How Does Artificial Intelligence Really Work in Agriculture?

How far are we from a computer being able to decide what variety or hybrid should be planted in a field, how it is fertilized, and prescribe crop protection chemicals needed? The promise of artificial intelligence (AI) has been a popular discussion in the media, not only for agriculture but for a variety of applications. But what is AI, how does it work in farming plus what does it mean and how does it impact agriculture?

One of the most common ways this new technology is discussed for use in agriculture is helping to make seed selection recommendations for individual fields. How does this work? How can a computer be programmed to know what seed to plant? There are a couple key aspects needed to make this new selection process work. One of the main items is the use of machine learning which represents a unique subset of algorithms within artificial intelligence. Machine learning is simply the ability for a computer to learn how to do things better or evolve without really being directly programmed by a person. The computer programming, or algorithms, start with a basic ability to perform a certain task.

One common example that people have participated in training an algorithm — and maybe didn’t know it is one — is the CAPTCHA system, which is often used to “prove you are a human” when logging into a website. The main purpose of the CAPTCHA system is to provide a higher level of security for websites, but at times it also learns from people. The system has been used in the past to train algorithms to better identify text. As people are looking at jumbled images and typing in the letters they see in an image, the machine learning algorithm verifies someone is a person when the letters are obvious while it learns and updates the algorithm for letters not initially known in an image. Once a sufficient number of people look at a letter and the majority agree on what letter it is, this information is fed back, or used to “train” the algorithm what letter is being displayed. As this process is repeated thousands, or millions of times, the computer system improves its ability to recognize letters. This well-trained computer algorithm can now be used to digitize old texts that are difficult to see, and time consuming for an actual person to try and transcribe. This training process for algorithms is used extensively today. Companies everywhere are developing machine learning algorithms and then presenting the computer with different information and letting it know the correct answer so the system learns, and is eventually able to complete the task on its own, accurately and quickly.

So now that we know how machines learn and artificial intelligence can be developed, how does that lead to a computer making a seeding recommendation? The next step in the process is to look for a doppelganger. This is where the big data term comes in to work with AI to solve problems. Companies working to provide some sort of AI-driven tool are always talking about how much data they have in their systems, and with good reason. It takes a lot of data to train the algorithms, but what are they being trained for in this instance? The idea is that in a certain soil type, with a certain weather pattern, and as many other variables as can be accounted for, seed variety X will have yield Y. If you have a big enough database of information, you can train the computer system to determine what the “best” variety is for a field. The system is essentially trained to look through all the data and find field conditions that are a doppelganger or look just like the field being asked about. Digging through (commonly called data mining) all this data allows the AI to make the determination variety XYZ is the best for this field since there is data from a bunch of other parts of different fields that have the same or similar conditions where that variety yielded better than other varieties grown in those conditions.

This is great. The computers can crunch through all this data and help farmers make more informed decisions. But why haven’t these products taken over the market yet? One hurdle, as mentioned above, is having enough data available. If you are trying to match up all the different variables for a field you need a lot of different combinations of soil types, weather, seed, fertility, planning dates, etc. You also need this data to be standardized and read into a system, and most important, for it to be accurate. As an industry this is something we struggle with. Think of a yield file from a combine. Often you’re lucky if the correct crop type was captured in the data and the yield sensor was calibrated this season. Most people in precision ag have seen fields of 250-bushel yields in “soybean” fields where the operator didn’t bother to label it as corn. For the AI system to be able to recommend a variety we not only need the correct crop type documented but we also need to know what variety was actually planted, when, and at what population to really be able to train the algorithms and mine the data.

Another obstacle is there are just a lot of variables to account for in farming. Most obvious is weather — it isn’t too hard to have a record of what happened in a field from a weather standpoint. However, knowing what the coming season is going to look like is a little trickier. So not only do you need to have all the different data about when, how, where, and which seed was planted, you need to know if it is going to be a hot dry year, or cool and wet. Forecasts are continually improving, largely from the application of the same type of AI systems to model weather to know what is coming. However forecast accuracy is really only something you can really trust out a few days, or maybe a week or two. Knowing what the next 6 months are going to be like is still fairly hard to predict for the most part, but again things are always getting better as the machines learn more.

Even though there are some hurdles the technology by its very nature is continually improving. Additionally, we as an industry are getting better at capturing accurate data these algorithms can use to continue to improve.

