Different sampling schemes were tested to estimate yield (kg/tree), fruit firmness (kg) and the refractometric index (°Baumé) in a peach orchard. In contrast to simple random sampling (SRS), the use of auxiliary information (NDVI and apparent electrical conductivity, ECa) allowed sampling points to be stratified according to two or three classes (strata) within the plot. Sampling schemes were compared in terms of accuracy and efficiency. Stratification of samples improved efficiency compared to SRS. However, yield and quality parameters may require different sampling strategies. While yield was better estimated using stratified samples based on the ECa, fruit quality (firmness and °Baumé) showed better results when stratifying by NDVI.

Chemical thinning in apple orchards is a commonly used technique for improving yield. The objective of this work was to quantify bloom intensity of individual trees using color images, and estimate the time for the peak of the bloom. Image acquisition campaigns were conducted in an apple orchard with Golden Delicious variety during two growing seasons. Image processing algorithms were developed to detect flowers. The correlation between the manual and automatic estimation of bloom intensity at the day of the peak was 0.90 and 0.97 for 2014 and 2015 respectively. Based on the above relationships, maps of blooming intensity were derived and its variability was established.

An increasing number of farm machines nowadays implement precision agriculture technologies. Most of these operate through proximal sensing using optical sensors (i.e. NIR or Vis-NIR). Imaging techniques in this context have received minor consideration due to the complex analysis of the data but on the other side offer great flexibility. This study reports a preliminary pilot imaging multi-sensor retrofit system to be applied independently on a wide range of agricultural machines and able to test different monitoring or control image-based applications for precision agriculture. The process, based on RGB image, was tested for in-field discrimination of weeds in lettuce and broccoli crops. It works by discriminating and extracting single plants from the soil and weeds. However, to be truly implementable, the experimental code should be optimized in order to shorten the time needed for acquisition and processing.

The goal of this work was to cluster maize plants perception points under six different growth stages in noisy 3D point clouds with known positions. The 3D point clouds were assembled with a 2D laser scanner mounted at the front of a mobile robot, fusing the data with the precise robot position, gained by a total station and an Inertial Measurement Unit. For clustering the single plants in the resulting point cloud, a graph-cut based algorithm was used. The algorithm results were compared with the corresponding measured values of plant height and stem position. An accuracy for the estimated height of 1.55 cm and the stem position of 2.05 cm was achieved.

The Society of Precision Agriculture Australia Inc. (SPAA) is recognised as a leading, grower driven farming group in Australia. As an organisation it provides programs and services to its members and wider industry to promote the development and adoption of Precision Agriculture (PA) technologies as a means of enhancing the profitability and sustainability of agricultural production systems. This is achieved through publishing Australia’s only PA-dedicated magazine, delivering field days, seminars and conducting on-farm PA demonstrations and experiments. SPAA provides farmers with an independent source of advice on new concepts and equipment. The grains industry was the springboard for initial adoption, with winegrapes, horticulture and the sugar industry the focus sectors for further expansion. The purpose of this paper is to share the SPAA experience with a view to assisting the development of similar organisations in other countries

APOLLO, a newly funded H2020 EU project will develop an agricultural advisory platform for small farmers based on Copernicus Sentinel satellites. It will provide services for tillage scheduling, irrigation scheduling, crop growth monitoring and yield estimation. The aim of this study was to identify the farmers’ requirements of the APOLLO platform. In total 121 farmers were interviewed in Spain, Serbia and Greece. More than 90% of the farmers pointed out that smart agriculture and use of satellite data in agriculture are important. Additionally, more than 80% want to have access to historical data and a flexible subscription policy to the platform according to their needs and use. However, significant differences exist among farmers of these countries in terms of technology awareness and penetration, which should be taken into consideration for developing a successful platform.

