mounted sprayer featured 27 nozzles over a 13.7 m boom width and a storage tank capacity of 1135 l. Nine digital color cameras continually take images in real-time while computer software processes the images in 0.15 s to determine the target locations where the nozzles open and spray at speeds up to 1.77 m s−1. Two wild blueberry fields in central Nova Scotia were selected for smart sprayer performance testing with spot-application (SA) of agrochemical as compared to control and uniform application techniques. Chateau® herbicide was applied in a field with an infestation of hair cap moss. Spray droplet comparison showed moss patches were properly targeted using the smart sprayer. SA provided the same coverage performance as compared to uniform on the moss targets with herbicide application savings of 78.5% using the smart sprayer. Harvestable yield results were similar for all application tracks. TruPhos Magnesium and ZincMax foliar fertilizers were tank mixed with Bravo® and Proline® fungicides and applied to compare the difference of SA, control and uniform application. Results showed SA of foliar fertilizer and fungicide led to less premature leaf drop and increased the blueberry stem height, number of branches, stem diameter and fruit buds. SA of foliar fertilizer and fungicide also increased the percent of healthy wild blueberry plants by 57.8% and the harvestable yield by 137.8%. Fungicide application savings using the smart sprayer for SA were 11.6%.

Northeastern North America is the world’s leading producer of wild blueberry. Ripening of wild blueberry is the leading factor for fruit quality. Currently, there are no protocols available for the farming community related to wild blueberry fruit ripening and maturity. A nondestructive, rapid, and reliable digital photography technique could be used to examine the ripening of wild blueberries for appropriate harvesting time. Two wild blueberry fields were selected to examine the berry ripening levels using digital photographic techniques at different time of harvest (early, middle, and late seasons). The fields were divided into four blocks and each block was further divided into three classes of times of harvest. Fruit images from each block were acquired and processed to count blue pixels from each image. A significant correlation was found between percentage of blue pixels and actual fruit yield in Field A (R2 = 0.96; P < 0.001) and Field B (R2 = 0.97; P < 0.001). The results also indicated that the effect of time of harvest on fruit yield was significant and fruit yield increased gradually during early harvesting, reached maximum during mid-season, and then started to decrease in late harvesting. Results indicated that 90% of green-berries had turned blue at the end of middle season compared to early season (58%). Based on the results of this study, optical analysis could help to keep fruit quality by optimizing appropriate harvesting time of wild blueberries. It is also suggested that the optimum time to harvest wild blueberries is middle season to ensure high fruit yield and quality. Keywords: Blue pixels, Fruit yield, Harvesting season, Wild blueberry.

Completely enclosed screen houses can physically exclude contact between the asian citrus psyllid [ACP (Diaphorina citri)] and young, healthy citrus (Citrus sp.) trees and prevent huanglongbing (HLB) disease development. The current study investigated the use of antipsyllid screen houses on plant growth and physiological parameters of young ‘Ray Ruby’ grapefruit (Citrus ×paradisi) trees. We tested two coverings [enclosed screen house and open-air (control)] and two planting systems (in-ground and container-grown), with four replications arranged in a split-plot experimental design. Trees grown inside screen houses developed larger canopy surface area, canopy surface area water use efficiency (CWUE), leaf area index (LAI) and LAI water use efficiency (LAIWUE) relative to trees grown in open-air plots (P < 0.01). Leaf water transpiration increased and leaf vapor pressure deficit (VPD) decreased in trees grown inside screen houses compared with trees grown in the open-air plots. CWUE was negatively related to leaf VPD (P < 0.01). Monthly leaf nitrogen concentration was consistently greater in container-grown trees in the open-air compared with trees grown in-ground and inside the screen houses. However, trees grown in-ground and inside the screen houses did not experience any severe leaf N deficiencies and were the largest trees, presenting the highest canopy surface area and LAI at the end of the study. The screen houses described here provided a better growing environment for in-ground grapefruit because the protective structures accelerated young tree growth compared with open-air plantings while protecting trees from HLB infection.