Machine learning is not only being used to help recommend seeds, the technology is also being applied in one way or another in applications like:

  • Automated machine adjustments (combine, planter down force, etc.)
  • Weather forecasting
  • Disease or pest identification, image recognition
  • Disease and pest movement
  • Machine maintenance and break-down prediction
  • Field accessibility or harvest advisory type estimations
  • Irrigation and water management
  • Nutrient use and fertility recommendations
  • Autonomous machines or robots

One other important aspect of AI to keep in mind is the data itself. Hopefully based on this article people understand why so many companies are interested in farmers sharing data with them. Anyone developing these machine learning algorithms needs tremendous amounts of data to train their systems, otherwise their product could be less accurate than a competitor with more data. This also shows why some people have been describing data as a new form of currency. Farmers should keep this in mind as they are looking at new software tools asking for them to share their data. The data is very valuable and important to train these algorithms, but also very difficult to quantify the monetary value of any particular set of data fed into the system. Individually the data records have little value, their true significance comes though when combined with many other records. It is important all parties know what is going on, who needs what data, what they are doing with it, and what benefits each party receives from sharing it. This is an exciting time to be involved with agriculture and AI will undoubtedly have a substantial impact on how farming is done for years to come.

December Update

Greetings and happy holiday’s ADC supporters, it is a busy time of year for the ADC. We have been supporting course activities by helping set up accounts for several precision ag classes where college students will be educated on real life use of agricultural data. This includes data collection from multiple systems, organizing, archiving and sharing through the ADC environment as well as learning how best to utilize agricultural data to bring value to the farm. We are also busy making upgrades and enhancements to the platform enabling easier use for different universities that are leveraging the system to manage their on-farm research projects and collaborations with cooperating growers.

Additionally, several of our board members have been busy at fall and winter conferences discussing the value of data and hurdles farmers are encountering when trying to optimize their operations using their data. The board members are using these opportunities to educate the industry on the importance of farmer-controlled data. Along those lines, we recently published an article on PrecisonAg.com discussing data privacy on the farm and how it relates to recent regulations regarding personal data enacted by the European Union (EU). We plan to post more articles going forward, so if there are any specific topics you would like us to address drop us a note.

We hope everyone had a productive 2018 though there were many challenges from both the markets and Mother Nature across the country. The ADC believes farmers and the industry need to make better informed decisions going forward to successfully navigate these challenging times. We are doing what we can to ensure everyone in the industry, individual farmers, ag retailers, service providers, universities and other research organizations can effectively collaborate and securely share and leverage the vast amounts of data being generated in today’s farming operations.

As we gather with family and friends in the coming weeks and reflect back on the past year and begin looking forward to 2019, it is clear data will play an increasing role within the agricultural industry. With this in mind, it will be essential for farmers to have a private, secure, online way to store and manage their information.  If you would like to become more involved and help support the ADC’s efforts please contact us at [email protected].  

The purpose of the ADC

The most common questions about the Ag Data Coalition (ADC) are about the purpose of our organization, and how it’s different from any of the other ag data efforts in the industry. Much like a farmer intensely focused on their crops can sometimes lose track of current events, those of us heavily involved in the ADC effort, who work in precision ag daily, can forget that what we do and why we do it isn’t widely known. A recent editorial on Crop Life is a good reminder precision ag is a confusing and rapidly changing field. The article represents a prime example of why the Ag Data Coalition was formed just over a year ago as a joint effort of original equipment manufacturers (OEM), technology companies, land-grant universities, and farmer organizations.

The objective of ADC is to help growers get a better handle on their data, enabling  them to start using more of these new digital tools in a practical and collaborative way on their farm or agribusiness; enabling data sharing with their preferred business partners. Our strategy was to establish a data repository independent from any one single OEM, ag company or software system.  Our goal was not to disrupt or compete with any existing data management services; just to provide farmers, ag service providers, ag technology providers, and university researchers a secure, neutral option that could offer unique and valuable benefits only because of its independent framework.

Today, many growers and ag service providers are utilizing multiple systems to enable data transfer, translation, analysis, and sharing – and the ultimate path of the data, and the user agreements involved, can be overwhelming.

It’s for this reason that the ADC has developed a neutral, independent, farmer-centric data repository where farmers can securely store and control the information collected every day in the fields by their tractors, harvesters, aerial imaging and other devices. Over time, that data can then be scrubbed, synced and transmitted in an efficient and uniform way to third parties — whether they be researchers, crop insurance agents, government officials, farm managers, input providers or anyone else the farmer chooses.

