Small-plot trials are the foundation of open-field agricultural research because they strike a balance between the control of an artificial environment and the realism of field-scale production. However, the size and scope of this research field is often limited by the ability to collect data, which is limited by access to labour. Remote sensing has long been investigated to allocate labour more efficiently, therefore enabling the rapid collection of data. Imagery collected by unmanned aerial vehicles (UAVs) are a significant development in remote sensing for agricultural research, and their potential for efficient workflows has generated interest from agricultural scientists. However, data analysis techniques have not matured at the same rate, and a knowledge gap exists between end users of the data and those who can manipulate, extract, and deliver it. This study was established to address the barrier to adoption of UAVs created by this knowledge gap. We created a tool that can semi-automatically extract plot-level statistics from UAV-acquired imagery. This tool simplifies tasks that were previously accomplished via a Geographic Information System (GIS) by incorporating these tools into a web-based application, the Guelph Plot Analyzer (GPA). Users can upload a GeoTiff raster file to the application, and are presented with the UAV-acquired map, as well as a variety of polygon drawing tools. Using a hierarchy of Trial to Replication to Plot, the user draws boundaries around each category, and the tool can then automatically populate a shapefile with polygons corresponding to the plots. Polygons can be buffered to remove border effects, and alleyways can be specified to correctly align rows. Once finalized, the user can export the overlay as a shapefile, as well as a spreadsheet containing image statistics, including the mean, median, range, and a histogram of pixel values. The plots are labelled according to the user’s specified naming convention, making the data easily transferrable to statistical analysis software, as well as seamless to integrate into existing studies. The plot extraction tool is an efficient means for non-remote sensing scientists to turn qualitative imagery into quantitative measures and will help modernize small-plot research as UAVs become more common.

Nowadays, precision agriculture combined with modern information and communications technologies, is becoming more common in agricultural activities such as automated irrigation systems, precision planting, variable rate applications of nutrients and pesticides, and agricultural decision support systems. In the latter, crop management data analysis, based on machine learning and data mining, focuses mainly on how to efficiently forecast and improve crop yield. In recent years, raw and semi-processed agricultural data are usually collected using sensors, robots, satellites, weather stations, farm equipment, farmers and agribusinesses while the Internet of Things (IoT) should deliver the promise of wirelessly connecting objects and devices in the agricultural ecosystem. Agricultural data typically captures information about farming entities and operations. Every farming entity encapsulates an individual farming concept, such as field, crop, seed, soil, temperature, humidity, pest, and weed. Agricultural datasets are spatial, temporal, complex, heterogeneous, non-standardized, and very large. In particular, agricultural data is considered as Big Data in terms of volume, variety, velocity and veracity.

Designing and developing a data warehouse for precision agriculture is a key foundation for establishing a crop intelligence platform, which will enable resource efficient agronomy decision making and recommendations. Some of the requirements for such an agricultural data warehouse are privacy, security, and real-time access among its stakeholders (e.g., farmers, farm equipment manufacturers, agribusinesses, co-operative societies, customers and possibly Government agencies). However, currently there are very few reports in the literature that focus on the design of efficient data warehouses with the view of enabling Agricultural Big Data analysis and data mining. In this paper, we propose a system architecture and a database schema for designing and implementing a continental level data warehouse. Besides, some major challenges and agriculture dimensions are also reviewed and analysed.

E-agricultural is an emerging field focusing in the enhancement of agriculture and rural development through improve in information and data processing. The data-intensive characteristic of these domains is evidenced by the great variety of data to be processed and analyzed. Countrywide estimates rely on maps, spectral images from satellites, and tables with rows for states, regions, municipalities, or farmers. Precision agriculture (PA) relies on maps of within field variability of soil and plant attributes, with one experiment using various technologies to measure soil and plant attributes. Despite the difficulty in obtaining data in the field and the interaction between the collection stage and the data processing, storage, and interpretation environments has been a bottleneck for producers seeking to make use of the technology. An existing problem is the organization and administration of this data to obtain the information that can be used for the correct management of the field. The objective of this work is to present a computational solution to this problem. AgDataBox-API is a platform that was developed to store and integrates traditional agricultural data, data samples, maps, and management zones. This platform was developed using cloud framework and is for other developers to easily integrate their systems into the cloud, without having to knowhow the internal integration is done. Communication between a system and AgDataBox-API is done using HTTP protocol. As example, a free mobile application was developed using Android and Apple operational systems and allow insertingprecision agriculture data using the smartphone. To demonstrate the potentiality of the software an experimental data from two sugarcane fields located at São JoãoMill (Araras - SP), each area with approximately 200 hectares characterized by production environment (texture and climate) was used. The results demonstrate how data can be easily handled and information can be extracted from it. This software is free of charge.

