IBM Watson

From Seed to Server: The Evolution of Modern Agriculture

By Mark Gildersleeve, vice president and Head of Business Solutions, The Weather Company, an IBM Business

When you think about artificial intelligence (AI), you probably don’t imagine using it for a farm. But you should: this week, IBM is bringing data and AI together with the global release of the Watson Decision Platform for Agriculture to help growers and enterprises make better decisions. This new platform is an innovation that draws upon IBM’s most advanced capabilities in AI, analytics, IoT, Cloud, and weather to create a suite of solutions that span the farm-to-fork ecosystem.

Farming has always been a complex undertaking that requires growers to manage an interconnected web of pre-season and in-season decisions while at the mercy of mother nature.  With the explosion of data from farm equipment, environmental sensors, and remote input, it’s impractical to rely on intuition or traditional technology to understand what drives variation in yield or provide guidance to growers. IBM is filling this gap by applying Watson AI to help growers  make confident, evidence-based decisions.

In parallel, food companies are looking for ways to meet consumer demand for better food quality and sustainability. IBM’s solution will bridge food companies and their grower suppliers to better manage the inputs and farming practices that can deliver on the promise of improved food quality.  IBM is drawing on its experience with improving  products ranging from wine to tomatoes to make this vision a reality.

At the core of IBM’s Platform is the Electronic Field Record which is the collection and integration point for the many disparate sources of IoT and practice data that, together, capture the current and historical state of the farm. It’s analogous to the Electronic Medical Record in Healthcare and is the “digital twin” of the physical farm and everything that happens on it. Growers are already benefiting from IBM’s efforts to integrate data sources while extracting insights from them. “Until now, nobody has tackled putting all this information into one place,” says 3rd-generation farmer Roric Paulman. “I’ve got 40 different ag apps on my phone. It just stops being useful.”

Paulman has 10,000 acres under cultivation in Nebraska and he generates one terabyte of data every month. IBM’s new platform allows him to bring everything together on his phone so he has a powerful, unified view of his farm.

For Paulman and other farmers, bringing AI to bear on data provides startling new powers. Growers can now film a field of corn from a drone and use Watson-enabled visual recognition analysis to identify crop disease or a pest infestation. The app also allows the grower to photograph plants up-close and have Watson identify the exact pest or disease that is placing stress on the crop. On Paulman’s farm, an agronomist currently visits once a week to analyze infestations and blight. Now, with a simple photo, Paulman can immediately find out what type of pest is affecting his plants and he can take remediation action.

“That means I can react in real-time and won’t lose yield waiting for the agronomist,” Paulman says. It also allows him to better target pesticide use, reducing environmental impact and lowering cost.

For large food producers, the platform offers an opportunity to “see” the fields in a new way. Food producers will have visibility to the likely yield from each supplier’s farm and can plan the logistics of when they want each farmer to deliver their supply. That provides new transparency to an otherwise inefficient system.

The platform also seeks to anticipate problems before they start. The platform helps farmers understand critical factors such as soil temperature and moisture levels, crop stress, pest and disease risk and identification, yield predictions, and alerts. That helps inform decisions like irrigation, planting, fertilization, worker safety, trading, and pest and disease eradication.

One of the biggest challenges farmers face is knowing when exactly to sell their crops. Prices fluctuate constantly and this platform offers a tool that marshals huge amounts of pricing data—from the local grain elevator to the futures markets—and recommends the best time to sell a crop in order to maximize profit. It’s the type of data gathering and analysis that would be impossible without AI and analytics

“I’ve been waiting for something like this,” Paulman says. “IBM has independence. They’re not trying to sell me more fertilizer or machines. They don’t have a horse in the race. It’s a trust thing.”

The grower application is just one piece of IBM’s larger effort to improve agriculture. The platform can help a full range of ecosystem participants such as agronomists, input providers, equipment manufacturers, traders, lenders, crop insurers, and governments make more confident decisions specific to their own roles.

Many of the analytics delivered by the Platform are generated by IBM PAIRS Geoscope which is a cloud-based innovation of IBM Research that can quickly provide contextual information about a specific location using geospatial-temporal information. Using machine learning techniques and analytics on satellite imagery, weather data, census data, land use and business location data, it can help companies make predictions about the future of their farms.

The new IBM Watson Decision Platform for Agriculture introduction is complementary to the existing Blockchain-based IBM Food Trust capabilities which facilitate food traceability across each step of the food supply such as origin, processing data, and shipping details.

IBM is partnering with a host of organizations to deliver the decision support capabilities of the Platform. For example:

  • In India, IBM Research has partnered with NITI Aayog, a government think tank to explore how AI can be used to leveraging AI to issue early warning on pest and disease outbreaks.
  • Main Street Data provides its Validator capabilities to benchmark yield against output from comparable fields and its MarketVision capabilities to help growers time their crop sales to maximize profit
  • In Kenya, IBM scientists in Nairobi partnered with Twiga Foods to build and test a blockchain-enabled microfinance lending platform which helps small farmers and food vendors get access to lending capital.
  • GiSC is a data cooperative run by growers for growers that integrates with the Platform to help users analyze their data to get more value from it. 

In each case, around the world, AI is helping feed us while helping farmers and the entire food chain to become more efficient and deliver better quality and sustainability.  

Image: Today, IBM is announcing the Watson Decision Platform for Agriculture, a suite of agribusiness tools and solutions to help growers leverage the power of AI to make better, more informed decisions. In this image, yield forecast projects crop output in specific field sections, to help growers estimate future harvest. National models by crop and region help enterprises make better financial services decisions. (Source: IBM)