High wind constraints during day time agrochemical spraying has pushed the wild blueberry producers to apply agrochemicals during the early morning, evening or after dark, to avoid drift problems due to low wind conditions. The objective of this study was to develop an artificial light source system combined with a smart sprayer comprising of a digital camera-based sensing system to allow cameras to detect target areas (weed, plant or bare soil) in real-time for accurate application of agrochemicals in low light conditions. After testing and evaluation of different light sources, a rugged light source system equipped with polystyrene diffuser sheets was constructed to provide an even distribution of light across the entire 12.2 m machine vision sensor boom. Distribution of artificial light underneath the sensing boom at zero ambient light was examined by recording the light intensity at 0.15 m spacing on the ground under the camera boom using a lux meter. Results of light distribution revealed that the Magnafire ® 70 W high intensity discharge (HID) lights provided wide angle of even light illumination, high intensity and rugged construction. A wild blueberry field was selected in central Nova Scotia, Canada, and a test track was made to evaluate the performance of the artificial light source system to apply agrochemicals on a spot-specific basis under low natural light conditions. A real-time kinematics-global positioning system (RTK-GPS) was used to map the boundary of the test track, selected bare soil areas, weed areas and wild blueberry plant areas in the field. Water sensitive papers (WSPs) were placed at randomly selected locations, the smart sprayer was operated under low light conditions, and the percent area coverage (PAC) was calculated. The mean PAC from WSP located in bare soil, weeds and blueberry spots in the track was 5.19%, 27.53%, and 1.74%, respectively. PAC of the WSPs placed in bare soil and blueberry patches were 22.34% and 25.79% lower than in weed patches, respectively. Results reported that the custom developed artificial light source system was accurate enough to detect targets in low light conditions. Additionally, spot-spacing only in weed areas resulted in 65% of chemical saving.

Spatial variability in fruit losses in relation to fruit yield, plant height, and ground slope can help to automate the wild blueberry harvester to improve picking performance. Currently, harvester operators adjust harvester’s head height, ground speed, and revolutions per minute (rpm) manually. This is not only laborious but also stressful for operators, as they encounter spatial variability during harvesting. The goal of this work was to identify the automation potential of the harvester to improve harvestable yield and reduce operator’s stress, keeping in view the spatial variability. Two fields were selected and test plots were constructed to examine the performance of the harvester in five zones of plant height, fruit yield, and ground slope. Fruit yield plant height and ground slope were recorded from each plot manually to examine their impact on total fruit loss. Keywords: Automation, Fruit losses, Spatial variability, Wild blueberry, Zonal analysis.Results confirmed significant variability in fruit yield, plant height, and ground slope. Fruit losses were significantly influenced by the spatial variations. Fruit losses increased with an increase in fruit yield and ground slope during mechanical harvesting. The picking performance of the blueberry harvester was significantly lower in short and very tall plants within selected fields. The dependence of fruit losses on fruit yield, plant height, and ground slope emphasize the need for real-time adjustments in machine operating parameters to improve berry recovery. Based on the results, it is concluded that there is a significant advantage of harvester’s automation to increase profit margins for growers with no additional cost. Keywords: Automation, Fruit losses, Spatial variability, Wild blueberry, Zonal analysis.

The goal of the project was to supply growers with knowledge on how incorporation of machine vision technology can affect the wild blueberry crop, disease pressures, and the overall savings of select agrochemical inputs. A machine vision system was developed and mounted on a rear sprayer boom in front of the sprayer nozzles capable of targeting the agrochemical application on an as-needed basis. Results showed that plants that received the proper fungicide application were less prone to premature leaf drop resulting in larger stem diameters and higher bud counts and harvestable fruit yield. Fungicide application savings using the smart sprayer for spot-application was 12% as compared to a uniform application.