The ADC data repository provides farmers as well as ag service providers a single common location that enables them to maintain  a backup of the historical raw files that they can then load into whatever system they choose. It also lets them store the output from those systems in a common repository and easily transfer any recommendations or prescriptions to their customers or advisors. There is no need for a service provider to manage an FTP server or track files down on different employees’ computers or hard drives. Additionally, if an employee leaves to work for a competitor, the customer still retains their ADC account and all that data won’t leave with the employee.

Getting data in one spot that a farmer can control is something fundamental to the success of the entire industry.

2017 Recap, 2018 Plans

With the holiday season here and another year coming to a close, we would like to look back at what the ADC has accomplished this year as well as look ahead to 2018 activities. Perhaps the most significant milestone for the ADC was officially forming our non-profit organization. This seemingly small act was the result of countless hours of discussion and research by the ADC founding members to determine what organizational structure was needed to meet all the needs we were trying to address. We were finally able to agree on a structure that would enable farmers to be in control of their data, industry participants to be involved in supporting the effort while keeping data secure and the organization neutral and independent, as well as enabling universities and other research institutions to participate. The formation of the non-profit was the first step in realizing this new organization. The second part was to create or partner with a data cooperative. We had planned to work with GiSC to form the Growers Ag Data Cooperative, but unfortunately this relationship was unable to be formed. However, both groups shared common goals and continue to work together on data education efforts for the industry.  While this was a setback, we are working on establishing a data cooperative that will be a sister organization to the current ADC non-profit and will be a focus during 2018.

Forming the ADC organization was not the only accomplishment in 2017, the pilot of the ADC data repository was completed providing a significant milestone on technology development. With this task completed, the ADC went “live” shortly after InfoAg offering accounts to the US ag industry. Using information collected during the pilot and by gathering feedback from some of our early adopters, we identified and implemented several improvements to the tool. We continue to refine and upgrade the system to mold the repository to meet the needs of all our various users.  During this process, the website was also revamped to provide additional information about the ADC and direct interested people and entities on how to purchase accounts; check it out http://agdatacoalition.org

The ADC continues to hold regular board meetings, several of which have involved outreach and coordination with other organizations. We have established a relationship with AgGateway through reciprocal memberships, have shared lessons learned with groups from places all over the globe including the US, Canada, the Netherlands, Australia, and New Zealand. Through these conversations, we confirmed the issues facing farmers in the US over data control are not unique and look forward to working with some of these organizations in the future to help ensure farmers globally are in control of their data.

We worked with Meister Media to host our first webinar that was hugely successful. There were people from all over the world registered to hear the conversation from the panel on ag data ownership and control. There were so many questions, the panel had to work for a couple days after the webinar to completely answer them. This is reassurance we are on the right path with the ADC and data control is an issue that concerns farmers and needs to be addressed across the industry. The board is also fielding regular calls from the media looking for insight into the ag data industry and how it impacts recent mergers and acquisitions in the industry, what it means for startups and innovation in the ag industry, and how all the different organizations and initiatives in the industry fit together.

2017 was a busy time getting the organization established and launching the data repository. As 2018 approaches, we plan to accelerate the activities that we feel we are at a crucial point in the ag industry. Farmers are starting to see the value in data as organizations like AgGateway and AEF (Agricultural industry Electronics Foundation) work to solve some of the interoperability issues that hinder broader adoption of many precision technologies. Additionally, ag tech investment continues to create a seemingly endless stream of startups focused on using a farmer’s data to provide insights improving overall farm operations. These startups are now also starting to be acquired by the larger, major players in the industry. The merger and acquisition of some large ag companies have also had a data component to this business decision, further illustrating the need for farmers to be in control of their data with a neutral, independent data repository.

To support farmers in 2018, we have several key areas of focus. First we will be looking to create the coop and add dedicated staff to help manage the operations of both organizations. The coop is needed to manage commercial operations and truly put growers in control of their data and the platform, also allowing the non-profit to focus more on education and outreach. With both organizations formed and dedicated staff, we also expect to see growth in both membership in the non-profit as more organizations sign on to support the effort as well as more farmers, service providers, and research organizations signing up for accounts.

Further, the ADC will continue our success with the data ownership webinar by hosting several more sessions with expert panels on similar data related topics. There is clearly a demand from all over the industry to better understand many of the issues facing growers as data becomes a more integral part of farm operations. We are also investigating options for different venues to further the discussion and other collaborations to help farmers understand the rapidly evolving ag data market.