For more than two decades, the success of Australia’s agricultural and rural sectors has been supported by the work of the Rural Research and Development Corporations (RDCs). The RDCs are funded by industry and government. For the first time, all fifteen of Australia’s RDC’s have joined forces with the Australian government to design a solution for the use of big data in Australian agriculture. This is the first known example of a nationwide approach for the digital transformation of an agriculture sector, internationally.

The Accelerating precision agriculture to decision agriculture project collaborated with six leading research organisations evaluated the current and desired state of digital agriculture in Australia and made recommendations for Australian primary producers to overcome the challenges currently limiting digital agriculture and profit from their data. The project conducted surveys of producers to understand their needs, drivers and level of knowledge; reviewed the state of and requirements for data connectivity on and off-farm; explored legal aspects looked at rules concerning data ownership, access, privacy and trust; assessed data sets currently available and what will be needed for digital agriculture in Australia; and it developed a big data reference architecture to support interoperability across datasets and systems into the future.

Digital agriculture in Australia was found to be in an immature state in many parts including strategy, culture, governance, technology, data, analytics, and training. This is to the detriment of innovation and producer adoption of digital agriculture in Australia. With maturity, the economic modelling identified that the implementation of digital agriculture across all Australian production sectors (as represented by the 15 RDCs) could lift the gross value of agricultural (including forestry, and fisheries and aquaculture) production by $20.3 billion (a 25% increase on 2014). Thirteen recommendations are made in the areas of policy, strategy, leadership, digital literacy and enablers. To achieve maturity, cross industry and cross-sector collaboration is vital as many of the issues impeding maturity are common and this scale of investment is required to implement solutions for Australian conditions and to keep pace with the rest of the world.

Precision agriculture is an emerging area at the intersection of engineering and agriculture, with the goal of intelligently managing crops at a microscale to maximize yield while minimizing necessary resource. Achieving these goals requires sensors and systems with predictive models to constantly monitor crop and environment status. Large datasets from various sensors are critical in developing predictive models which can optimally manage necessary resources. Initial experiments at University of St. Thomas (UST) greenhouse have demonstrated the feasibility of sensor system for use in Precision Agriculture. Hundreds of high-value vegetables such as lettuce, beans, peas, onions, spinach and bok-choy were planted in different types of soils and nutrients. Soil moisture and pH level of each plant were monitored and collected by soil sensors. A weather station was installed to collect the air temperature, air moisture, light, and wind information in the greenhouse. A Photosynthetically Active Radiation (PAR) sensor was also installed to monitor how the plant grows responding to different wavelengths. A multi-spectral camera was also used to observe the Near-Infrared Reflection (NIR) from each plant. This information reveals the amount of photosynthesis occurring in each plant, providing an important indicator of plant’s health. All information collected was time stamped such that different sensor information could be correlated. This information was then fed back to a controller to release water and nutrition to different plant groups at different times in order to meet different growth patterns.

During the 50-day growth period, over one billion data points were generated from 6 different plant types. In order to handle and process such big data. Cloudera Hadoop Cluster and software modules to process such data is being developed. Using the information collected from our infrastructure, more sophisticated models can be developed enabling more sustainable farming.

Agricultural data of many types (yield, weather, soil moisture, field operations, topography, etc.) comes in varied geospatial aggregation levels and time increments. For much of this data, consumption and utilization is not time sensitive. For other data elements, time is of the essence. We hypothesize that better quality data (for those later analyses) will also follow from real-time presentation and application of data for it is during the time that data is being collected that errors can be corrected and improvements of settings, operations, and protocol can be implemented.

The objectives of this work were to develop open source real time data exchanges for the purposes of logistics, profitability, and data quality.  The real time exchanges can require edge or cloud computing for analysis and visualization. The examples to be shared are open source contributions to the agriculture community related to: 1. Instant individual livestock records according to personal observation. 2. Presence/activity tracking to facilitate shared record keeping for improved logistics of personnel and machinery, 3. Auto-generation, analysis, and display of machine-based data in cropping systems to facilitate records and machinery and labor efficiency metrics “by the field”.