Precision herbicide application can substantially reduce herbicide input and weed control cost in turfgrass management systems. Intelligent spot-spraying system predominantly relies on machine vision-based detectors for autonomous weed control. In this work, several deep convolutional neural networks (DCNN) were constructed for detection of dandelion (Taraxacum officinale Web.), ground ivy (Glechoma hederacea L.), and spotted spurge (Euphorbia maculata L.) growing in perennial ryegrass. When the networks were trained using a dataset containing a total of 15,486 negative (images contained perennial ryegrass with no target weeds) and 17,600 positive images (images contained target weeds), VGGNet achieved high F1 scores (≥0.9278), with high recall values (≥0.9952) for detection of E. maculata, G. hederacea, and T. officinale growing in perennial ryegrass. The F1 scores of AlexNet ranged from 0.8437 to 0.9418 and were generally lower than VGGNet at detecting E. maculata, G. hederacea, and T. officinale. GoogleNet is not an effective DCNN at detecting these weed species mainly due to the low precision values. DetectNet is an effective DCNN and achieved high F1 scores (≥0.9843) in the testing datasets for detection of T. officinale growing in perennial ryegrass. Moreover, VGGNet had the highest Matthews correlation coefficient (MCC) values, while GoogleNet had the lowest MCC values. Overall, the approach of training DCNN, particularly VGGNet and DetectNet, presents a clear path toward developing a machine vision-based decision system in smart sprayers for precision weed control in perennial ryegrass.

Wild blueberry (Vaccinium angustifolium Ait.) fields are almost exclusively picked by mechanical harvesting machines which collect all available berries from the bushes in a single operation during late summer. The resulting stream of harvested fruit may contain a significant fraction of unmarketable unripe green and red berries in addition to the marketable fully ripe blue berries. In this study, we evaluated the performance of machine vision to detect wild blueberry fruit maturity on the bushes before harvesting. Fruit maturity data from unharvested blueberry fields could be used in decision-support tools for optimizing the harvest date as part of an integrated research program for improving wild blueberry harvester efficiency. Four versions of the Yolo (You only look once) family of convolutional neural networks on the Darknet deep learning framework were trained to recognize three classes of fruit maturity (unripe green, unripe red, and ripe blue) on a deep learning server equipped with a graphics processing card. The training dataset of 4,220 color images were cropped from 211 high-resolution digital camera images collected in a commercial wild blueberry field at four dates up to the time of harvest in summer 2018. The images contained overhead views of blueberry bushes with berries, which were labeled according to the three stages of maturity. A second wild blueberry field was used for independent validation of the results at four additional dates. The YoloV3-spp network performed best with 91% recall, and 28.3 s inference time, and could successfully identify the three maturity stages of blueberries in the second field.

Harvesting is one for the most important operations for farmers and special care to ensure maximum yield recovery and quality is vital for sustainability of the industry. Prior research has been done to improve berry picking efficiency but work to quantify and optimize the debris cleaning brush has been left untouched. The cylindrical debris cleaning brush is positioned on top of the berry harvesting picking reel and continuously rotates to propel debris from the picker teeth. The brush‘s filamentary bristles (0.24 cm in diameter) are visually adjusted 0.32 cm into the picker teeth prior to harvest. The annealed nylon bristles wear over time and require constant operator adjustment to maintain proper picking performance. To bench mark debris cleaning brush adjustment parameters a survey was distributed to commercial harvester operators and the results were analyzed suggesting 69.2% were operating outside of the manufacturers recommended adjustment range. Misadjusted brushes have the potential to cause increased debris in the harvested fruit and may lead to reduced berry quality. The bristle tip speed was analyzed in relation to common tractor engine speeds (1,200, 1,400 and 1,600 rpm) with results ranging from 6.58 to 13.88 m s-1. Airflow generated in the debris deflection shroud using each brush was analyzed and compared with terminal velocities findings from Esau et al. (2018) with results suggesting only brush 1 is capable of wind velocities high enough to successfully propel the debris away from the picker teeth with bristle tip speeds ranging from 9.15 to 13.88 m s-1.