If there are any questions, comments, suggestions you have or even just general feedback you can contact the ADC anytime over email at [email protected], through twitter @agdatacoaltion, or on LinkedIn at https://www.linkedin.com/company/10513332

Thanks for all you support in 2017 and we look forward to achieving even more in 2018.

The ADC Board of Directors

Ag Data Ownership & Control Webinar

The ADC has teamed with CropLife to host a webinar on ag data ownership and control Monday 13 November at 1:00 Central. A diverse group of experts on precision ag data will be discussing the complexities of ag data ownership and control. More and more data is being generated every day on the farm and it has value not only to farmers by better informing decisions to drive efficiency in their operations, but also to a growing list of companies and other organizations who have their own uses for the data.

The group will explain some of the issues facing the industry today and review some scenarios that may play out depending on who has access to which information. The discussion promises to be very interesting and will no doubt highlight the need for a neutral, independent data repository like the one the ADC provides.

Panel members include:

  • Don Bierman, CEO of Crop IMS and ADC vice-president, from the perspective of an ag service provider as well as how the ADC is helping growers take control of their data.
  • Larkin Martin, Alabama cotton, corn, soybean, and wheat farmer, an active user of multiple data sources in her operation.
  • Todd Janzen with the Ag Data Transparency Evaluator, providing his knowledge and legal perspectives.
  • Shannon Ferrell, Oklahoma State University, relating experience within the university/extension area working with farmer data and its economic impacts.

If you are interested in hearing the discussion, register for the webinar today!

ADC Data Repository Now Live

We are excited to announce the ADC data repository is now available for farmers, ag service providers, and researchers to sign up for their own accounts. The ADC team met with several interested companies, service providers, and universities recently at InfoAg to share the news. There was a lot of positive feedback and excitement about the system becoming available to help put farmers in control of their data.

For anyone interested in signing up for an account, simply visit the AgDataCoalition.org website and click the link to sign up. Also be sure to visit the ADC website, Twitter channel (@agdatacoalition) and LinkedIn page for more frequent updates now that the non-profit organization is officially founded and the system is live.

We would also like to thank all the participants in our pilot program last year. Thanks to their feedback, we identified four bundles of enhancements we will be rolling out in the platform to make controlling data even easier for users. Item one is already underway with our development team and we are working on scheduling the work for item two next. Watch for future announcements when the work is live in the system.

1. Additional admin controls for users who need to permission access based on different sites/locations
2. Additional user management tools for managing, modifying or updating accounts
3. Accounts tailored specifically for research project participants and an overall project manager account
4. Additional flexibility and options for grower accounts sponsored by their ag service provider or retailer

Thanks again for all of your support This is truly a turning point for the ag industry – enabling farmers to take control of their data in a neutral, independent data repository. If you have any questions, comments, or feedback, feel free to drop us a note at [email protected]

ADC at InfoAg 2017

It has been a busy time at the Agricultural Data Coalition, ADC. We successfully completed our pilot phase with the new ADC data repository tool and completed the founding and initial organization of the non-profit. We also began working on developing a relationship with the Growers Ag Data Cooperative, with the intent to align our efforts more closely in the future. In the short term the ADC is in the process of enhancing the platform based on feedback from the farmers, ag service providers, and universities involved in the pilot. We are also planning a webinar to discuss issues facing farmers and researchers working with on-farm data.

With all this going on, we wanted to all that have signed up for up dates on ADC activities. We know everyone is interested in putting farmers in the driver’s seat when it comes to the data generated and used on their farms, as well as ensuring universities and other research organizations have a reliable, secure means to access on-farm data.

If you are interested in finding out more about what ADC is working on, benefits of joining the non-profit, or when and how you will be able to obtain your own data repository account–we will be at InfoAg. ADC will not have a booth this year but several board members will be in attendance and would be happy to give you an update.  So please feel free to contact them directly or catch them during a session break. Additionally, we can accomodate small group meetings and discussions, please contact Don Bierman or email [email protected] to schedule a meeting time onsite at Union Station in St. Louis.

We look forward to seeing a lot of you at InofAg, and if you have any questions, don’t hesitate to contact us at [email protected].