In this paper, novel geospatial services are presented which are able to process on the server-side numerous remote sensing data based on big data frameworks like Hadoop and Rasdaman. The developed system itself features several software modules that orchestrate the different image processing algorithms responsible for the production of consistent value-added maps like canopy greenness and leaf area index. Through distributed multitemporal analysis, the entire crop growth cycle can be continuously monitored through the analysis of time-series observations. These observations cover multiple crop growth cycles, offering invaluable information by linking weather statistical data with the start, the end and the duration of each growth cycle enabling critical decisions by direct comparison with the current crop growth state.

Potential yield is one of the criteria used as an input to nitrogen (N) fertilizer management decisions when using SIX EASY STEPS (6ES), the fertilizer recommendation tool used in the Australian sugar industry. Most commonly, 6ES is implemented using a district yield potential (DYP). In this study, we use analysis of sugar mill and yield monitor data from the Herbert River cane growing district to demonstrate that yield is markedly spatially variable, with this variability following the same patterns from year to year. There would therefore be value in a more location specific consideration of potential yield and application of 6ES. Similar analyses could be readily conducted in other sugar producing regions with potentially important implications for fertilizer use efficiency and the minimization of nutrient accessions to the Great Barrier Reef.

New Super-High-Density (SHD) olive orchards designed for mechanical harvesting are increasing very rapidly in Spain. Most studies have focused in effectively removing the olive fruit, however the machine needs to put significant amount of energy on the canopy that could result in structural damage or extra stress on the trees. During harvest, a series of 3-axis accelerometers were installed on the tree structure in order to register vibration patterns. A LiDAR (Light Detection and Ranging) and a camera sensing device were also mounted on a tractor. Before and after harvest measurements showed significant differences in the LiDAR and image data. A fast estimate of the damage produced by an over-the-row harvester with contactless sensing could be useful information for adjusting the machine parameters in each olive grove automatically in the future.

Precise applying of PPP (Plant Protection Products) in orchards and vineyards requires new kinds of sprayer technologies and new methods of sensor data evaluation. In this paper a selective electrical driven sprayer, carried by the autonomous robotic platform elWObot, is introduced. A 3D-Simulation environment and the framework ROS (Robot Operating System) helps developing and testing the interaction between the sprayer and the robot. The calculated leaf wall area (LWA) and the distance from the sprayer to the leaves in the spray region, control the flow-rate and the air-assist of eight adjustable sprayers individually. First field trials showed that the adaption of the software from the simulation to the hardware worked as expected.

The establishment of the system Soil – Yield that occured in Latvia during the 1970–80s could be considered as the beginning of precision farming with the available technologies. The first precision farming technologies have been associated with harvesting where combines and tractors with the automatic steering were used. The precision agriculture in Latvia includes various branches. Latvia farmers are using precision crop farming, precision livestock farming, precision fruit growing, precision bee keeping, precision farming greenhouse and precision growing berries. Precision farming technologies in Latvia are introduced mainly in large scale farms, with more than 1000 ha. The most important researches in precision farming in Latvia were done in 2000s.

Monitoring grapevine canopy size and evolution during time is of great interest for the management of the vineyard. An interesting and cost effective solution for 3D characterization is provided by the Kinect sensor. To assess its practical applicability, field experiments were carried out on two different grapevines varieties (Glera and Merlot) for a three months period. The results from 3D digital imaging were compared with those achieved by direct hand-made measurements. Estimated volume was then effectively correlated to the number of leaves and to the leaf area index. The experiments demonstrated how a low cost 3D sensor can be applied for fast and repeatable reconstruction of vine vegetation, opening up for new potential improvements in variable rate application or pruning

Great technological advances have been made in Precision Agriculture (PA) in the past decade, yet adoption of PA in intensive grassland areas in North West Europe is low. This is despite the fact that in these areas the market structures are suitable and there are highly developed agricultural and food industries offering great potential for the application of new technology. Specific inefficiencies in plant nutrient management in soil exist, which are not only limiting grass yields but are also causing environmental deterioration. Soil nutrient management efficiency could be greatly improved using PA techniques, but the complexity of grassland systems, coupled with a lack of calibration of sensors specific to grassland, together with local barriers, appear to be the reasons why PA adoption is poor in these areas. This paper reviews new and existing technology including soil and crop sensors, navigation devices, remote sensing and unmanned aerial vehicles. The suitability and readiness of these technologies for adoption in grassland areas is discussed, along with data interpretation issues, future perspectives and research opportunities.