Deep learning convolutional neural networks (CNNs) are an emerging technology that provide an opportunity to increase agricultural efficiency through remote sensing and automatic inferencing of field conditions. This paper examined the novel use of CNNs to identify two weeds, hair fescue and sheep sorrel, in images of wild blueberry fields. Commercial herbicide sprayers provide a uniform application of agrochemicals to manage patches of these weeds. Three object-detection and three image-classification CNNs were trained to identify hair fescue and sheep sorrel using images from 58 wild blueberry fields. The CNNs were trained using 1280x720 images and were tested at four different internal resolutions. The CNNs were retrained with progressively smaller training datasets ranging from 3780 to 472 images to determine the effect of dataset size on accuracy. YOLOv3-Tiny was the best object-detection CNN, detecting at least one target weed per image with F1-scores of 0.97 for hair fescue and 0.90 for sheep sorrel at 1280 × 736 resolution. Darknet Reference was the most accurate image-classification CNN, classifying images containing hair fescue and sheep sorrel with F1-scores of 0.96 and 0.95, respectively at 1280 × 736. MobileNetV2 achieved comparable results at the lowest resolution, 864 × 480, with F1-scores of 0.95 for both weeds. Training dataset size had minimal effect on accuracy for all CNNs except Darknet Reference. This technology can be used in a smart sprayer to control target specific spray applications, reducing herbicide use. Future work will involve testing the CNNs for use on a smart sprayer and the development of an application to provide growers with field-specific information. Using CNNs to improve agricultural efficiency will create major cost-savings for wild blueberry producers.

Excessive use of herbicides for weed control increases the cost of crop production and can lead to environmental degradation. An intelligent spraying system can apply agrochemicals on an as-needed basis by detecting and selectively targeting the weeds. The objective of this research was to investigate the feasibility of using deep convolutional neural networks (DCNNs) for detecting lamb’s quarters (Chenopodium album) in potato fields. Five potato fields were selected in Prince Edward Island (PEI) and New Brunswick (NB), Canada to collect images of spatially and temporally varied potato plants and lamb’s quarters. The image database included pictures, taken under varying growth stages of potato, outdoor light (clear, cloudy, and partly cloudy), and shadowy conditions. The images were trained for DCNN models, namely GoogLeNet, VGG-16, and EfficientNet to classify lamb’s quarters and potato plants. Performance of two frameworks, namely TensorFlow and PyTorch, were compared in training, testing, and during inferring the DCNNs. Results showed excellent performance of DCNNs in lamb’s quarters and potato plant classification (accuracy > 90%). However, the EfficientNet with PyTorch framework showed a maximum accuracy of (0.92–0.97) for every growth stage of the plants. Inference times of DCNNs were recorded using three graphics processing units (GPUs), namely Nvidia GeForce 930MX, Nvidia GeForce GTX1080 Ti, and Nvidia GeForce GTX1050. All the DCNNs performed better with PyTorch than TensorFlow frameworks. It was concluded that the trained models can be used in automation of the spraying systems for the site-specific application of agrochemicals for weed control in potato fields. Such precision agriculture technologies will ensure economically viable and environmentally safe potato cultivation.