ADC board members attending InfoAg:

Amy Winstead – Agri AFC, Bruce Erickson – Purdue University, Don Bierman – Crop IMS, Joe Luck – University of Nebraska, John Fulton – The Ohio State, Mike Gomes – Topcon, Scott Schearer – The Ohio State

Ag Data Coalition Adds Agri-AFC as Founding Member

(SPRINGFIELD, Ohio) – Alabama-based Agri-AFC, LLC, added its name today to the list of founding members of the Agricultural Data Coalition (ADC), becoming the 14th organization to join the group since its formation this spring.

ADC’s mission is to build a secure repository where farmers can manage the volumes of production information generated by their farms. ADC expects Agri-AFC – a farm input retailer with locations in Alabama, Georgia, southern Mississippi and the Florida Panhandle – to provide valuable insights to help improve its technology and increase availability and adoption in key areas.

“Agri-AFC has a proven track record of helping growers maximize efficiency and profitability. And as a data-driven organization with a focus on innovation, constant improvement, and putting growers first, they are a perfect fit for ADC,” explained Matt Bechdol, the group’s interim executive director. “We’re proud to have Agri-AFC as a member and look forward to working with them as we enter the next phase of the effort and prepare to come to market.”

Bechdol noted that the ADC is currently conducting a pilot program of its data management system and hopes to publicly launch its technology before the year’s end.

“Understanding and managing the multitude of technology offerings and the flood of data that is now generated on-farm are the biggest challenges we encounter with our producers,” said Amy Winstead, Agri-AFC’s director of ag technologies. “Partnering with the ADC will enable us to continue working with our growers to manage and catalog their data while aligning with our goal to provide a seamless and transparent approach to ‘Big Data’ for our customers.”

She also explained that, to date, farmers have been unable to tap their farm data’s full potential because of hurdles to housing and transmitting information in a centralized and flexible way.

(more…)

Iowa AgSTATE Joins ADC as Founding Member

(SPRINGFIELD, OH) – The Agricultural Data Coalition (ADC) continues to expand its leadership diversity, as it announced today the addition of Iowa AgSTATE to its group of founding members. Iowa AgSTATE has been actively involved in digital agriculture strategy and education and summarized its work in a 2014 report on the Digital Transformation of Row Crop Agriculture.

“Independent, farmer-controlled solutions for data management is a key enabler for digital agriculture benefits to reach all producers,” said Matt Darr, member of the Iowa AgSTATE Digital Agriculture Task Force. “We look forward to contributing to the mission of the ADC and collaborating on national solutions for ag data management.”

Formed in 1997, Iowa AgSTATE (Agricultural Strategic Thinkers Acting Together Effectively) involves leadership of all segments of Iowa agriculture to develop a proactive, futuristic vision for Iowa agriculture and action plan to help make that vision a reality. Members include Agribusiness Association of Iowa; Iowa State Dairy Association; Iowa Cattlemen’s Association; Iowa Corn Growers Association; Iowa Corn Promotion Board; Iowa Farm Bureau Federation; Iowa Institute for Cooperatives; Iowa Pork Producers Association; Iowa Poultry Association; Iowa Soybean Association; Iowa State University College of Agriculture and Life Sciences; and Iowa Turkey Federation.

“We are proud to welcome Iowa AgSTATE to our roster of founding members,” said ADC interim executive director Matt Bechdol. “Our goal is to help farmers harness the full potential of the data they collect every day in the field in order to increase efficiencies, and fuel future growth and innovation. The Iowa AgSTATE group has been ahead of many in this area and the insight they bring to our coalition will help ensure we continue our focus on a diverse market, and create a product that meets the needs of all.”

(more…)

ADC Enters Pilot Phase for Farm Data Repository

(SPRINGFIELD, OH) – The development of a secure, online repository where farmers can store, manage and control the information generated on their farms took a major step forward as the Agricultural Data Coalition (ADC) initiated its pilot to demonstrate how a neutral repository of data would work to connect data among growers, service providers, and machines.

A group of growers, service providers, and university researchers from different parts of the country, representing numerous commodities, are participating in the testing phase to offer feedback on pace and direction for ADC’s data bank before it is officially offered to the entire farming community.

“This is an exciting phase for ADC, and underlines that a focused approach to solving key basic data challenges in appreciated” explained Matt Bechdol, the ADC’s interim executive director.

Bechdol described the new repository like a bank. Farmers deposit, or upload, data to a secure cloud where they can organize, manage, and share it. When farmers want to share information – with service providers, insurance agents, researchers, input providers or farm managers, for example – they authorize ADC to transmit it with the click of a button. Service providers can also make deposits with the grower’s permission.

(more…)

← Previous Page