In today’s global agricultural system, we are collecting, sorting, analyzing, and acting on data. Data mining is now integral in the universal effort to improve the quantity, quality, and sustainability of our food supply—now and into the future.

Feeding the world while protecting the environment is a science— a data-driven science. Data allows us to find practical solutions that deliver better results across every segment of the food chain.  While the role of data and intelligent data management may seem to be invisible to most of us, it is essential to assuring that today’s consumers—and future generations—don’t just eat, but thrive.

Statistics on the amount of data being created every day is mind-boggling

Many data science experts support the notion that we risk “drowning in data,” when what we really want to do is “swim in knowledge.”  Data scientist Abdelbarre Chafik highlights that every day, more than 2.5 quintillion bytes of data are created. (That is 2,500,000,000,000,000,000 bytes!)

AppDeveloper magazine recently stated,

Bits and Bytes and the Agricultural Sector

What has changed, however, is the sheer volume and variety of data that is now available to the agricultural sector through the emergence of new information technology. In order to use data effectively, we need to be collecting with purpose.

Collecting data is to drive better decision-making at every step along the food chain.  What’s more— this emerging focus on data management is rapidly becoming a core competency for all members of the food system.  Data holds the potential to make every segment of the food chain work better.

Because this is a new and rapidly growing market, many companies are trying to find their niche. It will be very interesting to see how this market place develops and which agriculture and data companies are able to work together in order to find the best solutions.

There are many companies competing in the agricultural data space. Source: AGC Partners

Data isn’t new to agriculture

Farm data has been collected for centuries— first as hieroglyphics etched in stone, followed by hand-written entries in dusty ledgers. Data is stored everywhere: in grain elevators, on commodity exchanges, in the basement of barns, on the rolling handwritten inventories of food stores, and countless other places along the food chain.

Farmers used basic facts and figures about input costs, pest controls, machinery expenses, yields, market bids, etc. to help themselves better produce their crop in future seasons. Commodity merchants tracked market trends, historic demand, crop estimates, stocks and other factors important to buying and selling farm products at a profit. Food manufacturers took careful note of stocks, purchase needs, ingredient prices, market demand and more. Food consumers also had a role to play in data management, even if only to stay within their household budget.

Today, the difference is that all of this information from the farmers, merchants, distributors, food processors, and the grocery store can be loaded into algorithms to provide consolidated information from farmer to consumer.

But, at every step along the way— all the players have different objectives. The farmers want to grow their crops with the best yield and the least inputs (pesticides, herbicides, and water). The commodity traders want to buy low and sell high. The food processor wants to buy food from the farmer and efficiently process it into a different product (for example soybeans into soybean oil.) And the consumer wants affordable, healthy, and safe food that is accessible daily.

Let’s imagine a few things can be done by harvesting this volume of data

As a consumer:

• Scan the label on your produce or fruit to learn about the farmer who grew your food.
• Scan the label on your meat packaging and know exactly what the cow was fed throughout its life.
• Supermarkets can manage their end of life products and notify consumers and food banks who could use them.
• Restaurants can use Food Genius to gather the popularity of over 22 million menu items to see what sells to which type of consumer – and then tailor their own menu.

As a farmer:

• Know the exact locations on the fields that have heavy water, normal, or drought conditions and manage pesticide applications.
• Know the approximate yield, around the globe, of their crop so they can decide whether to sell their crop at harvest or store it on site until prices are more favorable.
• Know the exact moment to plant their crops through weather and soil analytics.
• Program the driver-less tractor to manage the fields.
• Purchase the right seed each year for today’s climate and soil.
• Use big data to provide crop insurance for farmers regarding crop yields and weather patterns.

As the food producer:

• Be able to instantly track all the ingredients and their prices that come from around the world.
• Have instant access to sales at the grocery store so inventory can be managed accordingly.
• Know about every animal that is purchased for your farm and have access to what it was fed pre-purchase.
• Streamline transportation logistics in order to get optimal pricing to send product via rail, ship, or truck.
• Increase understanding of all food inputs to effectively manage margins.

How can we use data to improve food sustainability?

As we discussed in Farming from the Thermosphere, technology is becoming increasingly important in farming practices. Data becomes knowledge, knowledge becomes insight, and insight should inevitably become action.

But of all the data that is captured, it is important to discern what kinds of data are important to agriculture. While the internet and subsequently the Internet of Things (IoT) has allowed for better data collection, there is room for improvement. Here are some areas within the food supply chain that will benefit from improved data collection and management:

One of the most important questions to be resolved in a brave new data-driven world is— what we do with the data once we have it?

Many companies are trying to answer this question. In fact, a 2016 Global Opportunity Report cited “smart farming” as the top-ranked opportunity.

Farmers Edge specializes in precision agronomy and helps enable farmers to better monitor their fields and collect effective data. IBM’s artificial intelligence product, Watson (IoT), is attempting to transform precision agriculture by utilizing predictive weather analytics to help farmers. The platform also offers real-time plant and field monitoring. Bayer Digital Farming uses Amazon Web Service to help feed a growing population. In 2014, John Deere introduced SeedStar a mobile application that gives farmers a row-by-row assessment of their field and its performance. Moreover, John Deere recently (Sept 2017) acquired See and Spray Robotics, which sees, diagnoses, and executes on something as small as seedlings. Monsanto bought The Climate Corporation, which uses big data to predict weather and climate change. Cargill invested in Descartes Labs, which uses satellite imagery to help with crop forecasting. U.S. Foods bought Food Genius— and the list goes on…

Source: IBM

As technology enables the creation of larger amounts of data, determining which data is relevant, complete, and honest grows more difficult. Unfortunately, it is easy to twist data to support a pre-conceived idea, and data alone is often fuel for argument and debate.