Traditionally, wild blueberry growers apply fertilizer uniformly without considering the substantial variation in soil characteristics, topographic features, and berry yield. Occurrence of heavy rainfall events, gentle to severe topography along with high proportion of bare spots and weed patches emphasize the need for variable rate split (VRS) fertilization. The VRS fertilization has a potential to improve fertilizer use efficiency and reduce environmental impacts. Two commercial wild blueberry fields were selected in central Nova Scotia. Fields were divided into three sections [VRS section, uniform rate split (URS) section, and uniform rate (UR) section]. Fertilization was performed by following the global positioning system (GPS) guided prescription map. Soil samples and plant growth parameters were collected during the vegetative year and berry yield samples were collected during the crop year. The experimental design used for this study was split-plot design and the analysis of all collected data were performed using SAS (SAS, 2010) at 5% level of significance. Plant density and plant height were non-significantly different under all slope zones of VRS, URS, and UR treatment sections. Plants in URS and UR sections were taller than VRS sections in low lying areas. Although there were non-significant differences for berry yield in all slope zones of VRS, URS, and UR fertilizer treatments, the mean berry yield was higher in VRS section as compared to the other sections. Significant correlations were observed between soil properties and plant growth parameters under all treatment sections. The VRS fertilization saved 39% and 42% fertilizer in Cooper (field-1) and North River (field-2) fields, respectively. Based on the results of this study, it can be concluded that the VRS fertilization in wild blueberry fields could reduce fertilizer usage without affecting the crop productivity.

Wild blueberry is one of the most important fruit crops of Canada that produces more than 50% of the world‘s blueberries. Understanding and predicting the relationships between the machine operating parameters, fruit losses, topographic features, and crop characteristics can aid in better berry recovery during mechanical harvesting. This article suggested a modeling approach for prediction of fruit losses during harvesting using artificial neural network (ANN) and multiple regression (MR) techniques. Four wild blueberry sites were selected and completely randomized factorial (3 x 3) experiments were conducted at each site. One hundred sixty-two plots (0.91 x 3 m) were made at each site, in the path of operating harvester. Total fruit yield and losses were collected from each plot within selected sites. The harvester was operated at specific levels of ground speed (1.20, 1.60, and 2.00 km h-1) and head rotational speed (26, 28, and 30 rpm). The slope, plant height, and fruit zone were also recorded from each plot. The collected data were normalized, and 70% of the data were utilized for calibration, and 30% for validation of developed models using ANN and MR techniques. Results of root mean square error (RMSE) suggested that the tanh-sigmoid transfer function between the hidden layer and output layer was the best fit for this study. The developed models were validated internally and externally and the best performing configurations were identified based on RMSE, coefficient of efficiency, percent variation, and coefficient of determination. Results of scatter plot among the RMSE and epoch suggested that an epoch size (iterative steps) of 15,000 was appropriate to predict fruit losses using ANN approach. Results revealed that the prediction accuracy of MR model was lower (R2 = 0.46; RMSE = 0.14%) than the ANN model (R2 = 0.84; RMSE = 0.075%) for calibration dataset. Results reported that the ANN model predicted fruit losses with higher (R2 = 0.63; RMSE = 0.11%) accuracy when compared with MR model (R2 = 0.37; RMSE = 0.15%) for external validation dataset. Overall, results of this study suggested that the ANN model was able to accurately and reliably predict fruit losses during harvesting. These results can help to identify the factors responsible for fruit losses and to suggest optimal harvesting scenarios to improve harvesting efficiency.

Wild blueberry is a high value cash crop in northeastern North America. In the last two decades, improved management practices have changed crop characteristics. Currently, the wild blueberry industry is facing increased harvesting losses (15%-25%) due to changes in crop conditions. This study was designed to examine the effect of plant characteristics on picking efficiency of the wild blueberry harvester. Four wild blueberry fields were selected in Nova Scotia and New Brunswick, Atlantic Provinces of Canada. Plant height (PH) and plant density (PD) were classified into four different categories, i.e., tall plant - low plant density, tall plant - high plant density, short plant - low plant density, and short plant - high plant density, and stem thickness (ST) was used as a covariate. Nine yield plots (0.9 x 3 m) for each combination of PH and PD were selected randomly at each experimental field. The PH, PD, and ST were recorded manually from each selected plot. Factorial experiments with four replications were designed to identify the combined effect of ground speed (1.2, 1.6, and 2.0 km h-1) and header revolutions (26, 28, and 30 rpm) on berry losses at each category of PH and PD. Berry losses were collected from each plot within the selected fields. Factorial analysis of covariance (ANCOVA) using general linear model (GLM) procedure showed that the interaction of ground speed and header rpm was significant (p = 0.05) in each category of plant characteristics. Results of multiple means comparison showed that the lower ground speed and header rpm resulted in significantly lower losses when compared with higher ground speed and header rpm. The study findings also suggested a suitable combination of ground speed and header rpm for each class of plant characteristics to minimize the berry losses during harvesting.

