Big Data

On this page...

Big Data Basics      Initiatives in Big Data      Big Data Definitions      Big Data News 

    Relevant Publications


Big Data Introduction

Big Data is data whose scale, diversity, and complexity require new architecture, techniques, algorithms, and analytics to manage it and extract value and hidden knowledge from it.

So what exactly does that mean? This data includes large collections of farm data that is being used by farmers, companies, and government agencies to aid in decision making related to crop production and management practices as well as better predictions around nutrient and water availability.  It is important to understand what value all of this farm data provides to the producer.  By using farm data to drive input management and other farm decisions, producers can identify and quantify limiting productivity variables.

The Big Data Flow

  • A farmer will upload farm and personal data from ground and equipment sensors, drones, etc.

  • Agricultural Technology Provider (ATP) will aggregate farmer’s data, combines other relevant data set, and applies algorithms to analyze.

  • The ATP then gives the farmer a customized solution or recommendation based on data received.

  • The farmer can then use the recommendations provided by the ATP to make agronomic, economic, and farm management decisions on their farm.

What is "Digital Agriculture"?

Digital agriculture is evolving today as industry develops services and technologies to permit the wireless transmissions of data along with analytics to derive information.  The premise of digital agriculture includes the advancement of precision agriculture strategies, prescriptive agriculture and the hot topic of big data and how it could advance the agriculture sector.  A common thread to this progression is how precision agriculture technology will enable farmers, retailers and custom applicators to enhance nutrient management in regards to placement, timing and generation of new data layers for evaluating success.  These spatial data layers will most importantly direct new strategies that encompass provisions for sustainability and environmental surrounding nutrient management.   Digital Agriculture sums up the current status of the data space in agriculture, trends related to services directing input management and the value of data for improving productivity and profitability of farm operations.

“Digital Agriculture” combines multiple data sources with advanced crop and environmental analyses to provide support for on-farm decision making.

Digital Agriculture is made up of many components.  These components are used to make decisions based on social, economic, and environmental goals within a farming operation.  When a producer utilizes Digital Agriculture, they are advancing their operation by combining the latest technology with best management practices to increase the value of many aspects on the farm.  The components within Digital Agriculture include Enterprise Agriculture, Prescriptive Agriculture, Precision Agriculture and Big Data Use. 

When discussing Enterprise Agriculture, it is important to realize that there are many forms of agricultural enterprises around the world but decision making related to enterprise is always based on cost, regardless of the type of agricultural enterprise. Decision making is encountered everyday on a farm operation and many of these decision sit on a foundation of finances.  Digital Agriculture can assist farmers with creating budgets, analyzing productivity, input and personnel costs, etc.  By using data in these different areas, producers can make decisions that would provide the most economic return for their business.

Prescriptive Agriculture refers to the specific application of input (seed, fertilizer, pesticide, etc.) based on data analytics.  Data obtained from soil sampling for instance, can be used to determine how much fertilizer should be placed on the field.  Maps are often created by agronomists or consultants within the producers trusted network of professionals.  From here prescriptions can be made to help manage poorly yielding zones, improve higher yield potential areas, increase production in good zones, etc.  Common technology used in prescriptive agriculture includes GPS and VRT (Variable Rate Technology).  VRT consists of the machines, and systems for applying production materials at a specific time (and in specific locations within a field(s)).  Utilizing prescriptive agriculture practices allows producers to responsibly add inputs (such as nitrogen) to their land.  The benefits are not only seen by the producer in cost savings and increased yield potential, but also in the environment because fertilizers are more accurately dosed and placed within fields.

Useful Big Data Definitions

Precision Agriculture 

Precision agriculture is a farming management concept based on observing, measuring and responding to variability in crops. These variabilities contain many components that can be difficult to compute and as a result technology has advanced to off-set these difficulties.  Two types of technology can generally be found within precision agriculture: those which ensure accuracy, and those that are meant to enhance farming operations.  By combining these two technologies, farmers are able to create a decision support system for an entire operation, thereby maximizing profits and minimizing excessive resource use.

Agronomic Data

Represents data compiled from a specific farming operation or at the field level generally related to agronomy based information such as yield, population, hyrbid, nutrient application.  Agronomic Data is tied to the land or field where it was generated.  Types of Agronomic Data include (but are not limited to) hybrid selections, plant populations, yield data, soils data, pesticide application details, and scouting information.  Data generated from a yield monitor can be used to document yelds, and for on -farm seed trials.  in addition, yield monitor data can be used to make genetic, environmental, and management effect analyses. Soils data is being used to make fertilizer and regional environmental compliance decsioions, while scouting data is being used to make spraying decisions as well as regional pest or disease analytics.

Machine Data

Data that is compiled using multiple sensors located on agricultural machinery.  Most relate machine data to the information that can be collected from the CAN (controlled area network) on machines and implements. Machine data can also include guidance system information (autosteer, GPS path files, bearing, etc.), variable rate control/technology and seeding rate controllers.  Data in these forms is transmitted to Agricultural Technical Providers (ATPs) via CANBus, which is a high-spped, wired data network connection between devices.  This device utilizes a single wire set to relay information, which reduces the amount of wires needed for a system and allows for a cleaner way to transfer data.

Internet of Things

The network of physical objects or "things" embedded with electronics, software, sensors, and network connectivity, which enables these objects to collect and exchange data. The Internet of Things (IoT) allows objects to be sensed and controlled remotely across existing network infrastructure, creating opportunities for more direct integration between the physical world and computer-based systems, and resulting in improved efficiency, accuracy and economic benefit. Each thing is uniquely identifiable through its embedded computing system but is able to interoperate within the existing Internet infrastructure. Experts estimate that the IoT will consist of almost 50 billion objects by 2020.

Industrial Internet

A term coined by Frost & Sullivan and refers to the integration of complex physical machinery with networked sensors and software. The industrial Internet draws together fields such as machine learning, big data, the Internet of things, machine-to-machine communication and Cyber-physical system to ingest data from machines, analyze it (often in real-time), and use it to adjust operations.  Some consider the evolution of digital agriculture today (e.g. 2015) as leading to the Industrial Internet in agriculture.

Initiatives in Big Data within the Agricultural Community

Privacy and Security Principles for Farm Data

We feel that it is important for producers to have a trusted source of information about Big Data in Agriculture.  In May of 2015, the American Farm Bureau released the Privacy and Security Principles for Farm Data.  These 13  privacy and security principles outline preferences and common terminology that should be considered by data services and products handing farmer data.  Those that have signed this document represent agriculture industry and farmer organizations committed to ongoing engagement and dialogue regarding farmer data handling along with Big Data.

Click here for a detailed look at the Privacy and Security Principles for Farm Data

It is important for producers to work with their (or their prospective) Agricultural Technical Provider(s) to obtain the company data privacy policy.  Many companies have signed on to the Privacy and Security Principles for Farm Data Policy and it is imperative that their privacy policies are aligned with guidelines within the American Farm Bureau Privacy Policy.  Using the AFBF Privacy Policy, producers can select a trusted data service.  To be sure that the company you have chosen as your ATP is a trusted one, obtain their privacy policy and double check that it aligns with the Privacy and Security Principles for Farm Data Policy.  Additionally, the American Farm Bureau, with other cooperating organizations, have created a "Transparency Evaluator" to help bring clarity and transparency into the contracts that govern precision ag technology.  

Click here to access the Transparency Evaluator

News from the Big Data Community

C-FARE Releases a Report on Big Ag Data

Relevant Publications