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.

The main goal of this study was assessing the technological and agronomic performances of a centre pivot Variable Rate Irrigation (VRI) system. The study was conducted in 2015 on a 16-ha field cultivated with maize. Irrigation was scheduled in three Management Zones according to data provided by a real-time monitoring system based on an array of soil moisture sensors. First results demonstrated the potential benefits of the VRI system on irrigation performance however a multiyear comparison is requested for evaluating the response to climate variability. VRI resulted in yields comparable to the business-as-usual regime but through a noticeable reduction in irrigation volumes.

Recent technological progress in high-speed planting (HSP) warrants economic analysis of its potential. A whole farm optimization model of a 1000 ha Kentucky, USA corn and soybean operation finds that operating cost savings (labor, fuel, tractor repairs) and yield increases couple in recovering annual ownership costs of HSP technology. Changes in farm net returns are positive for all 12-row planter scenarios and all double speed cases for the 16-row planter but not for a 50% increase in speed with the 16-row planter. The greatest profit potential occurred when adopting the combination of HSP and variable rate application (VRA), with increased net returns of up to 6.57% compared to conventional speed no VRA for the 12-row planter.

This paper investigates the effectiveness of using a UAV with dual commercial off-the-shelf (COTS) cameras, one un-modified and one modified to sense near infra-red (NIR) wavelengths to identify the onset of disease within a trial crop of potatoes. The trial was composed of 2 plots of 16 drills containing 12 tubers exposed to the blackleg disease-causing bacterial pathogen (Pectobacterium atrosepticum) in order to demonstrate best practise tuber storage and haulm destruction methods. Eleven sets of aerial data were gathered between 27/5/2016~29/7/2016 and compared with ground truth data collected on 14/7/2016. Visual analysis of the data could only detect the onset of disease and not the specific infection and resulted in a user accuracy (UA) of 83% and producer accuracy (PA) of 78%, with a total accuracy (TA) of 91% and Kappa coefficient (K) of 0.75. The building blocks of an automated classification routine have been constructed using pixel and object based image analysis (OBIA) methods, which have shown promising first results (UA 65%, PA 73%, TA 87%, K 0.61) but requires further refinement to achieve an equivalent level of accuracy as that of the visual analysis.

This research has multidisciplinary characteristics with a focus on cotton fiber production and computational solutions to improved data exchange. The research is divided into three parts, the identification of the cotton fiber production processes, the formal ontology for identifying the data classes, and finally the proposal of a specific metadata standard for cotton fiber production. The absence of a specific standard for this segment favors the heterogeneity in the various data sources. The contribution of the research lies in improving the information exchange used in agricultural systems providing identification of each individual responsible for steps in the cotton production chain.

The objective of this study was to investigate the relationship between temperature–humidity index (THI) and rumination time (RT) in order to possibly exploit it as a useful tool for animal welfare improvement. During summer 2015 (1 June to 31 August), data from an Italian Holstein dairy farm located in the North of Italy were collected along with environmental data (i.e. ambient temperature and relative humidity) recorded with a weather station installed inside the barn. Rumination data were collected through the Heatime® HR system (SCR Engineers Ltd., Hadarim, Netanya, Israel), an automatic system composed of a neck collar with a Tag that records the RT and activity of each cow. A significant negative correlation was observed between RT and THI. Mixed linear models were fitted, including animal and test day as random effects, and parity, milk production level and date of last calving as fixed effects. A statistically significant effect of THI on RT was identified, with RT decreasing as THI increased.