Knowledge of spatial variability in fruit yield, crop characteristics, fruit loss, and slope of the field is critical for planning and implementing the operational recommendation for mechanical harvesting. Improved management practices have caused significant changes in crop conditions, which reduce the picking performance of the harvester as the harvester was designed in early 1980s. The goal of this work was to characterize and quantify the spatial pattern of variability in crop characteristics, fruit yield, and slope the field in relation to fruit loss during mechanical harvesting. Completely randomized experiments were designed and plots (0.91 x 3 m) were constructed in selected fields. Total fruit loss (pre- and post-harvest) and fruit yield were collected from each plot within selected fields. Slope, plant height, and fruit zone were also recorded from each plot to examine the impact of their spatial variability on fruit loss. The coefficient of variations (CVs) for fruit yield, berry loss, slope, plant height, and fruit zone suggested moderate to high variability (CV>15%) within selected fields. Correlation analysis showed higher fruit loss in high yielding areas and vice versa. Fruit yield, berry loss, slope, plant height, and fruit zone had large spatial variation (range of influence ~20 to 50 m) within selected fields. Kriged maps revealed substantial variation in these parameters. Variability in fruit loss corresponding with the spatial variations in crop characteristics, fruit yield, and slope suggested that the fruit loss during mechanical harvesting were influenced by the spatial variations in these parameters. Adjustments in operational settings (ground speed, head revolutions, head height, etc.) of the harvester in accordance with the spatial variations have the potential to increase profit margins for blueberry industry.

Understanding the relationships between soil properties, topographic features, and their impact on fruit yield is an important component of site-specific nutrient management. This article presents research that investigates the relationship between soil properties and fruit yield to provide a better understanding of their variation with respect to change in slope within selected wild blueberry fields. Two wild blueberry fields were selected and completely randomized experiments were constructed at each site. The selected sites were divided into five slope categories: 0 16° (Category 5). Soil samples were collected from each slope category and analyzed for pH, texture, electrical conductivity (EC), soil organic matter (SOM), and inorganic nitrogen (NH4+-N, NO3--N). The slope, volumetric moisture content (?v), and fruit yield data were also collected from each slope category. Soil variables, slope and fruit yield data were replicated ten times in each slope category.

An automated sensing and control system (hardware and software) was developed for real-time spot-application of granular fertilizer in mowed wild blueberry fields. The custom hardware system was incorporated into a commercial pneumatic granular fertilizer spreader. Custom software for the sensing and control system was developed by combining color co-occurrence matrix based texture analysis and g-ratio algorithms in C++ to acquire and process images in real-time to differentiate mowed wild blueberry plants from bare spots and weeds. The performance accuracy of the spot-applicable fertilizer spreader was evaluated both in laboratory simulation and real-time field tests. Simulation results reported that the accuracy of the developed system was 94.9 %. Real-time field tests reported that the system produced acceptable results at ground speeds of 1.6 and 3.2 km h−1 for the spot-application of fertilizer at target areas (in plant areas only) within the field. Results also indicated that the ground speed of 4.8 km h−1 was unacceptable, which could be due to blurred images at high speed and surface unevenness of the wild blueberry field. Spot-application of fertilizer using the modified fertilizer spreader could save fertilizer for the wild blueberry producers.

Most of the agricultural fields are generally irrigated or drained uniformly without considering the spatial and temporal variation in water table depth (WTD). Investigating WTD is important for scheduling irrigation, drainage system designs and water balance models. The objective of this study was to develop a software interface to estimate the variations in WTD via electromagnetic induction (EMI) methods using frequencies of a DUALEM-2 system. Two fields (Field 1: 45.38°N, 63.23°W and Field 2: 45.37°N, 63.25°W) were selected and thirty perforated observation wells were installed to calibrate the DUALEM-2 for predicting WTD. Boundaries of the selected sites and location of the wells were marked using a real time kinematics global positioning system (RTK-GPS). The user interface program was developed in Delphi 5.0 software and imported in a laptop computer to retrieve data from the DUALEM-2 system. The horizontal co-planar (HCP) geometry, perpendicular co-planar (PRP) geometry and WTD were recorded simultaneously from each well before and after every significant rainfall for three consecutive days. Comprehensive surveys were conducted to measure apparent ground conductivity (ECa) with DUALEM-2 and corresponding locations of the sampling points using Trimble Ag GPS 332. The regression model showed significant correlation between the HCP and WTD with co-efficient of determination (R2 = 0.71) for field 1 and (R2 = 0.53) for field 2. Maps were generated in ArcGIS 10 software to examine the accuracy of predicted WTD in comparison with actual values. Results indicated that the DUALEM-2 system was efficient in mapping variation rapidly and reliably in WTD in a non-destructive fashion rather than following conventional way of repeated well drilling for WTD determination. This information could be used for measuring the depletion of WTD during dry periods (droughts), site-specific irrigation and drainage design with the aided advantage of labor and time savings in case of observing precision water management practices at large fields.

Weed infestations reduce turfgrass aesthetics and uniformity. Postemergence (POST) herbicides are applied uniformly on turfgrass, hence areas without weeds are also sprayed. Deep learning, particularly the architecture of convolutional neural network (CNN), is a state-of-art approach to recognition of images and objects. In this paper, we report deep learning CNN (DL-CNN) models that are remarkably accurate at detection of broadleaf weeds in turfgrasses.VGGNet was the best model for detection of various broadleaf weeds growing in dormant bermudagrass [Cynodon dactylon (L.)] and DetectNet was the best model for detection of cutleaf evening-primrose (Oenothera laciniata Hill) in bahiagrass (Paspalum notatum Flugge) when the learning rate policy was exponential decay. These models achieved high FThe results of the present research demonstrate the potential for detection of broadleaf weed using DL-CNN models for detection of broadleaf weeds in turfgrass systems. Further research is required to evaluate weed control in field conditions using these models for in situ video input in conjunction with a smart sprayer. © 2019 Society of Chemical Industry.

Wild blueberry (Vaccinium angustifolium Ait.) fields in the north east Canada are naturally grown in a course textured thin layer of soil and below this layer is a soilless layer of gravel. The root zone depth of this crop varies from 10 to 15 cm. Investigating the depth to the gravel layer below the course textured soil is advantageous, as it affects the water holding capacity of the root zone. Water and nutrient management are the two primary determinants of crop yield and the amount of leaching. The objective of this study was to estimate the depth to the gravel layer using DualEM-2 instrument. A C++ program written in Visual Studio 2010 was used to develop mathematical models for estimating the depth to the gravel layer from the outputs of DualEM-2 sensor. Two wild blueberry fields were selected in central Nova Scotia, Canada to evaluate the performance of DualEM-2 instrument in estimating the rootzone depth above the gravel layer. The mid points of squares created by grid lines were used as the sampling points at each experimental site. The actual depth to the interface was measured manually at selected grid points (n = 50). The apparent ground conductivity (ECa) values of DualEM-2 were recorded and the depth to the interface was estimated for the same sampling points within the selected fields. The fruit yield samples were also collected from the same grid points to identify the impact of the depth to the gravel layer on crop yield. After calibrations, comprehensive surveys were conducted and the actual and estimated depths to the interface were established. The interpolated maps of fruit yield, and the actual (zin) and estimated ( $$ {\text{z}}_{\text{in}}^{*} $$ ) depths to the interface were created in ArcGIS 10 software. Results indicated that the zin was significantly correlated with $$ {\text{z}}_{\text{in}}^{*} $$ for the North River (R 2 = 0.73; RMSE = 0.27 m) and the Carmel (R 2 = 0.45; RMSE = 0.20 m) sites. Results revealed that the areas with shallow depth to the gravel layer were low yielding, indicating that the variation in the depth to the gravel layer can have an impact on crop productivity. Non-destructive estimations of the depth to the gravel layer can be used to develop erosion control strategies, which will result in an increased crop production.

Wild blueberry fields have a significant proportion of bare spots/weed patches, scattered throughout the field, emphasizing the need for targeted fertilizer applications. The existing prescription map-based variable rate (VR) spreader cannot take account of the presence of small, irregularly shaped bare spots/weed patches during fertilization as only each half of the boom (3.66 m; 6 nozzles) is controlled—not each individual nozzle. The objective of this study was to modify the existing VR spreader for spot-application (SA) of fertilizer only in plant areas. The sensing and control system developed was capable of discriminating bare spots/weeds from plants, and shifting the independent control from 6 nozzles (3.66 m) to each pair of nozzles (1.22 m). The modified VR granular (MVRG) fertilizer spreader was able to use a prescription map and the sensing and control systems simultaneously within a field, to avoid fertilization in variable sized bare spots/weed patches. The performance of the MVRG fertilizer spreader was evaluated under two different lighting conditions and three ground speeds. Twelve bare spots/weed patches and plant areas were randomly selected in the wild blueberry field and weighed sticky collectors were placed to collect clay filler which was used as an analogue of fertilizer. The MVRG fertilizer spreader was operated on SA (application only in plant areas) and uniform (application in plants and bare spots/weed patches) modes alternately and the collectors were collected and re-weighed. Results of this study suggested that the MVRG spreader was capable of detecting plants/bare spots/weeds for SA of fertilizer. Spot application of fertilizer can help to reduce excessive fertilizer usage in bare spots/weeds, which will increase farm profitability.

A three-year study was conducted at two sites in Florida with Spodosols and Entisols differing in drainage characteristics to: 1) estimate biomass and nutrient accumulation in 1- to 5-year-old citr...

Water is a limiting factor in Florida citrus production during the majority of the year because of the low water holding capacity of sandy soils resulting from low clay and the non-uniform distribution of the rainfall. In Florida, the major portion of rainfall comes in June through September. However, rainfall is scarce during the dry period from February through May, which coincides with the critical stages of bloom, leaf expansion, fruit set, and fruit enlargement. Irrigation is practiced to provide water when rainfall is not sufficient or timely to meet water needs. Proper irrigation scheduling is the application of water to crops only when needed and only in the amounts needed; that is, determining when to irrigate and how much water to apply. With proper irrigation scheduling, yield will not be limited by water stress. With citrus greening (HLB), irrigation scheduling is becoming more important and critical and growers cannot afford water stress or water excess. Any degree of water stress or imbalance can produce a deleterious change in physiological activity of growth and production of citrus trees. The number of fruit, fruit size, and tree canopy are reduced and premature fruit drop is increased with water stress. Extension growth in shoots and roots and leaf expansion are all negatively impacted by water stress. Other benefits of proper irrigation scheduling include reduced loss of nutrients from leaching as a result of excess water applications and reduced pollution of groundwater or surface waters from the leaching of nutrients. Recent studies have shown that for HLB-affected trees, irrigation frequency should increase and irrigation amounts should decrease to minimize water stress from drought stress or water excess, while ensuring optimal water availability in the rootzone at all times.